Request 3848 (accepted)

QtAV.changes Changed

QtAV.spec Changed

@@ -19,7 +19,7 @@
 %define sover 1
 %define ffmpeg_includedir -I%(pkg-config --variable=includedir libavutil)
 Name:           QtAV
-Version:        1.11.0
+Version:        1.12.0
 Release:        0
 Summary:        Qt multimedia framework
 License:        LGPL-2.1+ and GPL-3.0
@@ -40,6 +40,7 @@
 BuildRequires:  pkgconfig(Qt5Quick)
 BuildRequires:  pkgconfig(Qt5Widgets)
 BuildRequires:  pkgconfig(Qt5Sql)
+BuildRequires:  pkgconfig(Qt5Svg)
 BuildRequires:  pkgconfig(egl)
 BuildRequires:  pkgconfig(libass)
 BuildRequires:  pkgconfig(libavcodec)
@@ -64,23 +65,23 @@
 you to write a player with less effort than ever before.
 
 Features include:
-   * Hardware decoding suppprt: DXVA2, VAAPI, VDA, CedarX, CUDA
-   * OpenGL and ES2 support for Hi10P and other 16-bit YUV videos
-   * Real time preview
-   * Video capture in rgb and yuv format
-   * OSD and custom filters
-   * Subtitle
-   * Transform video using GraphicsItemRenderer. (rotate, shear, etc)
-   * Playing frame by frame (currently support forward playing)
-   * Playback speed control
-   * Variant streams: locale file, http, rtsp, etc.
-   * Audio channel, tracks and external audio tracks
-   * Dynamically change render engine when playing
-   * Multiple video outputs for 1 player
-   * Region of interest(ROI), i.e. video cropping
-   * Video eq: brightness, contrast, saturation, hue
-   * QML support as a plugin. Most playback APIs are compatible with
-     QtMultiMedia module
+    * Hardware decoding suppprt: DXVA2, VAAPI, VDA, CedarX, CUDA
+    * OpenGL and ES2 support for Hi10P and other 16-bit YUV videos
+    * Real time preview
+    * Video capture in rgb and yuv format
+    * OSD and custom filters
+    * Subtitle
+    * Transform video using GraphicsItemRenderer. (rotate, shear, etc)
+    * Playing frame by frame (currently support forward playing)
+    * Playback speed control
+    * Variant streams: locale file, http, rtsp, etc.
+    * Audio channel, tracks and external audio tracks
+    * Dynamically change render engine when playing
+    * Multiple video outputs for 1 player
+    * Region of interest(ROI), i.e. video cropping
+    * Video eq: brightness, contrast, saturation, hue
+    * QML support as a plugin. Most playback APIs are compatible with
+      QtMultiMedia module
 
 %package -n     lib%{name}%{sover}
 Summary:        QtAV library
@@ -115,7 +116,6 @@
 Group:          Productivity/Multimedia/Video/Players
 Requires:       %{name}-qml = %{version}
 Requires:       lib%{name}Widgets%{sover} = %{version}
-Requires:       libQt5Svg5
 Requires:       libqt5-qtquickcontrols
 
 %description -n	%{name}-players

QtAV-1.11.0.tar.gz/src/cuda/dllapi/cuda.h Deleted

@@ -1,10817 +0,0 @@
-/*
- * Copyright 1993-2014 NVIDIA Corporation. All rights reserved.
- *
- * NOTICE TO LICENSEE:
- *
- * This source code and/or documentation ("Licensed Deliverables") are
- * subject to NVIDIA intellectual property rights under U.S. and
- * international Copyright laws.
- *
- * These Licensed Deliverables contained herein is PROPRIETARY and
- * CONFIDENTIAL to NVIDIA and is being provided under the terms and
- * conditions of a form of NVIDIA software license agreement by and
- * between NVIDIA and Licensee ("License Agreement") or electronically
- * accepted by Licensee. Notwithstanding any terms or conditions to
- * the contrary in the License Agreement, reproduction or disclosure
- * of the Licensed Deliverables to any third party without the express
- * written consent of NVIDIA is prohibited.
- *
- * NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
- * LICENSE AGREEMENT, NVIDIA MAKES NO REPRESENTATION ABOUT THE
- * SUITABILITY OF THESE LICENSED DELIVERABLES FOR ANY PURPOSE. IT IS
- * PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED WARRANTY OF ANY KIND.
- * NVIDIA DISCLAIMS ALL WARRANTIES WITH REGARD TO THESE LICENSED
- * DELIVERABLES, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY,
- * NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
- * NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
- * LICENSE AGREEMENT, IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY
- * SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, OR ANY
- * DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
- * WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
- * ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
- * OF THESE LICENSED DELIVERABLES.
- *
- * U.S. Government End Users. These Licensed Deliverables are a
- * "commercial item" as that term is defined at 48 C.F.R. 2.101 (OCT
- * 1995), consisting of "commercial computer software" and "commercial
- * computer software documentation" as such terms are used in 48
- * C.F.R. 12.212 (SEPT 1995) and is provided to the U.S. Government
- * only as a commercial end item. Consistent with 48 C.F.R.12.212 and
- * 48 C.F.R. 227.7202-1 through 227.7202-4 (JUNE 1995), all
- * U.S. Government End Users acquire the Licensed Deliverables with
- * only those rights set forth herein.
- *
- * Any use of the Licensed Deliverables in individual and commercial
- * software must include, in the user documentation and internal
- * comments to the code, the above Disclaimer and U.S. Government End
- * Users Notice.
- */
-
-#ifndef __cuda_cuda_h__
-#define __cuda_cuda_h__
-
-#include <stdlib.h>
-
-/**
- * CUDA API versioning support
- */
-#if defined(CUDA_FORCE_API_VERSION)
- #if (CUDA_FORCE_API_VERSION == 3010)
- #define __CUDA_API_VERSION 3010
- #else
- #error "Unsupported value of CUDA_FORCE_API_VERSION"
- #endif
-#else
- #define __CUDA_API_VERSION 7050
-#endif /* CUDA_FORCE_API_VERSION */
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || defined(CUDA_API_PER_THREAD_DEFAULT_STREAM)
- #define __CUDA_API_PER_THREAD_DEFAULT_STREAM
- #define __CUDA_API_PTDS(api) api ## _ptds
- #define __CUDA_API_PTSZ(api) api ## _ptsz
-#else
- #define __CUDA_API_PTDS(api) api
- #define __CUDA_API_PTSZ(api) api
-#endif
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION >= 3020
- #define cuDeviceTotalMem cuDeviceTotalMem_v2
- #define cuCtxCreate cuCtxCreate_v2
- #define cuModuleGetGlobal cuModuleGetGlobal_v2
- #define cuMemGetInfo cuMemGetInfo_v2
- #define cuMemAlloc cuMemAlloc_v2
- #define cuMemAllocPitch cuMemAllocPitch_v2
- #define cuMemFree cuMemFree_v2
- #define cuMemGetAddressRange cuMemGetAddressRange_v2
- #define cuMemAllocHost cuMemAllocHost_v2
- #define cuMemHostGetDevicePointer cuMemHostGetDevicePointer_v2
- #define cuMemcpyHtoD __CUDA_API_PTDS(cuMemcpyHtoD_v2)
- #define cuMemcpyDtoH __CUDA_API_PTDS(cuMemcpyDtoH_v2)
- #define cuMemcpyDtoD __CUDA_API_PTDS(cuMemcpyDtoD_v2)
- #define cuMemcpyDtoA __CUDA_API_PTDS(cuMemcpyDtoA_v2)
- #define cuMemcpyAtoD __CUDA_API_PTDS(cuMemcpyAtoD_v2)
- #define cuMemcpyHtoA __CUDA_API_PTDS(cuMemcpyHtoA_v2)
- #define cuMemcpyAtoH __CUDA_API_PTDS(cuMemcpyAtoH_v2)
- #define cuMemcpyAtoA __CUDA_API_PTDS(cuMemcpyAtoA_v2)
- #define cuMemcpyHtoAAsync __CUDA_API_PTSZ(cuMemcpyHtoAAsync_v2)
- #define cuMemcpyAtoHAsync __CUDA_API_PTSZ(cuMemcpyAtoHAsync_v2)
- #define cuMemcpy2D __CUDA_API_PTDS(cuMemcpy2D_v2)
- #define cuMemcpy2DUnaligned __CUDA_API_PTDS(cuMemcpy2DUnaligned_v2)
- #define cuMemcpy3D __CUDA_API_PTDS(cuMemcpy3D_v2)
- #define cuMemcpyHtoDAsync __CUDA_API_PTSZ(cuMemcpyHtoDAsync_v2)
- #define cuMemcpyDtoHAsync __CUDA_API_PTSZ(cuMemcpyDtoHAsync_v2)
- #define cuMemcpyDtoDAsync __CUDA_API_PTSZ(cuMemcpyDtoDAsync_v2)
- #define cuMemcpy2DAsync __CUDA_API_PTSZ(cuMemcpy2DAsync_v2)
- #define cuMemcpy3DAsync __CUDA_API_PTSZ(cuMemcpy3DAsync_v2)
- #define cuMemsetD8 __CUDA_API_PTDS(cuMemsetD8_v2)
- #define cuMemsetD16 __CUDA_API_PTDS(cuMemsetD16_v2)
- #define cuMemsetD32 __CUDA_API_PTDS(cuMemsetD32_v2)
- #define cuMemsetD2D8 __CUDA_API_PTDS(cuMemsetD2D8_v2)
- #define cuMemsetD2D16 __CUDA_API_PTDS(cuMemsetD2D16_v2)
- #define cuMemsetD2D32 __CUDA_API_PTDS(cuMemsetD2D32_v2)
- #define cuArrayCreate cuArrayCreate_v2
- #define cuArrayGetDescriptor cuArrayGetDescriptor_v2
- #define cuArray3DCreate cuArray3DCreate_v2
- #define cuArray3DGetDescriptor cuArray3DGetDescriptor_v2
- #define cuTexRefSetAddress cuTexRefSetAddress_v2
- #define cuTexRefGetAddress cuTexRefGetAddress_v2
- #define cuGraphicsResourceGetMappedPointer cuGraphicsResourceGetMappedPointer_v2
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION >= 3020 */
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION >= 4000
- #define cuCtxDestroy cuCtxDestroy_v2
- #define cuCtxPopCurrent cuCtxPopCurrent_v2
- #define cuCtxPushCurrent cuCtxPushCurrent_v2
- #define cuStreamDestroy cuStreamDestroy_v2
- #define cuEventDestroy cuEventDestroy_v2
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION >= 4000 */
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION >= 4010
- #define cuTexRefSetAddress2D cuTexRefSetAddress2D_v3
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION >= 4010 */
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION >= 6050
- #define cuLinkCreate cuLinkCreate_v2
- #define cuLinkAddData cuLinkAddData_v2
- #define cuLinkAddFile cuLinkAddFile_v2
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION >= 6050 */
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION >= 6050
- #define cuMemHostRegister cuMemHostRegister_v2
- #define cuGraphicsResourceSetMapFlags cuGraphicsResourceSetMapFlags_v2
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION >= 6050 */
-
-#if !defined(__CUDA_API_VERSION_INTERNAL)
-#if defined(__CUDA_API_VERSION) && __CUDA_API_VERSION >= 3020 && __CUDA_API_VERSION < 4010
- #define cuTexRefSetAddress2D cuTexRefSetAddress2D_v2
-#endif /* __CUDA_API_VERSION && __CUDA_API_VERSION >= 3020 && __CUDA_API_VERSION < 4010 */
-#endif /* __CUDA_API_VERSION_INTERNAL */
-
-#if defined(__CUDA_API_PER_THREAD_DEFAULT_STREAM)
- #define cuMemcpy __CUDA_API_PTDS(cuMemcpy)
- #define cuMemcpyAsync __CUDA_API_PTSZ(cuMemcpyAsync)
- #define cuMemcpyPeer __CUDA_API_PTDS(cuMemcpyPeer)
- #define cuMemcpyPeerAsync __CUDA_API_PTSZ(cuMemcpyPeerAsync)
- #define cuMemcpy3DPeer __CUDA_API_PTDS(cuMemcpy3DPeer)
- #define cuMemcpy3DPeerAsync __CUDA_API_PTSZ(cuMemcpy3DPeerAsync)
-
- #define cuMemsetD8Async __CUDA_API_PTSZ(cuMemsetD8Async)
- #define cuMemsetD16Async __CUDA_API_PTSZ(cuMemsetD16Async)
- #define cuMemsetD32Async __CUDA_API_PTSZ(cuMemsetD32Async)
- #define cuMemsetD2D8Async __CUDA_API_PTSZ(cuMemsetD2D8Async)
- #define cuMemsetD2D16Async __CUDA_API_PTSZ(cuMemsetD2D16Async)
- #define cuMemsetD2D32Async __CUDA_API_PTSZ(cuMemsetD2D32Async)
-
- #define cuStreamGetPriority __CUDA_API_PTSZ(cuStreamGetPriority)
- #define cuStreamGetFlags __CUDA_API_PTSZ(cuStreamGetFlags)
- #define cuStreamWaitEvent __CUDA_API_PTSZ(cuStreamWaitEvent)
- #define cuStreamAddCallback __CUDA_API_PTSZ(cuStreamAddCallback)
- #define cuStreamAttachMemAsync __CUDA_API_PTSZ(cuStreamAttachMemAsync)
- #define cuStreamQuery __CUDA_API_PTSZ(cuStreamQuery)
- #define cuStreamSynchronize __CUDA_API_PTSZ(cuStreamSynchronize)
- #define cuEventRecord __CUDA_API_PTSZ(cuEventRecord)
- #define cuLaunchKernel __CUDA_API_PTSZ(cuLaunchKernel)
- #define cuGraphicsMapResources __CUDA_API_PTSZ(cuGraphicsMapResources)
- #define cuGraphicsUnmapResources __CUDA_API_PTSZ(cuGraphicsUnmapResources)
-#endif
-
-/**
- * \file cuda.h
- * \brief Header file for the CUDA Toolkit application programming interface.
- *
- * \file cudaGL.h
- * \brief Header file for the OpenGL interoperability functions of the
- * low-level CUDA driver application programming interface.
- *
- * \file cudaD3D9.h
- * \brief Header file for the Direct3D 9 interoperability functions of the
- * low-level CUDA driver application programming interface.
- */
-
-/**
- * \defgroup CUDA_TYPES Data types used by CUDA driver
- * @{
- */
-
-/**
- * CUDA API version number
- */
-#define CUDA_VERSION 7050
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/**
- * CUDA device pointer
- * CUdeviceptr is defined as an unsigned integer type whose size matches the size of a pointer on the target platform.
- */ 
-#if __CUDA_API_VERSION >= 3020
-
-#if defined(_WIN64) || defined(__LP64__)
-typedef unsigned long long CUdeviceptr;
-#else
-typedef unsigned int CUdeviceptr;
-#endif
-
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-typedef int CUdevice; /**< CUDA device */
-typedef struct CUctx_st *CUcontext; /**< CUDA context */
-typedef struct CUmod_st *CUmodule; /**< CUDA module */
-typedef struct CUfunc_st *CUfunction; /**< CUDA function */
-typedef struct CUarray_st *CUarray; /**< CUDA array */
-typedef struct CUmipmappedArray_st *CUmipmappedArray; /**< CUDA mipmapped array */
-typedef struct CUtexref_st *CUtexref; /**< CUDA texture reference */
-typedef struct CUsurfref_st *CUsurfref; /**< CUDA surface reference */
-typedef struct CUevent_st *CUevent; /**< CUDA event */
-typedef struct CUstream_st *CUstream; /**< CUDA stream */
-typedef struct CUgraphicsResource_st *CUgraphicsResource; /**< CUDA graphics interop resource */
-typedef unsigned long long CUtexObject; /**< An opaque value that represents a CUDA texture object */
-typedef unsigned long long CUsurfObject; /**< An opaque value that represents a CUDA surface object */
-
-typedef struct CUuuid_st { /**< CUDA definition of UUID */
- char bytes[16];
-} CUuuid;
-
-
-#if __CUDA_API_VERSION >= 4010
-
-/**
- * CUDA IPC handle size 
- */
-#define CU_IPC_HANDLE_SIZE 64
-
-/**
- * CUDA IPC event handle
- */
-typedef struct CUipcEventHandle_st {
- char reserved[CU_IPC_HANDLE_SIZE];
-} CUipcEventHandle;
-
-/**
- * CUDA IPC mem handle
- */
-typedef struct CUipcMemHandle_st {
- char reserved[CU_IPC_HANDLE_SIZE];
-} CUipcMemHandle;
-
-/**
- * CUDA Ipc Mem Flags
- */
-typedef enum CUipcMem_flags_enum {
- CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS = 0x1 /**< Automatically enable peer access between remote devices as needed */
-} CUipcMem_flags;
-
-#endif
-
-/**
- * CUDA Mem Attach Flags
- */
-typedef enum CUmemAttach_flags_enum {
- CU_MEM_ATTACH_GLOBAL = 0x1, /**< Memory can be accessed by any stream on any device */
- CU_MEM_ATTACH_HOST = 0x2, /**< Memory cannot be accessed by any stream on any device */
- CU_MEM_ATTACH_SINGLE = 0x4 /**< Memory can only be accessed by a single stream on the associated device */
-} CUmemAttach_flags;
-
-/**
- * Context creation flags
- */
-typedef enum CUctx_flags_enum {
- CU_CTX_SCHED_AUTO = 0x00, /**< Automatic scheduling */
- CU_CTX_SCHED_SPIN = 0x01, /**< Set spin as default scheduling */
- CU_CTX_SCHED_YIELD = 0x02, /**< Set yield as default scheduling */
- CU_CTX_SCHED_BLOCKING_SYNC = 0x04, /**< Set blocking synchronization as default scheduling */
- CU_CTX_BLOCKING_SYNC = 0x04, /**< Set blocking synchronization as default scheduling
- * \deprecated This flag was deprecated as of CUDA 4.0
- * and was replaced with ::CU_CTX_SCHED_BLOCKING_SYNC. */
- CU_CTX_SCHED_MASK = 0x07, 
- CU_CTX_MAP_HOST = 0x08, /**< Support mapped pinned allocations */
- CU_CTX_LMEM_RESIZE_TO_MAX = 0x10, /**< Keep local memory allocation after launch */
- CU_CTX_FLAGS_MASK = 0x1f
-} CUctx_flags;
-
-/**
- * Stream creation flags
- */
-typedef enum CUstream_flags_enum {
- CU_STREAM_DEFAULT = 0x0, /**< Default stream flag */
- CU_STREAM_NON_BLOCKING = 0x1 /**< Stream does not synchronize with stream 0 (the NULL stream) */
-} CUstream_flags;
-
-/**
- * Legacy stream handle
- *
- * Stream handle that can be passed as a CUstream to use an implicit stream
- * with legacy synchronization behavior.
- *
- * See details of the \link_sync_behavior
- */
-#define CU_STREAM_LEGACY ((CUstream)0x1)
-
-/**
- * Per-thread stream handle
- *
- * Stream handle that can be passed as a CUstream to use an implicit stream
- * with per-thread synchronization behavior.
- *
- * See details of the \link_sync_behavior
- */
-#define CU_STREAM_PER_THREAD ((CUstream)0x2)
-
-/**
- * Event creation flags
- */
-typedef enum CUevent_flags_enum {
- CU_EVENT_DEFAULT = 0x0, /**< Default event flag */
- CU_EVENT_BLOCKING_SYNC = 0x1, /**< Event uses blocking synchronization */
- CU_EVENT_DISABLE_TIMING = 0x2, /**< Event will not record timing data */
- CU_EVENT_INTERPROCESS = 0x4 /**< Event is suitable for interprocess use. CU_EVENT_DISABLE_TIMING must be set */
-} CUevent_flags;
-
-/**
- * Occupancy calculator flag
- */
-typedef enum CUoccupancy_flags_enum {
- CU_OCCUPANCY_DEFAULT = 0x0, /**< Default behavior */
- CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE = 0x1 /**< Assume global caching is enabled and cannot be automatically turned off */
-} CUoccupancy_flags;
-
-/**
- * Array formats
- */
-typedef enum CUarray_format_enum {
- CU_AD_FORMAT_UNSIGNED_INT8 = 0x01, /**< Unsigned 8-bit integers */
- CU_AD_FORMAT_UNSIGNED_INT16 = 0x02, /**< Unsigned 16-bit integers */
- CU_AD_FORMAT_UNSIGNED_INT32 = 0x03, /**< Unsigned 32-bit integers */
- CU_AD_FORMAT_SIGNED_INT8 = 0x08, /**< Signed 8-bit integers */
- CU_AD_FORMAT_SIGNED_INT16 = 0x09, /**< Signed 16-bit integers */
- CU_AD_FORMAT_SIGNED_INT32 = 0x0a, /**< Signed 32-bit integers */
- CU_AD_FORMAT_HALF = 0x10, /**< 16-bit floating point */
- CU_AD_FORMAT_FLOAT = 0x20 /**< 32-bit floating point */
-} CUarray_format;
-
-/**
- * Texture reference addressing modes
- */
-typedef enum CUaddress_mode_enum {
- CU_TR_ADDRESS_MODE_WRAP = 0, /**< Wrapping address mode */
- CU_TR_ADDRESS_MODE_CLAMP = 1, /**< Clamp to edge address mode */
- CU_TR_ADDRESS_MODE_MIRROR = 2, /**< Mirror address mode */
- CU_TR_ADDRESS_MODE_BORDER = 3 /**< Border address mode */
-} CUaddress_mode;
-
-/**
- * Texture reference filtering modes
- */
-typedef enum CUfilter_mode_enum {
- CU_TR_FILTER_MODE_POINT = 0, /**< Point filter mode */
- CU_TR_FILTER_MODE_LINEAR = 1 /**< Linear filter mode */
-} CUfilter_mode;
-
-/**
- * Device properties
- */
-typedef enum CUdevice_attribute_enum {
- CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 1, /**< Maximum number of threads per block */
- CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X = 2, /**< Maximum block dimension X */
- CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y = 3, /**< Maximum block dimension Y */
- CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z = 4, /**< Maximum block dimension Z */
- CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X = 5, /**< Maximum grid dimension X */
- CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y = 6, /**< Maximum grid dimension Y */
- CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z = 7, /**< Maximum grid dimension Z */
- CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK = 8, /**< Maximum shared memory available per block in bytes */
- CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK = 8, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK */
- CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY = 9, /**< Memory available on device for __constant__ variables in a CUDA C kernel in bytes */
- CU_DEVICE_ATTRIBUTE_WARP_SIZE = 10, /**< Warp size in threads */
- CU_DEVICE_ATTRIBUTE_MAX_PITCH = 11, /**< Maximum pitch in bytes allowed by memory copies */
- CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK = 12, /**< Maximum number of 32-bit registers available per block */
- CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK = 12, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK */
- CU_DEVICE_ATTRIBUTE_CLOCK_RATE = 13, /**< Typical clock frequency in kilohertz */
- CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT = 14, /**< Alignment requirement for textures */
- CU_DEVICE_ATTRIBUTE_GPU_OVERLAP = 15, /**< Device can possibly copy memory and execute a kernel concurrently. Deprecated. Use instead CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT. */
- CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT = 16, /**< Number of multiprocessors on device */
- CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT = 17, /**< Specifies whether there is a run time limit on kernels */
- CU_DEVICE_ATTRIBUTE_INTEGRATED = 18, /**< Device is integrated with host memory */
- CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY = 19, /**< Device can map host memory into CUDA address space */
- CU_DEVICE_ATTRIBUTE_COMPUTE_MODE = 20, /**< Compute mode (See ::CUcomputemode for details) */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH = 21, /**< Maximum 1D texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH = 22, /**< Maximum 2D texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT = 23, /**< Maximum 2D texture height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH = 24, /**< Maximum 3D texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT = 25, /**< Maximum 3D texture height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH = 26, /**< Maximum 3D texture depth */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH = 27, /**< Maximum 2D layered texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT = 28, /**< Maximum 2D layered texture height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS = 29, /**< Maximum layers in a 2D layered texture */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH = 27, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT = 28, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES = 29, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS */
- CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT = 30, /**< Alignment requirement for surfaces */
- CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS = 31, /**< Device can possibly execute multiple kernels concurrently */
- CU_DEVICE_ATTRIBUTE_ECC_ENABLED = 32, /**< Device has ECC support enabled */
- CU_DEVICE_ATTRIBUTE_PCI_BUS_ID = 33, /**< PCI bus ID of the device */
- CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID = 34, /**< PCI device ID of the device */
- CU_DEVICE_ATTRIBUTE_TCC_DRIVER = 35, /**< Device is using TCC driver model */
- CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE = 36, /**< Peak memory clock frequency in kilohertz */
- CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH = 37, /**< Global memory bus width in bits */
- CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE = 38, /**< Size of L2 cache in bytes */
- CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR = 39, /**< Maximum resident threads per multiprocessor */
- CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT = 40, /**< Number of asynchronous engines */
- CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING = 41, /**< Device shares a unified address space with the host */ 
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH = 42, /**< Maximum 1D layered texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS = 43, /**< Maximum layers in a 1D layered texture */
- CU_DEVICE_ATTRIBUTE_CAN_TEX2D_GATHER = 44, /**< Deprecated, do not use. */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH = 45, /**< Maximum 2D texture width if CUDA_ARRAY3D_TEXTURE_GATHER is set */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT = 46, /**< Maximum 2D texture height if CUDA_ARRAY3D_TEXTURE_GATHER is set */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE = 47, /**< Alternate maximum 3D texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE = 48,/**< Alternate maximum 3D texture height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE = 49, /**< Alternate maximum 3D texture depth */
- CU_DEVICE_ATTRIBUTE_PCI_DOMAIN_ID = 50, /**< PCI domain ID of the device */
- CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT = 51, /**< Pitch alignment requirement for textures */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH = 52, /**< Maximum cubemap texture width/height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH = 53, /**< Maximum cubemap layered texture width/height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS = 54, /**< Maximum layers in a cubemap layered texture */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH = 55, /**< Maximum 1D surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH = 56, /**< Maximum 2D surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT = 57, /**< Maximum 2D surface height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH = 58, /**< Maximum 3D surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT = 59, /**< Maximum 3D surface height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH = 60, /**< Maximum 3D surface depth */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH = 61, /**< Maximum 1D layered surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS = 62, /**< Maximum layers in a 1D layered surface */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH = 63, /**< Maximum 2D layered surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT = 64, /**< Maximum 2D layered surface height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS = 65, /**< Maximum layers in a 2D layered surface */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH = 66, /**< Maximum cubemap surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH = 67, /**< Maximum cubemap layered surface width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS = 68, /**< Maximum layers in a cubemap layered surface */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH = 69, /**< Maximum 1D linear texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH = 70, /**< Maximum 2D linear texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT = 71, /**< Maximum 2D linear texture height */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH = 72, /**< Maximum 2D linear texture pitch in bytes */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH = 73, /**< Maximum mipmapped 2D texture width */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT = 74,/**< Maximum mipmapped 2D texture height */
- CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR = 75, /**< Major compute capability version number */ 
- CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR = 76, /**< Minor compute capability version number */
- CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH = 77, /**< Maximum mipmapped 1D texture width */
- CU_DEVICE_ATTRIBUTE_STREAM_PRIORITIES_SUPPORTED = 78, /**< Device supports stream priorities */
- CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED = 79, /**< Device supports caching globals in L1 */
- CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED = 80, /**< Device supports caching locals in L1 */
- CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR = 81, /**< Maximum shared memory available per multiprocessor in bytes */
- CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR = 82, /**< Maximum number of 32-bit registers available per multiprocessor */
- CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY = 83, /**< Device can allocate managed memory on this system */
- CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD = 84, /**< Device is on a multi-GPU board */ 
- CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID = 85, /**< Unique id for a group of devices on the same multi-GPU board */
- CU_DEVICE_ATTRIBUTE_MAX
-} CUdevice_attribute;
-
-/**
- * Legacy device properties
- */
-typedef struct CUdevprop_st {
- int maxThreadsPerBlock; /**< Maximum number of threads per block */
- int maxThreadsDim[3]; /**< Maximum size of each dimension of a block */
- int maxGridSize[3]; /**< Maximum size of each dimension of a grid */
- int sharedMemPerBlock; /**< Shared memory available per block in bytes */
- int totalConstantMemory; /**< Constant memory available on device in bytes */
- int SIMDWidth; /**< Warp size in threads */
- int memPitch; /**< Maximum pitch in bytes allowed by memory copies */
- int regsPerBlock; /**< 32-bit registers available per block */
- int clockRate; /**< Clock frequency in kilohertz */
- int textureAlign; /**< Alignment requirement for textures */
-} CUdevprop;
-
-/**
- * Pointer information
- */
-typedef enum CUpointer_attribute_enum {
- CU_POINTER_ATTRIBUTE_CONTEXT = 1, /**< The ::CUcontext on which a pointer was allocated or registered */
- CU_POINTER_ATTRIBUTE_MEMORY_TYPE = 2, /**< The ::CUmemorytype describing the physical location of a pointer */
- CU_POINTER_ATTRIBUTE_DEVICE_POINTER = 3, /**< The address at which a pointer's memory may be accessed on the device */
- CU_POINTER_ATTRIBUTE_HOST_POINTER = 4, /**< The address at which a pointer's memory may be accessed on the host */
- CU_POINTER_ATTRIBUTE_P2P_TOKENS = 5, /**< A pair of tokens for use with the nv-p2p.h Linux kernel interface */
- CU_POINTER_ATTRIBUTE_SYNC_MEMOPS = 6, /**< Synchronize every synchronous memory operation initiated on this region */
- CU_POINTER_ATTRIBUTE_BUFFER_ID = 7, /**< A process-wide unique ID for an allocated memory region*/
- CU_POINTER_ATTRIBUTE_IS_MANAGED = 8 /**< Indicates if the pointer points to managed memory */
-} CUpointer_attribute;
-
-/**
- * Function properties
- */
-typedef enum CUfunction_attribute_enum {
- /**
- * The maximum number of threads per block, beyond which a launch of the
- * function would fail. This number depends on both the function and the
- * device on which the function is currently loaded.
- */
- CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 0,
-
- /**
- * The size in bytes of statically-allocated shared memory required by
- * this function. This does not include dynamically-allocated shared
- * memory requested by the user at runtime.
- */
- CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES = 1,
-
- /**
- * The size in bytes of user-allocated constant memory required by this
- * function.
- */
- CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES = 2,
-
- /**
- * The size in bytes of local memory used by each thread of this function.
- */
- CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES = 3,
-
- /**
- * The number of registers used by each thread of this function.
- */
- CU_FUNC_ATTRIBUTE_NUM_REGS = 4,
-
- /**
- * The PTX virtual architecture version for which the function was
- * compiled. This value is the major PTX version * 10 + the minor PTX
- * version, so a PTX version 1.3 function would return the value 13.
- * Note that this may return the undefined value of 0 for cubins
- * compiled prior to CUDA 3.0.
- */
- CU_FUNC_ATTRIBUTE_PTX_VERSION = 5,
-
- /**
- * The binary architecture version for which the function was compiled.
- * This value is the major binary version * 10 + the minor binary version,
- * so a binary version 1.3 function would return the value 13. Note that
- * this will return a value of 10 for legacy cubins that do not have a
- * properly-encoded binary architecture version.
- */
- CU_FUNC_ATTRIBUTE_BINARY_VERSION = 6,
-
- /**
- * The attribute to indicate whether the function has been compiled with 
- * user specified option "-Xptxas --dlcm=ca" set .
- */
- CU_FUNC_ATTRIBUTE_CACHE_MODE_CA = 7,
-
- CU_FUNC_ATTRIBUTE_MAX
-} CUfunction_attribute;
-
-/**
- * Function cache configurations
- */
-typedef enum CUfunc_cache_enum {
- CU_FUNC_CACHE_PREFER_NONE = 0x00, /**< no preference for shared memory or L1 (default) */
- CU_FUNC_CACHE_PREFER_SHARED = 0x01, /**< prefer larger shared memory and smaller L1 cache */
- CU_FUNC_CACHE_PREFER_L1 = 0x02, /**< prefer larger L1 cache and smaller shared memory */
- CU_FUNC_CACHE_PREFER_EQUAL = 0x03 /**< prefer equal sized L1 cache and shared memory */
-} CUfunc_cache;
-
-/**
- * Shared memory configurations
- */
-typedef enum CUsharedconfig_enum {
- CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE = 0x00, /**< set default shared memory bank size */
- CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE = 0x01, /**< set shared memory bank width to four bytes */
- CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE = 0x02 /**< set shared memory bank width to eight bytes */
-} CUsharedconfig;
-
-/**
- * Memory types
- */
-typedef enum CUmemorytype_enum {
- CU_MEMORYTYPE_HOST = 0x01, /**< Host memory */
- CU_MEMORYTYPE_DEVICE = 0x02, /**< Device memory */
- CU_MEMORYTYPE_ARRAY = 0x03, /**< Array memory */
- CU_MEMORYTYPE_UNIFIED = 0x04 /**< Unified device or host memory */
-} CUmemorytype;
-
-/**
- * Compute Modes
- */
-typedef enum CUcomputemode_enum {
- CU_COMPUTEMODE_DEFAULT = 0, /**< Default compute mode (Multiple contexts allowed per device) */
- CU_COMPUTEMODE_EXCLUSIVE = 1, /**< Compute-exclusive-thread mode (Only one context used by a single thread can be present on this device at a time) */
- CU_COMPUTEMODE_PROHIBITED = 2, /**< Compute-prohibited mode (No contexts can be created on this device at this time) */
- CU_COMPUTEMODE_EXCLUSIVE_PROCESS = 3 /**< Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time) */
-} CUcomputemode;
-
-/**
- * Online compiler and linker options
- */
-typedef enum CUjit_option_enum
-{
- /**
- * Max number of registers that a thread may use.\n
- * Option type: unsigned int\n
- * Applies to: compiler only
- */
- CU_JIT_MAX_REGISTERS = 0,
-
- /**
- * IN: Specifies minimum number of threads per block to target compilation
- * for\n
- * OUT: Returns the number of threads the compiler actually targeted.
- * This restricts the resource utilization fo the compiler (e.g. max
- * registers) such that a block with the given number of threads should be
- * able to launch based on register limitations. Note, this option does not
- * currently take into account any other resource limitations, such as
- * shared memory utilization.\n
- * Cannot be combined with ::CU_JIT_TARGET.\n
- * Option type: unsigned int\n
- * Applies to: compiler only
- */
- CU_JIT_THREADS_PER_BLOCK,
-
- /**
- * Overwrites the option value with the total wall clock time, in
- * milliseconds, spent in the compiler and linker\n
- * Option type: float\n
- * Applies to: compiler and linker
- */
- CU_JIT_WALL_TIME,
-
- /**
- * Pointer to a buffer in which to print any log messages
- * that are informational in nature (the buffer size is specified via
- * option ::CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES)\n
- * Option type: char *\n
- * Applies to: compiler and linker
- */
- CU_JIT_INFO_LOG_BUFFER,
-
- /**
- * IN: Log buffer size in bytes. Log messages will be capped at this size
- * (including null terminator)\n
- * OUT: Amount of log buffer filled with messages\n
- * Option type: unsigned int\n
- * Applies to: compiler and linker
- */
- CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES,
-
- /**
- * Pointer to a buffer in which to print any log messages that
- * reflect errors (the buffer size is specified via option
- * ::CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES)\n
- * Option type: char *\n
- * Applies to: compiler and linker
- */
- CU_JIT_ERROR_LOG_BUFFER,
-
- /**
- * IN: Log buffer size in bytes. Log messages will be capped at this size
- * (including null terminator)\n
- * OUT: Amount of log buffer filled with messages\n
- * Option type: unsigned int\n
- * Applies to: compiler and linker
- */
- CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES,
-
- /**
- * Level of optimizations to apply to generated code (0 - 4), with 4
- * being the default and highest level of optimizations.\n
- * Option type: unsigned int\n
- * Applies to: compiler only
- */
- CU_JIT_OPTIMIZATION_LEVEL,
-
- /**
- * No option value required. Determines the target based on the current
- * attached context (default)\n
- * Option type: No option value needed\n
- * Applies to: compiler and linker
- */
- CU_JIT_TARGET_FROM_CUCONTEXT,
-
- /**
- * Target is chosen based on supplied ::CUjit_target. Cannot be
- * combined with ::CU_JIT_THREADS_PER_BLOCK.\n
- * Option type: unsigned int for enumerated type ::CUjit_target\n
- * Applies to: compiler and linker
- */
- CU_JIT_TARGET,
-
- /**
- * Specifies choice of fallback strategy if matching cubin is not found.
- * Choice is based on supplied ::CUjit_fallback. This option cannot be
- * used with cuLink* APIs as the linker requires exact matches.\n
- * Option type: unsigned int for enumerated type ::CUjit_fallback\n
- * Applies to: compiler only
- */
- CU_JIT_FALLBACK_STRATEGY,
-
- /**
- * Specifies whether to create debug information in output (-g)
- * (0: false, default)\n
- * Option type: int\n
- * Applies to: compiler and linker
- */
- CU_JIT_GENERATE_DEBUG_INFO,
-
- /**
- * Generate verbose log messages (0: false, default)\n
- * Option type: int\n
- * Applies to: compiler and linker
- */
- CU_JIT_LOG_VERBOSE,
-
- /**
- * Generate line number information (-lineinfo) (0: false, default)\n
- * Option type: int\n
- * Applies to: compiler only
- */
- CU_JIT_GENERATE_LINE_INFO,
-
- /**
- * Specifies whether to enable caching explicitly (-dlcm) \n
- * Choice is based on supplied ::CUjit_cacheMode_enum.\n
- * Option type: unsigned int for enumerated type ::CUjit_cacheMode_enum\n
- * Applies to: compiler only
- */
- CU_JIT_CACHE_MODE,
-
- CU_JIT_NUM_OPTIONS
-
-} CUjit_option;
-
-/**
- * Online compilation targets
- */
-typedef enum CUjit_target_enum
-{
- CU_TARGET_COMPUTE_10 = 10, /**< Compute device class 1.0 */
- CU_TARGET_COMPUTE_11 = 11, /**< Compute device class 1.1 */
- CU_TARGET_COMPUTE_12 = 12, /**< Compute device class 1.2 */
- CU_TARGET_COMPUTE_13 = 13, /**< Compute device class 1.3 */
- CU_TARGET_COMPUTE_20 = 20, /**< Compute device class 2.0 */
- CU_TARGET_COMPUTE_21 = 21, /**< Compute device class 2.1 */
- CU_TARGET_COMPUTE_30 = 30, /**< Compute device class 3.0 */
- CU_TARGET_COMPUTE_32 = 32, /**< Compute device class 3.2 */
- CU_TARGET_COMPUTE_35 = 35, /**< Compute device class 3.5 */
- CU_TARGET_COMPUTE_37 = 37, /**< Compute device class 3.7 */
- CU_TARGET_COMPUTE_50 = 50, /**< Compute device class 5.0 */
- CU_TARGET_COMPUTE_52 = 52 /**< Compute device class 5.2 */
-} CUjit_target;
-
-/**
- * Cubin matching fallback strategies
- */
-typedef enum CUjit_fallback_enum
-{
- CU_PREFER_PTX = 0, /**< Prefer to compile ptx if exact binary match not found */
-
- CU_PREFER_BINARY /**< Prefer to fall back to compatible binary code if exact match not found */
-
-} CUjit_fallback;
-
-/**
- * Caching modes for dlcm 
- */
-typedef enum CUjit_cacheMode_enum
-{
- CU_JIT_CACHE_OPTION_NONE = 0, /**< Compile with no -dlcm flag specified */
- CU_JIT_CACHE_OPTION_CG, /**< Compile with L1 cache disabled */
- CU_JIT_CACHE_OPTION_CA /**< Compile with L1 cache enabled */
-} CUjit_cacheMode;
-
-/**
- * Device code formats
- */
-typedef enum CUjitInputType_enum
-{
- /**
- * Compiled device-class-specific device code\n
- * Applicable options: none
- */
- CU_JIT_INPUT_CUBIN = 0,
-
- /**
- * PTX source code\n
- * Applicable options: PTX compiler options
- */
- CU_JIT_INPUT_PTX,
-
- /**
- * Bundle of multiple cubins and/or PTX of some device code\n
- * Applicable options: PTX compiler options, ::CU_JIT_FALLBACK_STRATEGY
- */
- CU_JIT_INPUT_FATBINARY,
-
- /**
- * Host object with embedded device code\n
- * Applicable options: PTX compiler options, ::CU_JIT_FALLBACK_STRATEGY
- */
- CU_JIT_INPUT_OBJECT,
-
- /**
- * Archive of host objects with embedded device code\n
- * Applicable options: PTX compiler options, ::CU_JIT_FALLBACK_STRATEGY
- */
- CU_JIT_INPUT_LIBRARY,
-
- CU_JIT_NUM_INPUT_TYPES
-} CUjitInputType;
-
-#if __CUDA_API_VERSION >= 5050
-typedef struct CUlinkState_st *CUlinkState;
-#endif /* __CUDA_API_VERSION >= 5050 */
-
-/**
- * Flags to register a graphics resource
- */
-typedef enum CUgraphicsRegisterFlags_enum {
- CU_GRAPHICS_REGISTER_FLAGS_NONE = 0x00,
- CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY = 0x01,
- CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD = 0x02,
- CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST = 0x04,
- CU_GRAPHICS_REGISTER_FLAGS_TEXTURE_GATHER = 0x08
-} CUgraphicsRegisterFlags;
-
-/**
- * Flags for mapping and unmapping interop resources
- */
-typedef enum CUgraphicsMapResourceFlags_enum {
- CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE = 0x00,
- CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY = 0x01,
- CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD = 0x02
-} CUgraphicsMapResourceFlags;
-
-/**
- * Array indices for cube faces
- */
-typedef enum CUarray_cubemap_face_enum {
- CU_CUBEMAP_FACE_POSITIVE_X = 0x00, /**< Positive X face of cubemap */
- CU_CUBEMAP_FACE_NEGATIVE_X = 0x01, /**< Negative X face of cubemap */
- CU_CUBEMAP_FACE_POSITIVE_Y = 0x02, /**< Positive Y face of cubemap */
- CU_CUBEMAP_FACE_NEGATIVE_Y = 0x03, /**< Negative Y face of cubemap */
- CU_CUBEMAP_FACE_POSITIVE_Z = 0x04, /**< Positive Z face of cubemap */
- CU_CUBEMAP_FACE_NEGATIVE_Z = 0x05 /**< Negative Z face of cubemap */
-} CUarray_cubemap_face;
-
-/**
- * Limits
- */
-typedef enum CUlimit_enum {
- CU_LIMIT_STACK_SIZE = 0x00, /**< GPU thread stack size */
- CU_LIMIT_PRINTF_FIFO_SIZE = 0x01, /**< GPU printf FIFO size */
- CU_LIMIT_MALLOC_HEAP_SIZE = 0x02, /**< GPU malloc heap size */
- CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH = 0x03, /**< GPU device runtime launch synchronize depth */
- CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT = 0x04, /**< GPU device runtime pending launch count */
- CU_LIMIT_MAX
-} CUlimit;
-
-/**
- * Resource types
- */
-typedef enum CUresourcetype_enum {
- CU_RESOURCE_TYPE_ARRAY = 0x00, /**< Array resoure */
- CU_RESOURCE_TYPE_MIPMAPPED_ARRAY = 0x01, /**< Mipmapped array resource */
- CU_RESOURCE_TYPE_LINEAR = 0x02, /**< Linear resource */
- CU_RESOURCE_TYPE_PITCH2D = 0x03 /**< Pitch 2D resource */
-} CUresourcetype;
-
-/**
- * Error codes
- */
-typedef enum cudaError_enum {
- /**
- * The API call returned with no errors. In the case of query calls, this
- * can also mean that the operation being queried is complete (see
- * ::cuEventQuery() and ::cuStreamQuery()).
- */
- CUDA_SUCCESS = 0,
-
- /**
- * This indicates that one or more of the parameters passed to the API call
- * is not within an acceptable range of values.
- */
- CUDA_ERROR_INVALID_VALUE = 1,
-
- /**
- * The API call failed because it was unable to allocate enough memory to
- * perform the requested operation.
- */
- CUDA_ERROR_OUT_OF_MEMORY = 2,
-
- /**
- * This indicates that the CUDA driver has not been initialized with
- * ::cuInit() or that initialization has failed.
- */
- CUDA_ERROR_NOT_INITIALIZED = 3,
-
- /**
- * This indicates that the CUDA driver is in the process of shutting down.
- */
- CUDA_ERROR_DEINITIALIZED = 4,
-
- /**
- * This indicates profiler is not initialized for this run. This can
- * happen when the application is running with external profiling tools
- * like visual profiler.
- */
- CUDA_ERROR_PROFILER_DISABLED = 5,
-
- /**
- * \deprecated
- * This error return is deprecated as of CUDA 5.0. It is no longer an error
- * to attempt to enable/disable the profiling via ::cuProfilerStart or
- * ::cuProfilerStop without initialization.
- */
- CUDA_ERROR_PROFILER_NOT_INITIALIZED = 6,
-
- /**
- * \deprecated
- * This error return is deprecated as of CUDA 5.0. It is no longer an error
- * to call cuProfilerStart() when profiling is already enabled.
- */
- CUDA_ERROR_PROFILER_ALREADY_STARTED = 7,
-
- /**
- * \deprecated
- * This error return is deprecated as of CUDA 5.0. It is no longer an error
- * to call cuProfilerStop() when profiling is already disabled.
- */
- CUDA_ERROR_PROFILER_ALREADY_STOPPED = 8,
-
- /**
- * This indicates that no CUDA-capable devices were detected by the installed
- * CUDA driver.
- */
- CUDA_ERROR_NO_DEVICE = 100,
-
- /**
- * This indicates that the device ordinal supplied by the user does not
- * correspond to a valid CUDA device.
- */
- CUDA_ERROR_INVALID_DEVICE = 101,
-
-
- /**
- * This indicates that the device kernel image is invalid. This can also
- * indicate an invalid CUDA module.
- */
- CUDA_ERROR_INVALID_IMAGE = 200,
-
- /**
- * This most frequently indicates that there is no context bound to the
- * current thread. This can also be returned if the context passed to an
- * API call is not a valid handle (such as a context that has had
- * ::cuCtxDestroy() invoked on it). This can also be returned if a user
- * mixes different API versions (i.e. 3010 context with 3020 API calls).
- * See ::cuCtxGetApiVersion() for more details.
- */
- CUDA_ERROR_INVALID_CONTEXT = 201,
-
- /**
- * This indicated that the context being supplied as a parameter to the
- * API call was already the active context.
- * \deprecated
- * This error return is deprecated as of CUDA 3.2. It is no longer an
- * error to attempt to push the active context via ::cuCtxPushCurrent().
- */
- CUDA_ERROR_CONTEXT_ALREADY_CURRENT = 202,
-
- /**
- * This indicates that a map or register operation has failed.
- */
- CUDA_ERROR_MAP_FAILED = 205,
-
- /**
- * This indicates that an unmap or unregister operation has failed.
- */
- CUDA_ERROR_UNMAP_FAILED = 206,
-
- /**
- * This indicates that the specified array is currently mapped and thus
- * cannot be destroyed.
- */
- CUDA_ERROR_ARRAY_IS_MAPPED = 207,
-
- /**
- * This indicates that the resource is already mapped.
- */
- CUDA_ERROR_ALREADY_MAPPED = 208,
-
- /**
- * This indicates that there is no kernel image available that is suitable
- * for the device. This can occur when a user specifies code generation
- * options for a particular CUDA source file that do not include the
- * corresponding device configuration.
- */
- CUDA_ERROR_NO_BINARY_FOR_GPU = 209,
-
- /**
- * This indicates that a resource has already been acquired.
- */
- CUDA_ERROR_ALREADY_ACQUIRED = 210,
-
- /**
- * This indicates that a resource is not mapped.
- */
- CUDA_ERROR_NOT_MAPPED = 211,
-
- /**
- * This indicates that a mapped resource is not available for access as an
- * array.
- */
- CUDA_ERROR_NOT_MAPPED_AS_ARRAY = 212,
-
- /**
- * This indicates that a mapped resource is not available for access as a
- * pointer.
- */
- CUDA_ERROR_NOT_MAPPED_AS_POINTER = 213,
-
- /**
- * This indicates that an uncorrectable ECC error was detected during
- * execution.
- */
- CUDA_ERROR_ECC_UNCORRECTABLE = 214,
-
- /**
- * This indicates that the ::CUlimit passed to the API call is not
- * supported by the active device.
- */
- CUDA_ERROR_UNSUPPORTED_LIMIT = 215,
-
- /**
- * This indicates that the ::CUcontext passed to the API call can
- * only be bound to a single CPU thread at a time but is already 
- * bound to a CPU thread.
- */
- CUDA_ERROR_CONTEXT_ALREADY_IN_USE = 216,
-
- /**
- * This indicates that peer access is not supported across the given
- * devices.
- */
- CUDA_ERROR_PEER_ACCESS_UNSUPPORTED = 217,
-
- /**
- * This indicates that a PTX JIT compilation failed.
- */
- CUDA_ERROR_INVALID_PTX = 218,
-
- /**
- * This indicates an error with OpenGL or DirectX context.
- */
- CUDA_ERROR_INVALID_GRAPHICS_CONTEXT = 219,
-
- /**
- * This indicates that the device kernel source is invalid.
- */
- CUDA_ERROR_INVALID_SOURCE = 300,
-
- /**
- * This indicates that the file specified was not found.
- */
- CUDA_ERROR_FILE_NOT_FOUND = 301,
-
- /**
- * This indicates that a link to a shared object failed to resolve.
- */
- CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND = 302,
-
- /**
- * This indicates that initialization of a shared object failed.
- */
- CUDA_ERROR_SHARED_OBJECT_INIT_FAILED = 303,
-
- /**
- * This indicates that an OS call failed.
- */
- CUDA_ERROR_OPERATING_SYSTEM = 304,
-
- /**
- * This indicates that a resource handle passed to the API call was not
- * valid. Resource handles are opaque types like ::CUstream and ::CUevent.
- */
- CUDA_ERROR_INVALID_HANDLE = 400,
-
- /**
- * This indicates that a named symbol was not found. Examples of symbols
- * are global/constant variable names, texture names, and surface names.
- */
- CUDA_ERROR_NOT_FOUND = 500,
-
- /**
- * This indicates that asynchronous operations issued previously have not
- * completed yet. This result is not actually an error, but must be indicated
- * differently than ::CUDA_SUCCESS (which indicates completion). Calls that
- * may return this value include ::cuEventQuery() and ::cuStreamQuery().
- */
- CUDA_ERROR_NOT_READY = 600,
-
- /**
- * While executing a kernel, the device encountered a
- * load or store instruction on an invalid memory address.
- * The context cannot be used, so it must be destroyed (and a new one should be created).
- * All existing device memory allocations from this context are invalid
- * and must be reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_ILLEGAL_ADDRESS = 700,
-
- /**
- * This indicates that a launch did not occur because it did not have
- * appropriate resources. This error usually indicates that the user has
- * attempted to pass too many arguments to the device kernel, or the
- * kernel launch specifies too many threads for the kernel's register
- * count. Passing arguments of the wrong size (i.e. a 64-bit pointer
- * when a 32-bit int is expected) is equivalent to passing too many
- * arguments and can also result in this error.
- */
- CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES = 701,
-
- /**
- * This indicates that the device kernel took too long to execute. This can
- * only occur if timeouts are enabled - see the device attribute
- * ::CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. The
- * context cannot be used (and must be destroyed similar to
- * ::CUDA_ERROR_LAUNCH_FAILED). All existing device memory allocations from
- * this context are invalid and must be reconstructed if the program is to
- * continue using CUDA.
- */
- CUDA_ERROR_LAUNCH_TIMEOUT = 702,
-
- /**
- * This error indicates a kernel launch that uses an incompatible texturing
- * mode.
- */
- CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING = 703,
- 
- /**
- * This error indicates that a call to ::cuCtxEnablePeerAccess() is
- * trying to re-enable peer access to a context which has already
- * had peer access to it enabled.
- */
- CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED = 704,
-
- /**
- * This error indicates that ::cuCtxDisablePeerAccess() is 
- * trying to disable peer access which has not been enabled yet 
- * via ::cuCtxEnablePeerAccess(). 
- */
- CUDA_ERROR_PEER_ACCESS_NOT_ENABLED = 705,
-
- /**
- * This error indicates that the primary context for the specified device
- * has already been initialized.
- */
- CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE = 708,
-
- /**
- * This error indicates that the context current to the calling thread
- * has been destroyed using ::cuCtxDestroy, or is a primary context which
- * has not yet been initialized.
- */
- CUDA_ERROR_CONTEXT_IS_DESTROYED = 709,
-
- /**
- * A device-side assert triggered during kernel execution. The context
- * cannot be used anymore, and must be destroyed. All existing device 
- * memory allocations from this context are invalid and must be 
- * reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_ASSERT = 710,
-
- /**
- * This error indicates that the hardware resources required to enable
- * peer access have been exhausted for one or more of the devices 
- * passed to ::cuCtxEnablePeerAccess().
- */
- CUDA_ERROR_TOO_MANY_PEERS = 711,
-
- /**
- * This error indicates that the memory range passed to ::cuMemHostRegister()
- * has already been registered.
- */
- CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED = 712,
-
- /**
- * This error indicates that the pointer passed to ::cuMemHostUnregister()
- * does not correspond to any currently registered memory region.
- */
- CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED = 713,
-
- /**
- * While executing a kernel, the device encountered a stack error.
- * This can be due to stack corruption or exceeding the stack size limit.
- * The context cannot be used, so it must be destroyed (and a new one should be created).
- * All existing device memory allocations from this context are invalid
- * and must be reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_HARDWARE_STACK_ERROR = 714,
-
- /**
- * While executing a kernel, the device encountered an illegal instruction.
- * The context cannot be used, so it must be destroyed (and a new one should be created).
- * All existing device memory allocations from this context are invalid
- * and must be reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_ILLEGAL_INSTRUCTION = 715,
-
- /**
- * While executing a kernel, the device encountered a load or store instruction
- * on a memory address which is not aligned.
- * The context cannot be used, so it must be destroyed (and a new one should be created).
- * All existing device memory allocations from this context are invalid
- * and must be reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_MISALIGNED_ADDRESS = 716,
-
- /**
- * While executing a kernel, the device encountered an instruction
- * which can only operate on memory locations in certain address spaces
- * (global, shared, or local), but was supplied a memory address not
- * belonging to an allowed address space.
- * The context cannot be used, so it must be destroyed (and a new one should be created).
- * All existing device memory allocations from this context are invalid
- * and must be reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_INVALID_ADDRESS_SPACE = 717,
-
- /**
- * While executing a kernel, the device program counter wrapped its address space.
- * The context cannot be used, so it must be destroyed (and a new one should be created).
- * All existing device memory allocations from this context are invalid
- * and must be reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_INVALID_PC = 718,
-
- /**
- * An exception occurred on the device while executing a kernel. Common
- * causes include dereferencing an invalid device pointer and accessing
- * out of bounds shared memory. The context cannot be used, so it must
- * be destroyed (and a new one should be created). All existing device
- * memory allocations from this context are invalid and must be
- * reconstructed if the program is to continue using CUDA.
- */
- CUDA_ERROR_LAUNCH_FAILED = 719,
-
-
- /**
- * This error indicates that the attempted operation is not permitted.
- */
- CUDA_ERROR_NOT_PERMITTED = 800,
-
- /**
- * This error indicates that the attempted operation is not supported
- * on the current system or device.
- */
- CUDA_ERROR_NOT_SUPPORTED = 801,
-
- /**
- * This indicates that an unknown internal error has occurred.
- */
- CUDA_ERROR_UNKNOWN = 999
-} CUresult;
-
-#ifdef _WIN32
-#define CUDA_CB __stdcall
-#else
-#define CUDA_CB
-#endif
-
-/**
- * CUDA stream callback
- * \param hStream The stream the callback was added to, as passed to ::cuStreamAddCallback. May be NULL.
- * \param status ::CUDA_SUCCESS or any persistent error on the stream.
- * \param userData User parameter provided at registration.
- */
-typedef void (CUDA_CB *CUstreamCallback)(CUstream hStream, CUresult status, void *userData);
-
-/**
- * Block size to per-block dynamic shared memory mapping for a certain
- * kernel \param blockSize Block size of the kernel.
- *
- * \return The dynamic shared memory needed by a block.
- */
-typedef size_t (CUDA_CB *CUoccupancyB2DSize)(int blockSize);
-
-/**
- * If set, host memory is portable between CUDA contexts.
- * Flag for ::cuMemHostAlloc()
- */
-#define CU_MEMHOSTALLOC_PORTABLE 0x01
-
-/**
- * If set, host memory is mapped into CUDA address space and
- * ::cuMemHostGetDevicePointer() may be called on the host pointer.
- * Flag for ::cuMemHostAlloc()
- */
-#define CU_MEMHOSTALLOC_DEVICEMAP 0x02
-
-/**
- * If set, host memory is allocated as write-combined - fast to write,
- * faster to DMA, slow to read except via SSE4 streaming load instruction
- * (MOVNTDQA).
- * Flag for ::cuMemHostAlloc()
- */
-#define CU_MEMHOSTALLOC_WRITECOMBINED 0x04
-
-/**
- * If set, host memory is portable between CUDA contexts.
- * Flag for ::cuMemHostRegister()
- */
-#define CU_MEMHOSTREGISTER_PORTABLE 0x01
-
-/**
- * If set, host memory is mapped into CUDA address space and
- * ::cuMemHostGetDevicePointer() may be called on the host pointer.
- * Flag for ::cuMemHostRegister()
- */
-#define CU_MEMHOSTREGISTER_DEVICEMAP 0x02
-
-/**
- * If set, the passed memory pointer is treated as pointing to some
- * memory-mapped I/O space, e.g. belonging to a third-party PCIe device.
- * On Windows the flag is a no-op.
- * On Linux that memory is marked as non cache-coherent for the GPU and
- * is expected to be physically contiguous. It may return
- * CUDA_ERROR_NOT_PERMITTED if run as an unprivileged user,
- * CUDA_ERROR_NOT_SUPPORTED on older Linux kernel versions.
- * On all other platforms, it is not supported and CUDA_ERROR_NOT_SUPPORTED
- * is returned.
- * Flag for ::cuMemHostRegister()
- */
-#define CU_MEMHOSTREGISTER_IOMEMORY 0x04
-
-#if __CUDA_API_VERSION >= 3020
-
-/**
- * 2D memory copy parameters
- */
-typedef struct CUDA_MEMCPY2D_st {
- size_t srcXInBytes; /**< Source X in bytes */
- size_t srcY; /**< Source Y */
-
- CUmemorytype srcMemoryType; /**< Source memory type (host, device, array) */
- const void *srcHost; /**< Source host pointer */
- CUdeviceptr srcDevice; /**< Source device pointer */
- CUarray srcArray; /**< Source array reference */
- size_t srcPitch; /**< Source pitch (ignored when src is array) */
-
- size_t dstXInBytes; /**< Destination X in bytes */
- size_t dstY; /**< Destination Y */
-
- CUmemorytype dstMemoryType; /**< Destination memory type (host, device, array) */
- void *dstHost; /**< Destination host pointer */
- CUdeviceptr dstDevice; /**< Destination device pointer */
- CUarray dstArray; /**< Destination array reference */
- size_t dstPitch; /**< Destination pitch (ignored when dst is array) */
-
- size_t WidthInBytes; /**< Width of 2D memory copy in bytes */
- size_t Height; /**< Height of 2D memory copy */
-} CUDA_MEMCPY2D;
-
-/**
- * 3D memory copy parameters
- */
-typedef struct CUDA_MEMCPY3D_st {
- size_t srcXInBytes; /**< Source X in bytes */
- size_t srcY; /**< Source Y */
- size_t srcZ; /**< Source Z */
- size_t srcLOD; /**< Source LOD */
- CUmemorytype srcMemoryType; /**< Source memory type (host, device, array) */
- const void *srcHost; /**< Source host pointer */
- CUdeviceptr srcDevice; /**< Source device pointer */
- CUarray srcArray; /**< Source array reference */
- void *reserved0; /**< Must be NULL */
- size_t srcPitch; /**< Source pitch (ignored when src is array) */
- size_t srcHeight; /**< Source height (ignored when src is array; may be 0 if Depth==1) */
-
- size_t dstXInBytes; /**< Destination X in bytes */
- size_t dstY; /**< Destination Y */
- size_t dstZ; /**< Destination Z */
- size_t dstLOD; /**< Destination LOD */
- CUmemorytype dstMemoryType; /**< Destination memory type (host, device, array) */
- void *dstHost; /**< Destination host pointer */
- CUdeviceptr dstDevice; /**< Destination device pointer */
- CUarray dstArray; /**< Destination array reference */
- void *reserved1; /**< Must be NULL */
- size_t dstPitch; /**< Destination pitch (ignored when dst is array) */
- size_t dstHeight; /**< Destination height (ignored when dst is array; may be 0 if Depth==1) */
-
- size_t WidthInBytes; /**< Width of 3D memory copy in bytes */
- size_t Height; /**< Height of 3D memory copy */
- size_t Depth; /**< Depth of 3D memory copy */
-} CUDA_MEMCPY3D;
-
-/**
- * 3D memory cross-context copy parameters
- */
-typedef struct CUDA_MEMCPY3D_PEER_st {
- size_t srcXInBytes; /**< Source X in bytes */
- size_t srcY; /**< Source Y */
- size_t srcZ; /**< Source Z */
- size_t srcLOD; /**< Source LOD */
- CUmemorytype srcMemoryType; /**< Source memory type (host, device, array) */
- const void *srcHost; /**< Source host pointer */
- CUdeviceptr srcDevice; /**< Source device pointer */
- CUarray srcArray; /**< Source array reference */
- CUcontext srcContext; /**< Source context (ignored with srcMemoryType is ::CU_MEMORYTYPE_ARRAY) */
- size_t srcPitch; /**< Source pitch (ignored when src is array) */
- size_t srcHeight; /**< Source height (ignored when src is array; may be 0 if Depth==1) */
-
- size_t dstXInBytes; /**< Destination X in bytes */
- size_t dstY; /**< Destination Y */
- size_t dstZ; /**< Destination Z */
- size_t dstLOD; /**< Destination LOD */
- CUmemorytype dstMemoryType; /**< Destination memory type (host, device, array) */
- void *dstHost; /**< Destination host pointer */
- CUdeviceptr dstDevice; /**< Destination device pointer */
- CUarray dstArray; /**< Destination array reference */
- CUcontext dstContext; /**< Destination context (ignored with dstMemoryType is ::CU_MEMORYTYPE_ARRAY) */
- size_t dstPitch; /**< Destination pitch (ignored when dst is array) */
- size_t dstHeight; /**< Destination height (ignored when dst is array; may be 0 if Depth==1) */
-
- size_t WidthInBytes; /**< Width of 3D memory copy in bytes */
- size_t Height; /**< Height of 3D memory copy */
- size_t Depth; /**< Depth of 3D memory copy */
-} CUDA_MEMCPY3D_PEER;
-
-/**
- * Array descriptor
- */
-typedef struct CUDA_ARRAY_DESCRIPTOR_st
-{
- size_t Width; /**< Width of array */
- size_t Height; /**< Height of array */
-
- CUarray_format Format; /**< Array format */
- unsigned int NumChannels; /**< Channels per array element */
-} CUDA_ARRAY_DESCRIPTOR;
-
-/**
- * 3D array descriptor
- */
-typedef struct CUDA_ARRAY3D_DESCRIPTOR_st
-{
- size_t Width; /**< Width of 3D array */
- size_t Height; /**< Height of 3D array */
- size_t Depth; /**< Depth of 3D array */
-
- CUarray_format Format; /**< Array format */
- unsigned int NumChannels; /**< Channels per array element */
- unsigned int Flags; /**< Flags */
-} CUDA_ARRAY3D_DESCRIPTOR;
-
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-#if __CUDA_API_VERSION >= 5000
-
-/**
- * CUDA Resource descriptor
- */
-typedef struct CUDA_RESOURCE_DESC_st
-{
- CUresourcetype resType; /**< Resource type */
-
- union {
- struct {
- CUarray hArray; /**< CUDA array */
- } array;
- struct {
- CUmipmappedArray hMipmappedArray; /**< CUDA mipmapped array */
- } mipmap;
- struct {
- CUdeviceptr devPtr; /**< Device pointer */
- CUarray_format format; /**< Array format */
- unsigned int numChannels; /**< Channels per array element */
- size_t sizeInBytes; /**< Size in bytes */
- } linear;
- struct {
- CUdeviceptr devPtr; /**< Device pointer */
- CUarray_format format; /**< Array format */
- unsigned int numChannels; /**< Channels per array element */
- size_t width; /**< Width of the array in elements */
- size_t height; /**< Height of the array in elements */
- size_t pitchInBytes; /**< Pitch between two rows in bytes */
- } pitch2D;
- struct {
- int reserved[32];
- } reserved;
- } res;
-
- unsigned int flags; /**< Flags (must be zero) */
-} CUDA_RESOURCE_DESC;
-
-/**
- * Texture descriptor
- */
-typedef struct CUDA_TEXTURE_DESC_st {
- CUaddress_mode addressMode[3]; /**< Address modes */
- CUfilter_mode filterMode; /**< Filter mode */
- unsigned int flags; /**< Flags */
- unsigned int maxAnisotropy; /**< Maximum anisotropy ratio */
- CUfilter_mode mipmapFilterMode; /**< Mipmap filter mode */
- float mipmapLevelBias; /**< Mipmap level bias */
- float minMipmapLevelClamp; /**< Mipmap minimum level clamp */
- float maxMipmapLevelClamp; /**< Mipmap maximum level clamp */
- int reserved[16];
-} CUDA_TEXTURE_DESC;
-
-/**
- * Resource view format
- */
-typedef enum CUresourceViewFormat_enum
-{
- CU_RES_VIEW_FORMAT_NONE = 0x00, /**< No resource view format (use underlying resource format) */
- CU_RES_VIEW_FORMAT_UINT_1X8 = 0x01, /**< 1 channel unsigned 8-bit integers */
- CU_RES_VIEW_FORMAT_UINT_2X8 = 0x02, /**< 2 channel unsigned 8-bit integers */
- CU_RES_VIEW_FORMAT_UINT_4X8 = 0x03, /**< 4 channel unsigned 8-bit integers */
- CU_RES_VIEW_FORMAT_SINT_1X8 = 0x04, /**< 1 channel signed 8-bit integers */
- CU_RES_VIEW_FORMAT_SINT_2X8 = 0x05, /**< 2 channel signed 8-bit integers */
- CU_RES_VIEW_FORMAT_SINT_4X8 = 0x06, /**< 4 channel signed 8-bit integers */
- CU_RES_VIEW_FORMAT_UINT_1X16 = 0x07, /**< 1 channel unsigned 16-bit integers */
- CU_RES_VIEW_FORMAT_UINT_2X16 = 0x08, /**< 2 channel unsigned 16-bit integers */
- CU_RES_VIEW_FORMAT_UINT_4X16 = 0x09, /**< 4 channel unsigned 16-bit integers */
- CU_RES_VIEW_FORMAT_SINT_1X16 = 0x0a, /**< 1 channel signed 16-bit integers */
- CU_RES_VIEW_FORMAT_SINT_2X16 = 0x0b, /**< 2 channel signed 16-bit integers */
- CU_RES_VIEW_FORMAT_SINT_4X16 = 0x0c, /**< 4 channel signed 16-bit integers */
- CU_RES_VIEW_FORMAT_UINT_1X32 = 0x0d, /**< 1 channel unsigned 32-bit integers */
- CU_RES_VIEW_FORMAT_UINT_2X32 = 0x0e, /**< 2 channel unsigned 32-bit integers */
- CU_RES_VIEW_FORMAT_UINT_4X32 = 0x0f, /**< 4 channel unsigned 32-bit integers */
- CU_RES_VIEW_FORMAT_SINT_1X32 = 0x10, /**< 1 channel signed 32-bit integers */
- CU_RES_VIEW_FORMAT_SINT_2X32 = 0x11, /**< 2 channel signed 32-bit integers */
- CU_RES_VIEW_FORMAT_SINT_4X32 = 0x12, /**< 4 channel signed 32-bit integers */
- CU_RES_VIEW_FORMAT_FLOAT_1X16 = 0x13, /**< 1 channel 16-bit floating point */
- CU_RES_VIEW_FORMAT_FLOAT_2X16 = 0x14, /**< 2 channel 16-bit floating point */
- CU_RES_VIEW_FORMAT_FLOAT_4X16 = 0x15, /**< 4 channel 16-bit floating point */
- CU_RES_VIEW_FORMAT_FLOAT_1X32 = 0x16, /**< 1 channel 32-bit floating point */
- CU_RES_VIEW_FORMAT_FLOAT_2X32 = 0x17, /**< 2 channel 32-bit floating point */
- CU_RES_VIEW_FORMAT_FLOAT_4X32 = 0x18, /**< 4 channel 32-bit floating point */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC1 = 0x19, /**< Block compressed 1 */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC2 = 0x1a, /**< Block compressed 2 */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC3 = 0x1b, /**< Block compressed 3 */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC4 = 0x1c, /**< Block compressed 4 unsigned */
- CU_RES_VIEW_FORMAT_SIGNED_BC4 = 0x1d, /**< Block compressed 4 signed */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC5 = 0x1e, /**< Block compressed 5 unsigned */
- CU_RES_VIEW_FORMAT_SIGNED_BC5 = 0x1f, /**< Block compressed 5 signed */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC6H = 0x20, /**< Block compressed 6 unsigned half-float */
- CU_RES_VIEW_FORMAT_SIGNED_BC6H = 0x21, /**< Block compressed 6 signed half-float */
- CU_RES_VIEW_FORMAT_UNSIGNED_BC7 = 0x22 /**< Block compressed 7 */
-} CUresourceViewFormat;
-
-/**
- * Resource view descriptor
- */
-typedef struct CUDA_RESOURCE_VIEW_DESC_st
-{
- CUresourceViewFormat format; /**< Resource view format */
- size_t width; /**< Width of the resource view */
- size_t height; /**< Height of the resource view */
- size_t depth; /**< Depth of the resource view */
- unsigned int firstMipmapLevel; /**< First defined mipmap level */
- unsigned int lastMipmapLevel; /**< Last defined mipmap level */
- unsigned int firstLayer; /**< First layer index */
- unsigned int lastLayer; /**< Last layer index */
- unsigned int reserved[16];
-} CUDA_RESOURCE_VIEW_DESC;
-
-/**
- * GPU Direct v3 tokens
- */
-typedef struct CUDA_POINTER_ATTRIBUTE_P2P_TOKENS_st {
- unsigned long long p2pToken;
- unsigned int vaSpaceToken;
-} CUDA_POINTER_ATTRIBUTE_P2P_TOKENS;
-
-#endif /* __CUDA_API_VERSION >= 5000 */
-
-/**
- * If set, the CUDA array is a collection of layers, where each layer is either a 1D
- * or a 2D array and the Depth member of CUDA_ARRAY3D_DESCRIPTOR specifies the number 
- * of layers, not the depth of a 3D array.
- */
-#define CUDA_ARRAY3D_LAYERED 0x01
-
-/**
- * Deprecated, use CUDA_ARRAY3D_LAYERED
- */
-#define CUDA_ARRAY3D_2DARRAY 0x01
-
-/**
- * This flag must be set in order to bind a surface reference
- * to the CUDA array
- */
-#define CUDA_ARRAY3D_SURFACE_LDST 0x02
-
-/**
- * If set, the CUDA array is a collection of six 2D arrays, representing faces of a cube. The
- * width of such a CUDA array must be equal to its height, and Depth must be six.
- * If ::CUDA_ARRAY3D_LAYERED flag is also set, then the CUDA array is a collection of cubemaps
- * and Depth must be a multiple of six.
- */
-#define CUDA_ARRAY3D_CUBEMAP 0x04
-
-/**
- * This flag must be set in order to perform texture gather operations
- * on a CUDA array.
- */
-#define CUDA_ARRAY3D_TEXTURE_GATHER 0x08
-
-/**
- * This flag if set indicates that the CUDA
- * array is a DEPTH_TEXTURE.
-*/
-#define CUDA_ARRAY3D_DEPTH_TEXTURE 0x10
-
-/**
- * Override the texref format with a format inferred from the array.
- * Flag for ::cuTexRefSetArray()
- */
-#define CU_TRSA_OVERRIDE_FORMAT 0x01
-
-/**
- * Read the texture as integers rather than promoting the values to floats
- * in the range [0,1].
- * Flag for ::cuTexRefSetFlags()
- */
-#define CU_TRSF_READ_AS_INTEGER 0x01
-
-/**
- * Use normalized texture coordinates in the range [0,1) instead of [0,dim).
- * Flag for ::cuTexRefSetFlags()
- */
-#define CU_TRSF_NORMALIZED_COORDINATES 0x02
-
-/**
- * Perform sRGB->linear conversion during texture read.
- * Flag for ::cuTexRefSetFlags()
- */
-#define CU_TRSF_SRGB 0x10
-
-/**
- * End of array terminator for the \p extra parameter to
- * ::cuLaunchKernel
- */
-#define CU_LAUNCH_PARAM_END ((void*)0x00)
-
-/**
- * Indicator that the next value in the \p extra parameter to
- * ::cuLaunchKernel will be a pointer to a buffer containing all kernel
- * parameters used for launching kernel \p f. This buffer needs to
- * honor all alignment/padding requirements of the individual parameters.
- * If ::CU_LAUNCH_PARAM_BUFFER_SIZE is not also specified in the
- * \p extra array, then ::CU_LAUNCH_PARAM_BUFFER_POINTER will have no
- * effect.
- */
-#define CU_LAUNCH_PARAM_BUFFER_POINTER ((void*)0x01)
-
-/**
- * Indicator that the next value in the \p extra parameter to
- * ::cuLaunchKernel will be a pointer to a size_t which contains the
- * size of the buffer specified with ::CU_LAUNCH_PARAM_BUFFER_POINTER.
- * It is required that ::CU_LAUNCH_PARAM_BUFFER_POINTER also be specified
- * in the \p extra array if the value associated with
- * ::CU_LAUNCH_PARAM_BUFFER_SIZE is not zero.
- */
-#define CU_LAUNCH_PARAM_BUFFER_SIZE ((void*)0x02)
-
-/**
- * For texture references loaded into the module, use default texunit from
- * texture reference.
- */
-#define CU_PARAM_TR_DEFAULT -1
-
-/** @} */ /* END CUDA_TYPES */
-
-#ifdef _WIN32
-#define CUDAAPI __stdcall
-#else
-#define CUDAAPI
-#endif
-
-/**
- * \defgroup CUDA_ERROR Error Handling
- *
- * ___MANBRIEF___ error handling functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the error handling functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Gets the string description of an error code
- *
- * Sets \p *pStr to the address of a NULL-terminated string description
- * of the error code \p error.
- * If the error code is not recognized, ::CUDA_ERROR_INVALID_VALUE
- * will be returned and \p *pStr will be set to the NULL address.
- *
- * \param error - Error code to convert to string
- * \param pStr - Address of the string pointer.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::CUresult
- */
-CUresult CUDAAPI cuGetErrorString(CUresult error, const char **pStr);
-
-/**
- * \brief Gets the string representation of an error code enum name
- *
- * Sets \p *pStr to the address of a NULL-terminated string representation
- * of the name of the enum error code \p error.
- * If the error code is not recognized, ::CUDA_ERROR_INVALID_VALUE
- * will be returned and \p *pStr will be set to the NULL address.
- *
- * \param error - Error code to convert to string
- * \param pStr - Address of the string pointer.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::CUresult
- */
-CUresult CUDAAPI cuGetErrorName(CUresult error, const char **pStr);
-
-/** @} */ /* END CUDA_ERROR */
-
-/**
- * \defgroup CUDA_INITIALIZE Initialization
- *
- * ___MANBRIEF___ initialization functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the initialization functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Initialize the CUDA driver API
- *
- * Initializes the driver API and must be called before any other function from
- * the driver API. Currently, the \p Flags parameter must be 0. If ::cuInit()
- * has not been called, any function from the driver API will return
- * ::CUDA_ERROR_NOT_INITIALIZED.
- *
- * \param Flags - Initialization flag for CUDA.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- */
-CUresult CUDAAPI cuInit(unsigned int Flags);
-
-/** @} */ /* END CUDA_INITIALIZE */
-
-/**
- * \defgroup CUDA_VERSION Version Management
- *
- * ___MANBRIEF___ version management functions of the low-level CUDA driver
- * API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the version management functions of the low-level
- * CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Returns the CUDA driver version
- *
- * Returns in \p *driverVersion the version number of the installed CUDA
- * driver. This function automatically returns ::CUDA_ERROR_INVALID_VALUE if
- * the \p driverVersion argument is NULL.
- *
- * \param driverVersion - Returns the CUDA driver version
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- */
-CUresult CUDAAPI cuDriverGetVersion(int *driverVersion);
-
-/** @} */ /* END CUDA_VERSION */
-
-/**
- * \defgroup CUDA_DEVICE Device Management
- *
- * ___MANBRIEF___ device management functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the device management functions of the low-level
- * CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Returns a handle to a compute device
- *
- * Returns in \p *device a device handle given an ordinal in the range [0,
- * ::cuDeviceGetCount()-1].
- *
- * \param device - Returned device handle
- * \param ordinal - Device number to get handle for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetAttribute,
- * ::cuDeviceGetCount,
- * ::cuDeviceGetName,
- * ::cuDeviceTotalMem
- */
-CUresult CUDAAPI cuDeviceGet(CUdevice *device, int ordinal);
-
-/**
- * \brief Returns the number of compute-capable devices
- *
- * Returns in \p *count the number of devices with compute capability greater
- * than or equal to 1.0 that are available for execution. If there is no such
- * device, ::cuDeviceGetCount() returns 0.
- *
- * \param count - Returned number of compute-capable devices
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetAttribute,
- * ::cuDeviceGetName,
- * ::cuDeviceGet,
- * ::cuDeviceTotalMem
- */
-CUresult CUDAAPI cuDeviceGetCount(int *count);
-
-/**
- * \brief Returns an identifer string for the device
- *
- * Returns an ASCII string identifying the device \p dev in the NULL-terminated
- * string pointed to by \p name. \p len specifies the maximum length of the
- * string that may be returned.
- *
- * \param name - Returned identifier string for the device
- * \param len - Maximum length of string to store in \p name
- * \param dev - Device to get identifier string for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetAttribute,
- * ::cuDeviceGetCount,
- * ::cuDeviceGet,
- * ::cuDeviceTotalMem
- */
-CUresult CUDAAPI cuDeviceGetName(char *name, int len, CUdevice dev);
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Returns the total amount of memory on the device
- *
- * Returns in \p *bytes the total amount of memory available on the device
- * \p dev in bytes.
- *
- * \param bytes - Returned memory available on device in bytes
- * \param dev - Device handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetAttribute,
- * ::cuDeviceGetCount,
- * ::cuDeviceGetName,
- * ::cuDeviceGet,
- */
-CUresult CUDAAPI cuDeviceTotalMem(size_t *bytes, CUdevice dev);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Returns information about the device
- *
- * Returns in \p *pi the integer value of the attribute \p attrib on device
- * \p dev. The supported attributes are:
- * - ::CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK: Maximum number of threads per
- * block;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X: Maximum x-dimension of a block;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y: Maximum y-dimension of a block;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z: Maximum z-dimension of a block;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X: Maximum x-dimension of a grid;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y: Maximum y-dimension of a grid;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z: Maximum z-dimension of a grid;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK: Maximum amount of
- * shared memory available to a thread block in bytes;
- * - ::CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY: Memory available on device for
- * __constant__ variables in a CUDA C kernel in bytes;
- * - ::CU_DEVICE_ATTRIBUTE_WARP_SIZE: Warp size in threads;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_PITCH: Maximum pitch in bytes allowed by the
- * memory copy functions that involve memory regions allocated through
- * ::cuMemAllocPitch();
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH: Maximum 1D 
- * texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH: Maximum width
- * for a 1D texture bound to linear memory;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH: Maximum 
- * mipmapped 1D texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH: Maximum 2D 
- * texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT: Maximum 2D 
- * texture height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH: Maximum width
- * for a 2D texture bound to linear memory;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT: Maximum height
- * for a 2D texture bound to linear memory;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH: Maximum pitch
- * in bytes for a 2D texture bound to linear memory;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH: Maximum 
- * mipmapped 2D texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT: Maximum
- * mipmapped 2D texture height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH: Maximum 3D 
- * texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT: Maximum 3D 
- * texture height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH: Maximum 3D 
- * texture depth;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE: 
- * Alternate maximum 3D texture width, 0 if no alternate
- * maximum 3D texture size is supported;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE: 
- * Alternate maximum 3D texture height, 0 if no alternate
- * maximum 3D texture size is supported;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE: 
- * Alternate maximum 3D texture depth, 0 if no alternate
- * maximum 3D texture size is supported;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_WIDTH:
- * Maximum cubemap texture width or height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH: 
- * Maximum 1D layered texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS: 
- * Maximum layers in a 1D layered texture;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_WIDTH: 
- * Maximum 2D layered texture width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_HEIGHT: 
- * Maximum 2D layered texture height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LAYERED_LAYERS: 
- * Maximum layers in a 2D layered texture;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH: 
- * Maximum cubemap layered texture width or height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS: 
- * Maximum layers in a cubemap layered texture;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_WIDTH:
- * Maximum 1D surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_WIDTH:
- * Maximum 2D surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_HEIGHT:
- * Maximum 2D surface height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_WIDTH:
- * Maximum 3D surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_HEIGHT:
- * Maximum 3D surface height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE3D_DEPTH:
- * Maximum 3D surface depth;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_WIDTH:
- * Maximum 1D layered surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE1D_LAYERED_LAYERS:
- * Maximum layers in a 1D layered surface;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_WIDTH:
- * Maximum 2D layered surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_HEIGHT:
- * Maximum 2D layered surface height;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACE2D_LAYERED_LAYERS:
- * Maximum layers in a 2D layered surface;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_WIDTH:
- * Maximum cubemap surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH:
- * Maximum cubemap layered surface width;
- * - ::CU_DEVICE_ATTRIBUTE_MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS:
- * Maximum layers in a cubemap layered surface;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK: Maximum number of 32-bit
- * registers available to a thread block;
- * - ::CU_DEVICE_ATTRIBUTE_CLOCK_RATE: The typical clock frequency in kilohertz;
- * - ::CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT: Alignment requirement; texture
- * base addresses aligned to ::textureAlign bytes do not need an offset
- * applied to texture fetches;
- * - ::CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT: Pitch alignment requirement
- * for 2D texture references bound to pitched memory;
- * - ::CU_DEVICE_ATTRIBUTE_GPU_OVERLAP: 1 if the device can concurrently copy
- * memory between host and device while executing a kernel, or 0 if not;
- * - ::CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT: Number of multiprocessors on
- * the device;
- * - ::CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT: 1 if there is a run time limit
- * for kernels executed on the device, or 0 if not;
- * - ::CU_DEVICE_ATTRIBUTE_INTEGRATED: 1 if the device is integrated with the
- * memory subsystem, or 0 if not;
- * - ::CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY: 1 if the device can map host
- * memory into the CUDA address space, or 0 if not;
- * - ::CU_DEVICE_ATTRIBUTE_COMPUTE_MODE: Compute mode that device is currently
- * in. Available modes are as follows:
- * - ::CU_COMPUTEMODE_DEFAULT: Default mode - Device is not restricted and
- * can have multiple CUDA contexts present at a single time.
- * - ::CU_COMPUTEMODE_EXCLUSIVE: Compute-exclusive mode - Device can have
- * only one CUDA context present on it at a time.
- * - ::CU_COMPUTEMODE_PROHIBITED: Compute-prohibited mode - Device is
- * prohibited from creating new CUDA contexts.
- * - ::CU_COMPUTEMODE_EXCLUSIVE_PROCESS: Compute-exclusive-process mode - Device
- * can have only one context used by a single process at a time.
- * - ::CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS: 1 if the device supports
- * executing multiple kernels within the same context simultaneously, or 0 if
- * not. It is not guaranteed that multiple kernels will be resident
- * on the device concurrently so this feature should not be relied upon for
- * correctness;
- * - ::CU_DEVICE_ATTRIBUTE_ECC_ENABLED: 1 if error correction is enabled on the
- * device, 0 if error correction is disabled or not supported by the device;
- * - ::CU_DEVICE_ATTRIBUTE_PCI_BUS_ID: PCI bus identifier of the device;
- * - ::CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID: PCI device (also known as slot) identifier
- * of the device;
- * - ::CU_DEVICE_ATTRIBUTE_TCC_DRIVER: 1 if the device is using a TCC driver. TCC
- * is only available on Tesla hardware running Windows Vista or later;
- * - ::CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE: Peak memory clock frequency in kilohertz;
- * - ::CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH: Global memory bus width in bits;
- * - ::CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE: Size of L2 cache in bytes. 0 if the device doesn't have L2 cache;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR: Maximum resident threads per multiprocessor;
- * - ::CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING: 1 if the device shares a unified address space with 
- * the host, or 0 if not;
- * - ::CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR: Major compute capability version number;
- * - ::CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR: Minor compute capability version number;
- * - ::CU_DEVICE_ATTRIBUTE_GLOBAL_L1_CACHE_SUPPORTED: 1 if device supports caching globals 
- * in L1 cache, 0 if caching globals in L1 cache is not supported by the device;
- * - ::CU_DEVICE_ATTRIBUTE_LOCAL_L1_CACHE_SUPPORTED: 1 if device supports caching locals 
- * in L1 cache, 0 if caching locals in L1 cache is not supported by the device;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_MULTIPROCESSOR: Maximum amount of
- * shared memory available to a multiprocessor in bytes; this amount is shared
- * by all thread blocks simultaneously resident on a multiprocessor;
- * - ::CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_MULTIPROCESSOR: Maximum number of 32-bit
- * registers available to a multiprocessor; this number is shared by all thread
- * blocks simultaneously resident on a multiprocessor;
- * - ::CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY: 1 if device supports allocating managed memory
- * on this system, 0 if allocating managed memory is not supported by the device on this system.
- * - ::CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD: 1 if device is on a multi-GPU board, 0 if not.
- * - ::CU_DEVICE_ATTRIBUTE_MULTI_GPU_BOARD_GROUP_ID: Unique identifier for a group of devices
- * associated with the same board. Devices on the same multi-GPU board will share the same identifier.
- *
- * \param pi - Returned device attribute value
- * \param attrib - Device attribute to query
- * \param dev - Device handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetCount,
- * ::cuDeviceGetName,
- * ::cuDeviceGet,
- * ::cuDeviceTotalMem
- */
-CUresult CUDAAPI cuDeviceGetAttribute(int *pi, CUdevice_attribute attrib, CUdevice dev);
-
-/** @} */ /* END CUDA_DEVICE */
-
-/**
- * \defgroup CUDA_DEVICE_DEPRECATED Device Management [DEPRECATED]
- *
- * ___MANBRIEF___ deprecated device management functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the device management functions of the low-level
- * CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Returns properties for a selected device
- *
- * \deprecated
- *
- * This function was deprecated as of CUDA 5.0 and replaced by ::cuDeviceGetAttribute().
- *
- * Returns in \p *prop the properties of device \p dev. The ::CUdevprop
- * structure is defined as:
- *
- * \code
- typedef struct CUdevprop_st {
- int maxThreadsPerBlock;
- int maxThreadsDim[3];
- int maxGridSize[3];
- int sharedMemPerBlock;
- int totalConstantMemory;
- int SIMDWidth;
- int memPitch;
- int regsPerBlock;
- int clockRate;
- int textureAlign
- } CUdevprop;
- * \endcode
- * where:
- *
- * - ::maxThreadsPerBlock is the maximum number of threads per block;
- * - ::maxThreadsDim[3] is the maximum sizes of each dimension of a block;
- * - ::maxGridSize[3] is the maximum sizes of each dimension of a grid;
- * - ::sharedMemPerBlock is the total amount of shared memory available per
- * block in bytes;
- * - ::totalConstantMemory is the total amount of constant memory available on
- * the device in bytes;
- * - ::SIMDWidth is the warp size;
- * - ::memPitch is the maximum pitch allowed by the memory copy functions that
- * involve memory regions allocated through ::cuMemAllocPitch();
- * - ::regsPerBlock is the total number of registers available per block;
- * - ::clockRate is the clock frequency in kilohertz;
- * - ::textureAlign is the alignment requirement; texture base addresses that
- * are aligned to ::textureAlign bytes do not need an offset applied to
- * texture fetches.
- *
- * \param prop - Returned properties of device
- * \param dev - Device to get properties for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetAttribute,
- * ::cuDeviceGetCount,
- * ::cuDeviceGetName,
- * ::cuDeviceGet,
- * ::cuDeviceTotalMem
- */
-CUresult CUDAAPI cuDeviceGetProperties(CUdevprop *prop, CUdevice dev);
-
-/**
- * \brief Returns the compute capability of the device
- *
- * \deprecated
- *
- * This function was deprecated as of CUDA 5.0 and its functionality superceded
- * by ::cuDeviceGetAttribute(). 
- *
- * Returns in \p *major and \p *minor the major and minor revision numbers that
- * define the compute capability of the device \p dev.
- *
- * \param major - Major revision number
- * \param minor - Minor revision number
- * \param dev - Device handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa
- * ::cuDeviceGetAttribute,
- * ::cuDeviceGetCount,
- * ::cuDeviceGetName,
- * ::cuDeviceGet,
- * ::cuDeviceTotalMem
- */
-CUresult CUDAAPI cuDeviceComputeCapability(int *major, int *minor, CUdevice dev);
-
-/** @} */ /* END CUDA_DEVICE_DEPRECATED */
-
-/**
- * \defgroup CUDA_PRIMARY_CTX Primary Context Management
- *
- * ___MANBRIEF___ primary context management functions of the low-level CUDA driver
- * API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the primary context management functions of the low-level
- * CUDA driver application programming interface.
- *
- * The primary context unique per device and it's shared with CUDA runtime API.
- * Those functions allows seemless integration with other libraries using CUDA.
- *
- * @{
- */
-
-#if __CUDA_API_VERSION >= 7000
-
-/**
- * \brief Retain the primary context on the GPU
- *
- * Retains the primary context on the device, creating it if necessary,
- * increasing its usage count. The caller must call
- * ::cuDevicePrimaryCtxRelease() when done using the context.
- * Unlike ::cuCtxCreate() the newly created context is not pushed onto the stack.
- *
- * Context creation will fail with ::CUDA_ERROR_UNKNOWN if the compute mode of
- * the device is ::CU_COMPUTEMODE_PROHIBITED. Similarly, context creation will
- * also fail with ::CUDA_ERROR_UNKNOWN if the compute mode for the device is
- * set to ::CU_COMPUTEMODE_EXCLUSIVE and there is already an active, non-primary,
- * context on the device. The function ::cuDeviceGetAttribute() can be used with
- * ::CU_DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the
- * device. The nvidia-smi tool can be used to set the compute mode for
- * devices. Documentation for nvidia-smi can be obtained by passing a
- * -h option to it.
- *
- * Please note that the primary context always supports pinned allocations. Other
- * flags can be specified by ::cuDevicePrimaryCtxSetFlags().
- *
- * \param pctx - Returned context handle of the new context
- * \param dev - Device for which primary context is requested
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_DEVICE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa ::cuDevicePrimaryCtxRelease,
- * ::cuDevicePrimaryCtxSetFlags,
- * ::cuCtxCreate,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuDevicePrimaryCtxRetain(CUcontext *pctx, CUdevice dev);
-
-/**
- * \brief Release the primary context on the GPU
- *
- * Releases the primary context interop on the device by decreasing the usage
- * count by 1. If the usage drops to 0 the primary context of device \p dev
- * will be destroyed regardless of how many threads it is current to.
- *
- * Please note that unlike ::cuCtxDestroy() this method does not pop the context
- * from stack in any circumstances.
- *
- * \param dev - Device which primary context is released
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa ::cuDevicePrimaryCtxRetain,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuDevicePrimaryCtxRelease(CUdevice dev);
-
-/**
- * \brief Set flags for the primary context
- *
- * Sets the flags for the primary context on the device overwriting perviously
- * set ones. If the primary context is already created
- * ::CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE is returned.
- *
- * The three LSBs of the \p flags parameter can be used to control how the OS
- * thread, which owns the CUDA context at the time of an API call, interacts
- * with the OS scheduler when waiting for results from the GPU. Only one of
- * the scheduling flags can be set when creating a context.
- *
- * - ::CU_CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for
- * results from the GPU. This can decrease latency when waiting for the GPU,
- * but may lower the performance of CPU threads if they are performing work in
- * parallel with the CUDA thread.
- *
- * - ::CU_CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for
- * results from the GPU. This can increase latency when waiting for the GPU,
- * but can increase the performance of CPU threads performing work in parallel
- * with the GPU.
- *
- * - ::CU_CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a
- * synchronization primitive when waiting for the GPU to finish work.
- *
- * - ::CU_CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a
- * synchronization primitive when waiting for the GPU to finish work. 
- * Deprecated: This flag was deprecated as of CUDA 4.0 and was
- * replaced with ::CU_CTX_SCHED_BLOCKING_SYNC.
- *
- * - ::CU_CTX_SCHED_AUTO: The default value if the \p flags parameter is zero,
- * uses a heuristic based on the number of active CUDA contexts in the
- * process \e C and the number of logical processors in the system \e P. If
- * \e C > \e P, then CUDA will yield to other OS threads when waiting for
- * the GPU (::CU_CTX_SCHED_YIELD), otherwise CUDA will not yield while
- * waiting for results and actively spin on the processor (::CU_CTX_SCHED_SPIN).
- * However, on low power devices like Tegra, it always defaults to
- * ::CU_CTX_SCHED_BLOCKING_SYNC.
- *
- * - ::CU_CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory
- * after resizing local memory for a kernel. This can prevent thrashing by
- * local memory allocations when launching many kernels with high local
- * memory usage at the cost of potentially increased memory usage.
- *
- * \param dev - Device for which the primary context flags are set
- * \param flags - New flags for the device
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_DEVICE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE
- * \notefnerr
- *
- * \sa ::cuDevicePrimaryCtxRetain,
- * ::cuDevicePrimaryCtxGetState,
- * ::cuCtxCreate,
- * ::cuCtxGetFlags
- */
-CUresult CUDAAPI cuDevicePrimaryCtxSetFlags(CUdevice dev, unsigned int flags);
-
-/**
- * \brief Get the state of the primary context
- *
- * Returns in \p *flags the flags for the primary context of \p dev, and in
- * \p *active whether it is active. See ::cuDevicePrimaryCtxSetFlags for flag
- * values.
- *
- * \param dev - Device to get primary context flags for
- * \param flags - Pointer to store flags
- * \param active - Pointer to store context state; 0 = inactive, 1 = active
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_DEVICE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * \notefnerr
- *
- * \sa ::cuDevicePrimaryCtxSetFlags,
- * ::cuCtxGetFlags
- */
-CUresult CUDAAPI cuDevicePrimaryCtxGetState(CUdevice dev, unsigned int *flags, int *active);
-
-/**
- * \brief Destroy all allocations and reset all state on the primary context
- *
- * Explicitly destroys and cleans up all resources associated with the current
- * device in the current process.
- *
- * Note that it is responsibility of the calling function to ensure that no
- * other module in the process is using the device any more. For that reason
- * it is recommended to use ::cuDevicePrimaryCtxRelease() in most cases.
- * However it is safe for other modules to call ::cuDevicePrimaryCtxRelease()
- * even after resetting the device.
- *
- * \param dev - Device for which primary context is destroyed
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_DEVICE,
- * ::CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE
- * \notefnerr
- *
- * \sa ::cuDevicePrimaryCtxRetain,
- * ::cuDevicePrimaryCtxRelease,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- *
- */
-CUresult CUDAAPI cuDevicePrimaryCtxReset(CUdevice dev);
-
-#endif /* __CUDA_API_VERSION >= 7000 */
-
-/** @} */ /* END CUDA_PRIMARY_CTX */
-
-
-/**
- * \defgroup CUDA_CTX Context Management
- *
- * ___MANBRIEF___ context management functions of the low-level CUDA driver
- * API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the context management functions of the low-level
- * CUDA driver application programming interface.
- *
- * @{
- */
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Create a CUDA context
- *
- * Creates a new CUDA context and associates it with the calling thread. The
- * \p flags parameter is described below. The context is created with a usage
- * count of 1 and the caller of ::cuCtxCreate() must call ::cuCtxDestroy() or
- * when done using the context. If a context is already current to the thread, 
- * it is supplanted by the newly created context and may be restored by a subsequent 
- * call to ::cuCtxPopCurrent().
- *
- * The three LSBs of the \p flags parameter can be used to control how the OS
- * thread, which owns the CUDA context at the time of an API call, interacts
- * with the OS scheduler when waiting for results from the GPU. Only one of
- * the scheduling flags can be set when creating a context.
- *
- * - ::CU_CTX_SCHED_SPIN: Instruct CUDA to actively spin when waiting for
- * results from the GPU. This can decrease latency when waiting for the GPU,
- * but may lower the performance of CPU threads if they are performing work in
- * parallel with the CUDA thread.
- *
- * - ::CU_CTX_SCHED_YIELD: Instruct CUDA to yield its thread when waiting for
- * results from the GPU. This can increase latency when waiting for the GPU,
- * but can increase the performance of CPU threads performing work in parallel
- * with the GPU.
- * 
- * - ::CU_CTX_SCHED_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a
- * synchronization primitive when waiting for the GPU to finish work.
- *
- * - ::CU_CTX_BLOCKING_SYNC: Instruct CUDA to block the CPU thread on a
- * synchronization primitive when waiting for the GPU to finish work. 
- * Deprecated: This flag was deprecated as of CUDA 4.0 and was
- * replaced with ::CU_CTX_SCHED_BLOCKING_SYNC. 
- *
- * - ::CU_CTX_SCHED_AUTO: The default value if the \p flags parameter is zero,
- * uses a heuristic based on the number of active CUDA contexts in the
- * process \e C and the number of logical processors in the system \e P. If
- * \e C > \e P, then CUDA will yield to other OS threads when waiting for 
- * the GPU (::CU_CTX_SCHED_YIELD), otherwise CUDA will not yield while 
- * waiting for results and actively spin on the processor (::CU_CTX_SCHED_SPIN). 
- * However, on low power devices like Tegra, it always defaults to 
- * ::CU_CTX_SCHED_BLOCKING_SYNC.
- *
- * - ::CU_CTX_MAP_HOST: Instruct CUDA to support mapped pinned allocations.
- * This flag must be set in order to allocate pinned host memory that is
- * accessible to the GPU.
- *
- * - ::CU_CTX_LMEM_RESIZE_TO_MAX: Instruct CUDA to not reduce local memory
- * after resizing local memory for a kernel. This can prevent thrashing by
- * local memory allocations when launching many kernels with high local
- * memory usage at the cost of potentially increased memory usage.
- *
- * Context creation will fail with ::CUDA_ERROR_UNKNOWN if the compute mode of
- * the device is ::CU_COMPUTEMODE_PROHIBITED. Similarly, context creation will
- * also fail with ::CUDA_ERROR_UNKNOWN if the compute mode for the device is
- * set to ::CU_COMPUTEMODE_EXCLUSIVE and there is already an active context on
- * the device. The function ::cuDeviceGetAttribute() can be used with
- * ::CU_DEVICE_ATTRIBUTE_COMPUTE_MODE to determine the compute mode of the
- * device. The nvidia-smi tool can be used to set the compute mode for
- * devices. Documentation for nvidia-smi can be obtained by passing a
- * -h option to it.
- *
- * \param pctx - Returned context handle of the new context
- * \param flags - Context creation flags
- * \param dev - Device to create context on
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_DEVICE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxCreate(CUcontext *pctx, unsigned int flags, CUdevice dev);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Destroy a CUDA context
- *
- * Destroys the CUDA context specified by \p ctx. The context \p ctx will be
- * destroyed regardless of how many threads it is current to.
- * It is the responsibility of the calling function to ensure that no API
- * call issues using \p ctx while ::cuCtxDestroy() is executing.
- *
- * If \p ctx is current to the calling thread then \p ctx will also be 
- * popped from the current thread's context stack (as though ::cuCtxPopCurrent()
- * were called). If \p ctx is current to other threads, then \p ctx will
- * remain current to those threads, and attempting to access \p ctx from
- * those threads will result in the error ::CUDA_ERROR_CONTEXT_IS_DESTROYED.
- *
- * \param ctx - Context to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxDestroy(CUcontext ctx);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Pushes a context on the current CPU thread
- *
- * Pushes the given context \p ctx onto the CPU thread's stack of current
- * contexts. The specified context becomes the CPU thread's current context, so
- * all CUDA functions that operate on the current context are affected.
- *
- * The previous current context may be made current again by calling
- * ::cuCtxDestroy() or ::cuCtxPopCurrent().
- *
- * \param ctx - Context to push
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxPushCurrent(CUcontext ctx);
-
-/**
- * \brief Pops the current CUDA context from the current CPU thread.
- *
- * Pops the current CUDA context from the CPU thread and passes back the 
- * old context handle in \p *pctx. That context may then be made current 
- * to a different CPU thread by calling ::cuCtxPushCurrent().
- *
- * If a context was current to the CPU thread before ::cuCtxCreate() or
- * ::cuCtxPushCurrent() was called, this function makes that context current to
- * the CPU thread again.
- *
- * \param pctx - Returned new context handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxPopCurrent(CUcontext *pctx);
-
-/**
- * \brief Binds the specified CUDA context to the calling CPU thread
- *
- * Binds the specified CUDA context to the calling CPU thread.
- * If \p ctx is NULL then the CUDA context previously bound to the
- * calling CPU thread is unbound and ::CUDA_SUCCESS is returned.
- *
- * If there exists a CUDA context stack on the calling CPU thread, this
- * will replace the top of that stack with \p ctx. 
- * If \p ctx is NULL then this will be equivalent to popping the top
- * of the calling CPU thread's CUDA context stack (or a no-op if the
- * calling CPU thread's CUDA context stack is empty).
- *
- * \param ctx - Context to bind to the calling CPU thread
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT
- * \notefnerr
- *
- * \sa ::cuCtxGetCurrent, ::cuCtxCreate, ::cuCtxDestroy
- */
-CUresult CUDAAPI cuCtxSetCurrent(CUcontext ctx);
-
-/**
- * \brief Returns the CUDA context bound to the calling CPU thread.
- *
- * Returns in \p *pctx the CUDA context bound to the calling CPU thread.
- * If no context is bound to the calling CPU thread then \p *pctx is
- * set to NULL and ::CUDA_SUCCESS is returned.
- *
- * \param pctx - Returned context handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * \notefnerr
- *
- * \sa ::cuCtxSetCurrent, ::cuCtxCreate, ::cuCtxDestroy
- */
-CUresult CUDAAPI cuCtxGetCurrent(CUcontext *pctx);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-/**
- * \brief Returns the device ID for the current context
- *
- * Returns in \p *device the ordinal of the current context's device.
- *
- * \param device - Returned device ID for the current context
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxGetDevice(CUdevice *device);
-
-#if __CUDA_API_VERSION >= 7000
-/**
- * \brief Returns the flags for the current context
- *
- * Returns in \p *flags the flags of the current context. See ::cuCtxCreate
- * for flag values.
- *
- * \param flags - Pointer to store flags of current context
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetCurrent,
- * ::cuCtxGetDevice
- * ::cuCtxGetLimit,
- * ::cuCtxGetSharedMemConfig,
- * ::cuCtxGetStreamPriorityRange
- */
-CUresult CUDAAPI cuCtxGetFlags(unsigned int *flags);
-#endif /* __CUDA_API_VERSION >= 7000 */
-
-/**
- * \brief Block for a context's tasks to complete
- *
- * Blocks until the device has completed all preceding requested tasks.
- * ::cuCtxSynchronize() returns an error if one of the preceding tasks failed.
- * If the context was created with the ::CU_CTX_SCHED_BLOCKING_SYNC flag, the 
- * CPU thread will block until the GPU context has finished its work.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit
- */
-CUresult CUDAAPI cuCtxSynchronize(void);
-
-/**
- * \brief Set resource limits
- *
- * Setting \p limit to \p value is a request by the application to update
- * the current limit maintained by the context. The driver is free to
- * modify the requested value to meet h/w requirements (this could be
- * clamping to minimum or maximum values, rounding up to nearest element
- * size, etc). The application can use ::cuCtxGetLimit() to find out exactly
- * what the limit has been set to.
- *
- * Setting each ::CUlimit has its own specific restrictions, so each is
- * discussed here.
- *
- * - ::CU_LIMIT_STACK_SIZE controls the stack size in bytes of each GPU thread.
- * This limit is only applicable to devices of compute capability 2.0 and
- * higher. Attempting to set this limit on devices of compute capability
- * less than 2.0 will result in the error ::CUDA_ERROR_UNSUPPORTED_LIMIT
- * being returned.
- *
- * - ::CU_LIMIT_PRINTF_FIFO_SIZE controls the size in bytes of the FIFO used
- * by the ::printf() device system call. Setting ::CU_LIMIT_PRINTF_FIFO_SIZE
- * must be performed before launching any kernel that uses the ::printf()
- * device system call, otherwise ::CUDA_ERROR_INVALID_VALUE will be returned.
- * This limit is only applicable to devices of compute capability 2.0 and
- * higher. Attempting to set this limit on devices of compute capability
- * less than 2.0 will result in the error ::CUDA_ERROR_UNSUPPORTED_LIMIT
- * being returned.
- *
- * - ::CU_LIMIT_MALLOC_HEAP_SIZE controls the size in bytes of the heap used
- * by the ::malloc() and ::free() device system calls. Setting
- * ::CU_LIMIT_MALLOC_HEAP_SIZE must be performed before launching any kernel
- * that uses the ::malloc() or ::free() device system calls, otherwise
- * ::CUDA_ERROR_INVALID_VALUE will be returned. This limit is only applicable
- * to devices of compute capability 2.0 and higher. Attempting to set this
- * limit on devices of compute capability less than 2.0 will result in the
- * error ::CUDA_ERROR_UNSUPPORTED_LIMIT being returned.
- *
- * - ::CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH controls the maximum nesting depth of
- * a grid at which a thread can safely call ::cudaDeviceSynchronize(). Setting
- * this limit must be performed before any launch of a kernel that uses the 
- * device runtime and calls ::cudaDeviceSynchronize() above the default sync
- * depth, two levels of grids. Calls to ::cudaDeviceSynchronize() will fail 
- * with error code ::cudaErrorSyncDepthExceeded if the limitation is 
- * violated. This limit can be set smaller than the default or up the maximum
- * launch depth of 24. When setting this limit, keep in mind that additional
- * levels of sync depth require the driver to reserve large amounts of device
- * memory which can no longer be used for user allocations. If these 
- * reservations of device memory fail, ::cuCtxSetLimit will return 
- * ::CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value.
- * This limit is only applicable to devices of compute capability 3.5 and
- * higher. Attempting to set this limit on devices of compute capability less
- * than 3.5 will result in the error ::CUDA_ERROR_UNSUPPORTED_LIMIT being 
- * returned.
- *
- * - ::CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT controls the maximum number of
- * outstanding device runtime launches that can be made from the current
- * context. A grid is outstanding from the point of launch up until the grid
- * is known to have been completed. Device runtime launches which violate 
- * this limitation fail and return ::cudaErrorLaunchPendingCountExceeded when
- * ::cudaGetLastError() is called after launch. If more pending launches than
- * the default (2048 launches) are needed for a module using the device
- * runtime, this limit can be increased. Keep in mind that being able to
- * sustain additional pending launches will require the driver to reserve
- * larger amounts of device memory upfront which can no longer be used for
- * allocations. If these reservations fail, ::cuCtxSetLimit will return
- * ::CUDA_ERROR_OUT_OF_MEMORY, and the limit can be reset to a lower value.
- * This limit is only applicable to devices of compute capability 3.5 and
- * higher. Attempting to set this limit on devices of compute capability less
- * than 3.5 will result in the error ::CUDA_ERROR_UNSUPPORTED_LIMIT being
- * returned.
- *
- * \param limit - Limit to set
- * \param value - Size of limit
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_UNSUPPORTED_LIMIT,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxSetLimit(CUlimit limit, size_t value);
-
-/**
- * \brief Returns resource limits
- *
- * Returns in \p *pvalue the current size of \p limit. The supported
- * ::CUlimit values are:
- * - ::CU_LIMIT_STACK_SIZE: stack size in bytes of each GPU thread.
- * - ::CU_LIMIT_PRINTF_FIFO_SIZE: size in bytes of the FIFO used by the
- * ::printf() device system call.
- * - ::CU_LIMIT_MALLOC_HEAP_SIZE: size in bytes of the heap used by the
- * ::malloc() and ::free() device system calls.
- * - ::CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH: maximum grid depth at which a thread
- * can issue the device runtime call ::cudaDeviceSynchronize() to wait on
- * child grid launches to complete.
- * - ::CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT: maximum number of outstanding
- * device runtime launches that can be made from this context.
- *
- * \param limit - Limit to query
- * \param pvalue - Returned size of limit
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_UNSUPPORTED_LIMIT
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxGetLimit(size_t *pvalue, CUlimit limit);
-
-/**
- * \brief Returns the preferred cache configuration for the current context.
- *
- * On devices where the L1 cache and shared memory use the same hardware
- * resources, this function returns through \p pconfig the preferred cache configuration
- * for the current context. This is only a preference. The driver will use
- * the requested configuration if possible, but it is free to choose a different
- * configuration if required to execute functions.
- *
- * This will return a \p pconfig of ::CU_FUNC_CACHE_PREFER_NONE on devices
- * where the size of the L1 cache and shared memory are fixed.
- *
- * The supported cache configurations are:
- * - ::CU_FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default)
- * - ::CU_FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache
- * - ::CU_FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory
- * - ::CU_FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory
- *
- * \param pconfig - Returned cache configuration
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize,
- * ::cuFuncSetCacheConfig
- */
-CUresult CUDAAPI cuCtxGetCacheConfig(CUfunc_cache *pconfig);
-
-/**
- * \brief Sets the preferred cache configuration for the current context.
- *
- * On devices where the L1 cache and shared memory use the same hardware
- * resources, this sets through \p config the preferred cache configuration for
- * the current context. This is only a preference. The driver will use
- * the requested configuration if possible, but it is free to choose a different
- * configuration if required to execute the function. Any function preference
- * set via ::cuFuncSetCacheConfig() will be preferred over this context-wide
- * setting. Setting the context-wide cache configuration to
- * ::CU_FUNC_CACHE_PREFER_NONE will cause subsequent kernel launches to prefer
- * to not change the cache configuration unless required to launch the kernel.
- *
- * This setting does nothing on devices where the size of the L1 cache and
- * shared memory are fixed.
- *
- * Launching a kernel with a different preference than the most recent
- * preference setting may insert a device-side synchronization point.
- *
- * The supported cache configurations are:
- * - ::CU_FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default)
- * - ::CU_FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache
- * - ::CU_FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory
- * - ::CU_FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory
- *
- * \param config - Requested cache configuration
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize,
- * ::cuFuncSetCacheConfig
- */
-CUresult CUDAAPI cuCtxSetCacheConfig(CUfunc_cache config);
-
-#if __CUDA_API_VERSION >= 4020
-/**
- * \brief Returns the current shared memory configuration for the current context.
- *
- * This function will return in \p pConfig the current size of shared memory banks
- * in the current context. On devices with configurable shared memory banks, 
- * ::cuCtxSetSharedMemConfig can be used to change this setting, so that all 
- * subsequent kernel launches will by default use the new bank size. When 
- * ::cuCtxGetSharedMemConfig is called on devices without configurable shared 
- * memory, it will return the fixed bank size of the hardware.
- *
- * The returned bank configurations can be either:
- * - ::CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: shared memory bank width is 
- * four bytes.
- * - ::CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: shared memory bank width will
- * eight bytes.
- *
- * \param pConfig - returned shared memory configuration
- * \return 
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize,
- * ::cuCtxGetSharedMemConfig,
- * ::cuFuncSetCacheConfig,
- */
-CUresult CUDAAPI cuCtxGetSharedMemConfig(CUsharedconfig *pConfig);
-
-/**
- * \brief Sets the shared memory configuration for the current context.
- *
- * On devices with configurable shared memory banks, this function will set
- * the context's shared memory bank size which is used for subsequent kernel 
- * launches. 
- *
- * Changed the shared memory configuration between launches may insert a device
- * side synchronization point between those launches.
- *
- * Changing the shared memory bank size will not increase shared memory usage
- * or affect occupancy of kernels, but may have major effects on performance. 
- * Larger bank sizes will allow for greater potential bandwidth to shared memory,
- * but will change what kinds of accesses to shared memory will result in bank 
- * conflicts.
- *
- * This function will do nothing on devices with fixed shared memory bank size.
- *
- * The supported bank configurations are:
- * - ::CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE: set bank width to the default initial
- * setting (currently, four bytes).
- * - ::CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: set shared memory bank width to
- * be natively four bytes.
- * - ::CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: set shared memory bank width to
- * be natively eight bytes.
- *
- * \param config - requested shared memory configuration
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize,
- * ::cuCtxGetSharedMemConfig,
- * ::cuFuncSetCacheConfig,
- */
-CUresult CUDAAPI cuCtxSetSharedMemConfig(CUsharedconfig config);
-#endif
-
-/**
- * \brief Gets the context's API version.
- *
- * Returns a version number in \p version corresponding to the capabilities of
- * the context (e.g. 3010 or 3020), which library developers can use to direct
- * callers to a specific API version. If \p ctx is NULL, returns the API version
- * used to create the currently bound context.
- *
- * Note that new API versions are only introduced when context capabilities are
- * changed that break binary compatibility, so the API version and driver version
- * may be different. For example, it is valid for the API version to be 3020 while
- * the driver version is 4020.
- *
- * \param ctx - Context to check
- * \param version - Pointer to version
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxGetApiVersion(CUcontext ctx, unsigned int *version);
-
-/**
- * \brief Returns numerical values that correspond to the least and
- * greatest stream priorities.
- *
- * Returns in \p *leastPriority and \p *greatestPriority the numerical values that correspond
- * to the least and greatest stream priorities respectively. Stream priorities
- * follow a convention where lower numbers imply greater priorities. The range of
- * meaningful stream priorities is given by [\p *greatestPriority, \p *leastPriority].
- * If the user attempts to create a stream with a priority value that is
- * outside the meaningful range as specified by this API, the priority is
- * automatically clamped down or up to either \p *leastPriority or \p *greatestPriority
- * respectively. See ::cuStreamCreateWithPriority for details on creating a
- * priority stream.
- * A NULL may be passed in for \p *leastPriority or \p *greatestPriority if the value
- * is not desired.
- *
- * This function will return '0' in both \p *leastPriority and \p *greatestPriority if
- * the current context's device does not support stream priorities
- * (see ::cuDeviceGetAttribute).
- *
- * \param leastPriority - Pointer to an int in which the numerical value for least
- * stream priority is returned
- * \param greatestPriority - Pointer to an int in which the numerical value for greatest
- * stream priority is returned
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE,
- * \notefnerr
- *
- * \sa ::cuStreamCreateWithPriority,
- * ::cuStreamGetPriority,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxGetStreamPriorityRange(int *leastPriority, int *greatestPriority);
-
-/** @} */ /* END CUDA_CTX */
-
-/**
- * \defgroup CUDA_CTX_DEPRECATED Context Management [DEPRECATED]
- *
- * ___MANBRIEF___ deprecated context management functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the deprecated context management functions of the low-level
- * CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Increment a context's usage-count
- *
- * \deprecated
- *
- * Note that this function is deprecated and should not be used.
- *
- * Increments the usage count of the context and passes back a context handle
- * in \p *pctx that must be passed to ::cuCtxDetach() when the application is
- * done with the context. ::cuCtxAttach() fails if there is no context current
- * to the thread.
- *
- * Currently, the \p flags parameter must be 0.
- *
- * \param pctx - Returned context handle of the current context
- * \param flags - Context attach flags (must be 0)
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxDetach,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxAttach(CUcontext *pctx, unsigned int flags);
-
-/**
- * \brief Decrement a context's usage-count
- *
- * \deprecated
- *
- * Note that this function is deprecated and should not be used.
- *
- * Decrements the usage count of the context \p ctx, and destroys the context
- * if the usage count goes to 0. The context must be a handle that was passed
- * back by ::cuCtxCreate() or ::cuCtxAttach(), and must be current to the
- * calling thread.
- *
- * \param ctx - Context to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT
- * \notefnerr
- *
- * \sa ::cuCtxCreate,
- * ::cuCtxDestroy,
- * ::cuCtxGetApiVersion,
- * ::cuCtxGetCacheConfig,
- * ::cuCtxGetDevice,
- * ::cuCtxGetFlags,
- * ::cuCtxGetLimit,
- * ::cuCtxPopCurrent,
- * ::cuCtxPushCurrent,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxSetLimit,
- * ::cuCtxSynchronize
- */
-CUresult CUDAAPI cuCtxDetach(CUcontext ctx);
-
-/** @} */ /* END CUDA_CTX_DEPRECATED */
-
-
-/**
- * \defgroup CUDA_MODULE Module Management
- *
- * ___MANBRIEF___ module management functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the module management functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Loads a compute module
- *
- * Takes a filename \p fname and loads the corresponding module \p module into
- * the current context. The CUDA driver API does not attempt to lazily
- * allocate the resources needed by a module; if the memory for functions and
- * data (constant and global) needed by the module cannot be allocated,
- * ::cuModuleLoad() fails. The file should be a \e cubin file as output by
- * \b nvcc, or a \e PTX file either as output by \b nvcc or handwritten, or
- * a \e fatbin file as output by \b nvcc from toolchain 4.0 or later.
- *
- * \param module - Returned module
- * \param fname - Filename of module to load
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_PTX,
- * ::CUDA_ERROR_NOT_FOUND,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_FILE_NOT_FOUND,
- * ::CUDA_ERROR_NO_BINARY_FOR_GPU,
- * ::CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleLoad(CUmodule *module, const char *fname);
-
-/**
- * \brief Load a module's data
- *
- * Takes a pointer \p image and loads the corresponding module \p module into
- * the current context. The pointer may be obtained by mapping a \e cubin or
- * \e PTX or \e fatbin file, passing a \e cubin or \e PTX or \e fatbin file
- * as a NULL-terminated text string, or incorporating a \e cubin or \e fatbin
- * object into the executable resources and using operating system calls such
- * as Windows \c FindResource() to obtain the pointer.
- *
- * \param module - Returned module
- * \param image - Module data to load
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_PTX,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_NO_BINARY_FOR_GPU,
- * ::CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleLoadData(CUmodule *module, const void *image);
-
-/**
- * \brief Load a module's data with options
- *
- * Takes a pointer \p image and loads the corresponding module \p module into
- * the current context. The pointer may be obtained by mapping a \e cubin or
- * \e PTX or \e fatbin file, passing a \e cubin or \e PTX or \e fatbin file
- * as a NULL-terminated text string, or incorporating a \e cubin or \e fatbin
- * object into the executable resources and using operating system calls such
- * as Windows \c FindResource() to obtain the pointer. Options are passed as
- * an array via \p options and any corresponding parameters are passed in
- * \p optionValues. The number of total options is supplied via \p numOptions.
- * Any outputs will be returned via \p optionValues. 
- *
- * \param module - Returned module
- * \param image - Module data to load
- * \param numOptions - Number of options
- * \param options - Options for JIT
- * \param optionValues - Option values for JIT
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_PTX,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_NO_BINARY_FOR_GPU,
- * ::CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleLoadDataEx(CUmodule *module, const void *image, unsigned int numOptions, CUjit_option *options, void **optionValues);
-
-/**
- * \brief Load a module's data
- *
- * Takes a pointer \p fatCubin and loads the corresponding module \p module
- * into the current context. The pointer represents a fat binary object,
- * which is a collection of different \e cubin and/or \e PTX files, all
- * representing the same device code, but compiled and optimized for different
- * architectures.
- *
- * Prior to CUDA 4.0, there was no documented API for constructing and using
- * fat binary objects by programmers. Starting with CUDA 4.0, fat binary
- * objects can be constructed by providing the -fatbin option to \b nvcc.
- * More information can be found in the \b nvcc document.
- *
- * \param module - Returned module
- * \param fatCubin - Fat binary to load
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_PTX,
- * ::CUDA_ERROR_NOT_FOUND,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_NO_BINARY_FOR_GPU,
- * ::CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleLoadFatBinary(CUmodule *module, const void *fatCubin);
-
-/**
- * \brief Unloads a module
- *
- * Unloads a module \p hmod from the current context.
- *
- * \param hmod - Module to unload
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary
- */
-CUresult CUDAAPI cuModuleUnload(CUmodule hmod);
-
-/**
- * \brief Returns a function handle
- *
- * Returns in \p *hfunc the handle of the function of name \p name located in
- * module \p hmod. If no function of that name exists, ::cuModuleGetFunction()
- * returns ::CUDA_ERROR_NOT_FOUND.
- *
- * \param hfunc - Returned function handle
- * \param hmod - Module to retrieve function from
- * \param name - Name of function to retrieve
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_NOT_FOUND
- * \notefnerr
- *
- * \sa ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleGetFunction(CUfunction *hfunc, CUmodule hmod, const char *name);
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Returns a global pointer from a module
- *
- * Returns in \p *dptr and \p *bytes the base pointer and size of the
- * global of name \p name located in module \p hmod. If no variable of that name
- * exists, ::cuModuleGetGlobal() returns ::CUDA_ERROR_NOT_FOUND. Both
- * parameters \p dptr and \p bytes are optional. If one of them is
- * NULL, it is ignored.
- *
- * \param dptr - Returned global device pointer
- * \param bytes - Returned global size in bytes
- * \param hmod - Module to retrieve global from
- * \param name - Name of global to retrieve
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_NOT_FOUND
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleGetGlobal(CUdeviceptr *dptr, size_t *bytes, CUmodule hmod, const char *name);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Returns a handle to a texture reference
- *
- * Returns in \p *pTexRef the handle of the texture reference of name \p name
- * in the module \p hmod. If no texture reference of that name exists,
- * ::cuModuleGetTexRef() returns ::CUDA_ERROR_NOT_FOUND. This texture reference
- * handle should not be destroyed, since it will be destroyed when the module
- * is unloaded.
- *
- * \param pTexRef - Returned texture reference
- * \param hmod - Module to retrieve texture reference from
- * \param name - Name of texture reference to retrieve
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_NOT_FOUND
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetSurfRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleGetTexRef(CUtexref *pTexRef, CUmodule hmod, const char *name);
-
-/**
- * \brief Returns a handle to a surface reference
- *
- * Returns in \p *pSurfRef the handle of the surface reference of name \p name
- * in the module \p hmod. If no surface reference of that name exists,
- * ::cuModuleGetSurfRef() returns ::CUDA_ERROR_NOT_FOUND.
- *
- * \param pSurfRef - Returned surface reference
- * \param hmod - Module to retrieve surface reference from
- * \param name - Name of surface reference to retrieve
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_NOT_FOUND
- * \notefnerr
- *
- * \sa ::cuModuleGetFunction,
- * ::cuModuleGetGlobal,
- * ::cuModuleGetTexRef,
- * ::cuModuleLoad,
- * ::cuModuleLoadData,
- * ::cuModuleLoadDataEx,
- * ::cuModuleLoadFatBinary,
- * ::cuModuleUnload
- */
-CUresult CUDAAPI cuModuleGetSurfRef(CUsurfref *pSurfRef, CUmodule hmod, const char *name);
-
-#if __CUDA_API_VERSION >= 5050
-
-/**
- * \brief Creates a pending JIT linker invocation.
- *
- * If the call is successful, the caller owns the returned CUlinkState, which
- * should eventually be destroyed with ::cuLinkDestroy. The
- * device code machine size (32 or 64 bit) will match the calling application.
- *
- * Both linker and compiler options may be specified. Compiler options will
- * be applied to inputs to this linker action which must be compiled from PTX.
- * The options ::CU_JIT_WALL_TIME,
- * ::CU_JIT_INFO_LOG_BUFFER_SIZE_BYTES, and ::CU_JIT_ERROR_LOG_BUFFER_SIZE_BYTES
- * will accumulate data until the CUlinkState is destroyed.
- *
- * \p optionValues must remain valid for the life of the CUlinkState if output
- * options are used. No other references to inputs are maintained after this
- * call returns.
- *
- * \param numOptions Size of options arrays
- * \param options Array of linker and compiler options
- * \param optionValues Array of option values, each cast to void *
- * \param stateOut On success, this will contain a CUlinkState to specify
- * and complete this action
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuLinkAddData,
- * ::cuLinkAddFile,
- * ::cuLinkComplete,
- * ::cuLinkDestroy
- */
-CUresult CUDAAPI
-cuLinkCreate(unsigned int numOptions, CUjit_option *options, void **optionValues, CUlinkState *stateOut);
-
-/**
- * \brief Add an input to a pending linker invocation
- *
- * Ownership of \p data is retained by the caller. No reference is retained to any
- * inputs after this call returns.
- *
- * This method accepts only compiler options, which are used if the data must
- * be compiled from PTX, and does not accept any of
- * ::CU_JIT_WALL_TIME, ::CU_JIT_INFO_LOG_BUFFER, ::CU_JIT_ERROR_LOG_BUFFER,
- * ::CU_JIT_TARGET_FROM_CUCONTEXT, or ::CU_JIT_TARGET.
- *
- * \param state A pending linker action.
- * \param type The type of the input data.
- * \param data The input data. PTX must be NULL-terminated.
- * \param size The length of the input data.
- * \param name An optional name for this input in log messages.
- * \param numOptions Size of options.
- * \param options Options to be applied only for this input (overrides options from ::cuLinkCreate).
- * \param optionValues Array of option values, each cast to void *.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_IMAGE,
- * ::CUDA_ERROR_INVALID_PTX,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_NO_BINARY_FOR_GPU
- *
- * \sa ::cuLinkCreate,
- * ::cuLinkAddFile,
- * ::cuLinkComplete,
- * ::cuLinkDestroy
- */
-CUresult CUDAAPI
-cuLinkAddData(CUlinkState state, CUjitInputType type, void *data, size_t size, const char *name,
- unsigned int numOptions, CUjit_option *options, void **optionValues);
-
-/**
- * \brief Add a file input to a pending linker invocation
- *
- * No reference is retained to any inputs after this call returns.
- *
- * This method accepts only compiler options, which are used if the input
- * must be compiled from PTX, and does not accept any of
- * ::CU_JIT_WALL_TIME, ::CU_JIT_INFO_LOG_BUFFER, ::CU_JIT_ERROR_LOG_BUFFER,
- * ::CU_JIT_TARGET_FROM_CUCONTEXT, or ::CU_JIT_TARGET.
- *
- * This method is equivalent to invoking ::cuLinkAddData on the contents
- * of the file.
- *
- * \param state A pending linker action
- * \param type The type of the input data
- * \param path Path to the input file
- * \param numOptions Size of options
- * \param options Options to be applied only for this input (overrides options from ::cuLinkCreate)
- * \param optionValues Array of option values, each cast to void *
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_FILE_NOT_FOUND
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_IMAGE,
- * ::CUDA_ERROR_INVALID_PTX,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_NO_BINARY_FOR_GPU
- *
- * \sa ::cuLinkCreate,
- * ::cuLinkAddData,
- * ::cuLinkComplete,
- * ::cuLinkDestroy
- */
-CUresult CUDAAPI
-cuLinkAddFile(CUlinkState state, CUjitInputType type, const char *path,
- unsigned int numOptions, CUjit_option *options, void **optionValues);
-
-/**
- * \brief Complete a pending linker invocation
- *
- * Completes the pending linker action and returns the cubin image for the linked
- * device code, which can be used with ::cuModuleLoadData. The cubin is owned by
- * \p state, so it should be loaded before \p state is destroyed via ::cuLinkDestroy.
- * This call does not destroy \p state.
- *
- * \param state A pending linker invocation
- * \param cubinOut On success, this will point to the output image
- * \param sizeOut Optional parameter to receive the size of the generated image
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- *
- * \sa ::cuLinkCreate,
- * ::cuLinkAddData,
- * ::cuLinkAddFile,
- * ::cuLinkDestroy,
- * ::cuModuleLoadData
- */
-CUresult CUDAAPI
-cuLinkComplete(CUlinkState state, void **cubinOut, size_t *sizeOut);
-
-/**
- * \brief Destroys state for a JIT linker invocation.
- *
- * \param state State object for the linker invocation
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_HANDLE
- *
- * \sa ::cuLinkCreate
- */
-CUresult CUDAAPI
-cuLinkDestroy(CUlinkState state);
-
-#endif /* __CUDA_API_VERSION >= 5050 */
-
-/** @} */ /* END CUDA_MODULE */
-
-
-/**
- * \defgroup CUDA_MEM Memory Management
- *
- * ___MANBRIEF___ memory management functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the memory management functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Gets free and total memory
- *
- * Returns in \p *free and \p *total respectively, the free and total amount of
- * memory available for allocation by the CUDA context, in bytes.
- *
- * \param free - Returned free memory in bytes
- * \param total - Returned total memory in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemGetInfo(size_t *free, size_t *total);
-
-/**
- * \brief Allocates device memory
- *
- * Allocates \p bytesize bytes of linear memory on the device and returns in
- * \p *dptr a pointer to the allocated memory. The allocated memory is suitably
- * aligned for any kind of variable. The memory is not cleared. If \p bytesize
- * is 0, ::cuMemAlloc() returns ::CUDA_ERROR_INVALID_VALUE.
- *
- * \param dptr - Returned device pointer
- * \param bytesize - Requested allocation size in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemAlloc(CUdeviceptr *dptr, size_t bytesize);
-
-/**
- * \brief Allocates pitched device memory
- *
- * Allocates at least \p WidthInBytes * \p Height bytes of linear memory on
- * the device and returns in \p *dptr a pointer to the allocated memory. The
- * function may pad the allocation to ensure that corresponding pointers in
- * any given row will continue to meet the alignment requirements for
- * coalescing as the address is updated from row to row. \p ElementSizeBytes
- * specifies the size of the largest reads and writes that will be performed
- * on the memory range. \p ElementSizeBytes may be 4, 8 or 16 (since coalesced
- * memory transactions are not possible on other data sizes). If
- * \p ElementSizeBytes is smaller than the actual read/write size of a kernel,
- * the kernel will run correctly, but possibly at reduced speed. The pitch
- * returned in \p *pPitch by ::cuMemAllocPitch() is the width in bytes of the
- * allocation. The intended usage of pitch is as a separate parameter of the
- * allocation, used to compute addresses within the 2D array. Given the row
- * and column of an array element of type \b T, the address is computed as:
- * \code
- T* pElement = (T*)((char*)BaseAddress + Row * Pitch) + Column;
- * \endcode
- *
- * The pitch returned by ::cuMemAllocPitch() is guaranteed to work with
- * ::cuMemcpy2D() under all circumstances. For allocations of 2D arrays, it is
- * recommended that programmers consider performing pitch allocations using
- * ::cuMemAllocPitch(). Due to alignment restrictions in the hardware, this is
- * especially true if the application will be performing 2D memory copies
- * between different regions of device memory (whether linear memory or CUDA
- * arrays).
- *
- * The byte alignment of the pitch returned by ::cuMemAllocPitch() is guaranteed
- * to match or exceed the alignment requirement for texture binding with
- * ::cuTexRefSetAddress2D().
- *
- * \param dptr - Returned device pointer
- * \param pPitch - Returned pitch of allocation in bytes
- * \param WidthInBytes - Requested allocation width in bytes
- * \param Height - Requested allocation height in rows
- * \param ElementSizeBytes - Size of largest reads/writes for range
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemAllocPitch(CUdeviceptr *dptr, size_t *pPitch, size_t WidthInBytes, size_t Height, unsigned int ElementSizeBytes);
-
-/**
- * \brief Frees device memory
- *
- * Frees the memory space pointed to by \p dptr, which must have been returned
- * by a previous call to ::cuMemAlloc() or ::cuMemAllocPitch().
- *
- * \param dptr - Pointer to memory to free
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemFree(CUdeviceptr dptr);
-
-/**
- * \brief Get information on memory allocations
- *
- * Returns the base address in \p *pbase and size in \p *psize of the
- * allocation by ::cuMemAlloc() or ::cuMemAllocPitch() that contains the input
- * pointer \p dptr. Both parameters \p pbase and \p psize are optional. If one
- * of them is NULL, it is ignored.
- *
- * \param pbase - Returned base address
- * \param psize - Returned size of device memory allocation
- * \param dptr - Device pointer to query
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemGetAddressRange(CUdeviceptr *pbase, size_t *psize, CUdeviceptr dptr);
-
-/**
- * \brief Allocates page-locked host memory
- *
- * Allocates \p bytesize bytes of host memory that is page-locked and
- * accessible to the device. The driver tracks the virtual memory ranges
- * allocated with this function and automatically accelerates calls to
- * functions such as ::cuMemcpy(). Since the memory can be accessed directly by
- * the device, it can be read or written with much higher bandwidth than
- * pageable memory obtained with functions such as ::malloc(). Allocating
- * excessive amounts of memory with ::cuMemAllocHost() may degrade system
- * performance, since it reduces the amount of memory available to the system
- * for paging. As a result, this function is best used sparingly to allocate
- * staging areas for data exchange between host and device.
- *
- * Note all host memory allocated using ::cuMemHostAlloc() will automatically
- * be immediately accessible to all contexts on all devices which support unified
- * addressing (as may be queried using ::CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING).
- * The device pointer that may be used to access this host memory from those 
- * contexts is always equal to the returned host pointer \p *pp.
- * See \ref CUDA_UNIFIED for additional details.
- *
- * \param pp - Returned host pointer to page-locked memory
- * \param bytesize - Requested allocation size in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemAllocHost(void **pp, size_t bytesize);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Frees page-locked host memory
- *
- * Frees the memory space pointed to by \p p, which must have been returned by
- * a previous call to ::cuMemAllocHost().
- *
- * \param p - Pointer to memory to free
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemFreeHost(void *p);
-
-/**
- * \brief Allocates page-locked host memory
- *
- * Allocates \p bytesize bytes of host memory that is page-locked and accessible
- * to the device. The driver tracks the virtual memory ranges allocated with
- * this function and automatically accelerates calls to functions such as
- * ::cuMemcpyHtoD(). Since the memory can be accessed directly by the device,
- * it can be read or written with much higher bandwidth than pageable memory
- * obtained with functions such as ::malloc(). Allocating excessive amounts of
- * pinned memory may degrade system performance, since it reduces the amount
- * of memory available to the system for paging. As a result, this function is
- * best used sparingly to allocate staging areas for data exchange between
- * host and device.
- *
- * The \p Flags parameter enables different options to be specified that
- * affect the allocation, as follows.
- *
- * - ::CU_MEMHOSTALLOC_PORTABLE: The memory returned by this call will be
- * considered as pinned memory by all CUDA contexts, not just the one that
- * performed the allocation.
- *
- * - ::CU_MEMHOSTALLOC_DEVICEMAP: Maps the allocation into the CUDA address
- * space. The device pointer to the memory may be obtained by calling
- * ::cuMemHostGetDevicePointer(). This feature is available only on GPUs
- * with compute capability greater than or equal to 1.1.
- *
- * - ::CU_MEMHOSTALLOC_WRITECOMBINED: Allocates the memory as write-combined
- * (WC). WC memory can be transferred across the PCI Express bus more
- * quickly on some system configurations, but cannot be read efficiently by
- * most CPUs. WC memory is a good option for buffers that will be written by
- * the CPU and read by the GPU via mapped pinned memory or host->device
- * transfers.
- *
- * All of these flags are orthogonal to one another: a developer may allocate
- * memory that is portable, mapped and/or write-combined with no restrictions.
- *
- * The CUDA context must have been created with the ::CU_CTX_MAP_HOST flag in
- * order for the ::CU_MEMHOSTALLOC_DEVICEMAP flag to have any effect.
- *
- * The ::CU_MEMHOSTALLOC_DEVICEMAP flag may be specified on CUDA contexts for
- * devices that do not support mapped pinned memory. The failure is deferred
- * to ::cuMemHostGetDevicePointer() because the memory may be mapped into
- * other CUDA contexts via the ::CU_MEMHOSTALLOC_PORTABLE flag.
- *
- * The memory allocated by this function must be freed with ::cuMemFreeHost().
- *
- * Note all host memory allocated using ::cuMemHostAlloc() will automatically
- * be immediately accessible to all contexts on all devices which support unified
- * addressing (as may be queried using ::CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING).
- * Unless the flag ::CU_MEMHOSTALLOC_WRITECOMBINED is specified, the device pointer 
- * that may be used to access this host memory from those contexts is always equal 
- * to the returned host pointer \p *pp. If the flag ::CU_MEMHOSTALLOC_WRITECOMBINED
- * is specified, then the function ::cuMemHostGetDevicePointer() must be used
- * to query the device pointer, even if the context supports unified addressing.
- * See \ref CUDA_UNIFIED for additional details.
- *
- * \param pp - Returned host pointer to page-locked memory
- * \param bytesize - Requested allocation size in bytes
- * \param Flags - Flags for allocation request
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemHostAlloc(void **pp, size_t bytesize, unsigned int Flags);
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Passes back device pointer of mapped pinned memory
- *
- * Passes back the device pointer \p pdptr corresponding to the mapped, pinned
- * host buffer \p p allocated by ::cuMemHostAlloc.
- *
- * ::cuMemHostGetDevicePointer() will fail if the ::CU_MEMHOSTALLOC_DEVICEMAP
- * flag was not specified at the time the memory was allocated, or if the
- * function is called on a GPU that does not support mapped pinned memory.
- *
- * \p Flags provides for future releases. For now, it must be set to 0.
- *
- * \param pdptr - Returned device pointer
- * \param p - Host pointer
- * \param Flags - Options (must be 0)
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemHostGetDevicePointer(CUdeviceptr *pdptr, void *p, unsigned int Flags);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Passes back flags that were used for a pinned allocation
- *
- * Passes back the flags \p pFlags that were specified when allocating
- * the pinned host buffer \p p allocated by ::cuMemHostAlloc.
- *
- * ::cuMemHostGetFlags() will fail if the pointer does not reside in
- * an allocation performed by ::cuMemAllocHost() or ::cuMemHostAlloc().
- *
- * \param pFlags - Returned flags word
- * \param p - Host pointer
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuMemAllocHost, ::cuMemHostAlloc
- */
-CUresult CUDAAPI cuMemHostGetFlags(unsigned int *pFlags, void *p);
-
-#if __CUDA_API_VERSION >= 6000
-
-/**
- * \brief Allocates memory that will be automatically managed by the Unified Memory system
- *
- * Allocates \p bytesize bytes of managed memory on the device and returns in
- * \p *dptr a pointer to the allocated memory. If the device doesn't support
- * allocating managed memory, ::CUDA_ERROR_NOT_SUPPORTED is returned. Support
- * for managed memory can be queried using the device attribute
- * ::CU_DEVICE_ATTRIBUTE_MANAGED_MEMORY. The allocated memory is suitably
- * aligned for any kind of variable. The memory is not cleared. If \p bytesize
- * is 0, ::cuMemAllocManaged returns ::CUDA_ERROR_INVALID_VALUE. The pointer
- * is valid on the CPU and on all GPUs in the system that support managed memory.
- * All accesses to this pointer must obey the Unified Memory programming model.
- *
- * \p flags specifies the default stream association for this allocation.
- * \p flags must be one of ::CU_MEM_ATTACH_GLOBAL or ::CU_MEM_ATTACH_HOST. If
- * ::CU_MEM_ATTACH_GLOBAL is specified, then this memory is accessible from
- * any stream on any device. If ::CU_MEM_ATTACH_HOST is specified, then the
- * allocation is created with initial visibility restricted to host access only;
- * an explicit call to ::cuStreamAttachMemAsync will be required to enable access
- * on the device.
- *
- * If the association is later changed via ::cuStreamAttachMemAsync to
- * a single stream, the default association as specifed during ::cuMemAllocManaged
- * is restored when that stream is destroyed. For __managed__ variables, the
- * default association is always ::CU_MEM_ATTACH_GLOBAL. Note that destroying a
- * stream is an asynchronous operation, and as a result, the change to default
- * association won't happen until all work in the stream has completed.
- *
- * Memory allocated with ::cuMemAllocManaged should be released with ::cuMemFree.
- *
- * On a multi-GPU system with peer-to-peer support, where multiple GPUs support
- * managed memory, the physical storage is created on the GPU which is active
- * at the time ::cuMemAllocManaged is called. All other GPUs will reference the
- * data at reduced bandwidth via peer mappings over the PCIe bus. The Unified
- * Memory management system does not migrate memory between GPUs.
- *
- * On a multi-GPU system where multiple GPUs support managed memory, but not
- * all pairs of such GPUs have peer-to-peer support between them, the physical
- * storage is created in 'zero-copy' or system memory. All GPUs will reference
- * the data at reduced bandwidth over the PCIe bus. In these circumstances,
- * use of the environment variable, CUDA_VISIBLE_DEVICES, is recommended to
- * restrict CUDA to only use those GPUs that have peer-to-peer support.
- * Alternatively, users can also set CUDA_MANAGED_FORCE_DEVICE_ALLOC to a
- * non-zero value to force the driver to always use device memory for physical storage.
- * When this environment variable is set to a non-zero value, all contexts created in
- * that process on devices that support managed memory have to be peer-to-peer compatible
- * with each other. Context creation will fail if a context is created on a device that
- * supports managed memory and is not peer-to-peer compatible with any of the other
- * managed memory supporting devices on which contexts were previously created, even if
- * those contexts have been destroyed. These environment variables are described
- * in the CUDA programming guide under the "CUDA environment variables" section.
- *
- * \param dptr - Returned device pointer
- * \param bytesize - Requested allocation size in bytes
- * \param flags - Must be one of ::CU_MEM_ATTACH_GLOBAL or ::CU_MEM_ATTACH_HOST
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_NOT_SUPPORTED,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32,
- * ::cuDeviceGetAttribute, ::cuStreamAttachMemAsync
- */
-CUresult CUDAAPI cuMemAllocManaged(CUdeviceptr *dptr, size_t bytesize, unsigned int flags);
-
-#endif /* __CUDA_API_VERSION >= 6000 */
-
-#if __CUDA_API_VERSION >= 4010
-
-/**
- * \brief Returns a handle to a compute device
- *
- * Returns in \p *device a device handle given a PCI bus ID string.
- *
- * \param dev - Returned device handle
- *
- * \param pciBusId - String in one of the following forms: 
- * [domain]:[bus]:[device].[function]
- * [domain]:[bus]:[device]
- * [bus]:[device].[function]
- * where \p domain, \p bus, \p device, and \p function are all hexadecimal values
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa ::cuDeviceGet, ::cuDeviceGetAttribute, ::cuDeviceGetPCIBusId
- */
-CUresult CUDAAPI cuDeviceGetByPCIBusId(CUdevice *dev, const char *pciBusId);
-
-/**
- * \brief Returns a PCI Bus Id string for the device
- *
- * Returns an ASCII string identifying the device \p dev in the NULL-terminated
- * string pointed to by \p pciBusId. \p len specifies the maximum length of the
- * string that may be returned.
- *
- * \param pciBusId - Returned identifier string for the device in the following format
- * [domain]:[bus]:[device].[function]
- * where \p domain, \p bus, \p device, and \p function are all hexadecimal values.
- * pciBusId should be large enough to store 13 characters including the NULL-terminator.
- *
- * \param len - Maximum length of string to store in \p name
- *
- * \param dev - Device to get identifier string for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa ::cuDeviceGet, ::cuDeviceGetAttribute, ::cuDeviceGetByPCIBusId
- */
-CUresult CUDAAPI cuDeviceGetPCIBusId(char *pciBusId, int len, CUdevice dev);
-
-/**
- * \brief Gets an interprocess handle for a previously allocated event
- *
- * Takes as input a previously allocated event. This event must have been 
- * created with the ::CU_EVENT_INTERPROCESS and ::CU_EVENT_DISABLE_TIMING 
- * flags set. This opaque handle may be copied into other processes and
- * opened with ::cuIpcOpenEventHandle to allow efficient hardware
- * synchronization between GPU work in different processes.
- *
- * After the event has been opened in the importing process, 
- * ::cuEventRecord, ::cuEventSynchronize, ::cuStreamWaitEvent and 
- * ::cuEventQuery may be used in either process. Performing operations 
- * on the imported event after the exported event has been freed 
- * with ::cuEventDestroy will result in undefined behavior.
- *
- * IPC functionality is restricted to devices with support for unified 
- * addressing on Linux operating systems.
- *
- * \param pHandle - Pointer to a user allocated CUipcEventHandle
- * in which to return the opaque event handle
- * \param event - Event allocated with ::CU_EVENT_INTERPROCESS and 
- * ::CU_EVENT_DISABLE_TIMING flags.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_MAP_FAILED
- *
- * \sa 
- * ::cuEventCreate, 
- * ::cuEventDestroy, 
- * ::cuEventSynchronize,
- * ::cuEventQuery,
- * ::cuStreamWaitEvent,
- * ::cuIpcOpenEventHandle,
- * ::cuIpcGetMemHandle,
- * ::cuIpcOpenMemHandle,
- * ::cuIpcCloseMemHandle
- */
-CUresult CUDAAPI cuIpcGetEventHandle(CUipcEventHandle *pHandle, CUevent event);
-
-/**
- * \brief Opens an interprocess event handle for use in the current process
- *
- * Opens an interprocess event handle exported from another process with 
- * ::cuIpcGetEventHandle. This function returns a ::CUevent that behaves like 
- * a locally created event with the ::CU_EVENT_DISABLE_TIMING flag specified. 
- * This event must be freed with ::cuEventDestroy.
- *
- * Performing operations on the imported event after the exported event has 
- * been freed with ::cuEventDestroy will result in undefined behavior.
- *
- * IPC functionality is restricted to devices with support for unified 
- * addressing on Linux operating systems.
- *
- * \param phEvent - Returns the imported event
- * \param handle - Interprocess handle to open
- *
- * \returns
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_MAP_FAILED,
- * ::CUDA_ERROR_PEER_ACCESS_UNSUPPORTED,
- * ::CUDA_ERROR_INVALID_HANDLE
- *
- * \sa
- * ::cuEventCreate, 
- * ::cuEventDestroy, 
- * ::cuEventSynchronize,
- * ::cuEventQuery,
- * ::cuStreamWaitEvent,
- * ::cuIpcGetEventHandle,
- * ::cuIpcGetMemHandle,
- * ::cuIpcOpenMemHandle,
- * ::cuIpcCloseMemHandle
- */
-CUresult CUDAAPI cuIpcOpenEventHandle(CUevent *phEvent, CUipcEventHandle handle);
-
-/**
- * \brief Gets an interprocess memory handle for an existing device memory
- * allocation
- *
- * Takes a pointer to the base of an existing device memory allocation created 
- * with ::cuMemAlloc and exports it for use in another process. This is a 
- * lightweight operation and may be called multiple times on an allocation
- * without adverse effects. 
- *
- * If a region of memory is freed with ::cuMemFree and a subsequent call
- * to ::cuMemAlloc returns memory with the same device address,
- * ::cuIpcGetMemHandle will return a unique handle for the
- * new memory. 
- *
- * IPC functionality is restricted to devices with support for unified 
- * addressing on Linux operating systems.
- *
- * \param pHandle - Pointer to user allocated ::CUipcMemHandle to return
- * the handle in.
- * \param dptr - Base pointer to previously allocated device memory 
- *
- * \returns
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_MAP_FAILED,
- * 
- * \sa
- * ::cuMemAlloc,
- * ::cuMemFree,
- * ::cuIpcGetEventHandle,
- * ::cuIpcOpenEventHandle,
- * ::cuIpcOpenMemHandle,
- * ::cuIpcCloseMemHandle
- */
-CUresult CUDAAPI cuIpcGetMemHandle(CUipcMemHandle *pHandle, CUdeviceptr dptr);
-
-/**
- * \brief Opens an interprocess memory handle exported from another process
- * and returns a device pointer usable in the local process.
- *
- * Maps memory exported from another process with ::cuIpcGetMemHandle into
- * the current device address space. For contexts on different devices 
- * ::cuIpcOpenMemHandle can attempt to enable peer access between the
- * devices as if the user called ::cuCtxEnablePeerAccess. This behavior is 
- * controlled by the ::CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS flag. 
- * ::cuDeviceCanAccessPeer can determine if a mapping is possible.
- *
- * Contexts that may open ::CUipcMemHandles are restricted in the following way.
- * ::CUipcMemHandles from each ::CUdevice in a given process may only be opened 
- * by one ::CUcontext per ::CUdevice per other process.
- *
- * Memory returned from ::cuIpcOpenMemHandle must be freed with
- * ::cuIpcCloseMemHandle.
- *
- * Calling ::cuMemFree on an exported memory region before calling
- * ::cuIpcCloseMemHandle in the importing context will result in undefined
- * behavior.
- *
- * IPC functionality is restricted to devices with support for unified 
- * addressing on Linux operating systems.
- * 
- * \param pdptr - Returned device pointer
- * \param handle - ::CUipcMemHandle to open
- * \param Flags - Flags for this operation. Must be specified as ::CU_IPC_MEM_LAZY_ENABLE_PEER_ACCESS
- *
- * \returns
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_MAP_FAILED,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_TOO_MANY_PEERS
- *
- * \note No guarantees are made about the address returned in \p *pdptr. 
- * In particular, multiple processes may not receive the same address for the same \p handle.
- *
- * \sa
- * ::cuMemAlloc,
- * ::cuMemFree,
- * ::cuIpcGetEventHandle,
- * ::cuIpcOpenEventHandle,
- * ::cuIpcGetMemHandle,
- * ::cuIpcCloseMemHandle,
- * ::cuCtxEnablePeerAccess,
- * ::cuDeviceCanAccessPeer,
- */
-CUresult CUDAAPI cuIpcOpenMemHandle(CUdeviceptr *pdptr, CUipcMemHandle handle, unsigned int Flags);
-
-/**
- * \brief Close memory mapped with ::cuIpcOpenMemHandle
- * 
- * Unmaps memory returnd by ::cuIpcOpenMemHandle. The original allocation
- * in the exporting process as well as imported mappings in other processes
- * will be unaffected.
- *
- * Any resources used to enable peer access will be freed if this is the
- * last mapping using them.
- *
- * IPC functionality is restricted to devices with support for unified 
- * addressing on Linux operating systems.
- *
- * \param dptr - Device pointer returned by ::cuIpcOpenMemHandle
- * 
- * \returns
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_MAP_FAILED,
- * ::CUDA_ERROR_INVALID_HANDLE,
- *
- * \sa
- * ::cuMemAlloc,
- * ::cuMemFree,
- * ::cuIpcGetEventHandle,
- * ::cuIpcOpenEventHandle,
- * ::cuIpcGetMemHandle,
- * ::cuIpcOpenMemHandle,
- */
-CUresult CUDAAPI cuIpcCloseMemHandle(CUdeviceptr dptr);
-
-#endif /* __CUDA_API_VERSION >= 4010 */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Registers an existing host memory range for use by CUDA
- *
- * Page-locks the memory range specified by \p p and \p bytesize and maps it
- * for the device(s) as specified by \p Flags. This memory range also is added
- * to the same tracking mechanism as ::cuMemHostAlloc to automatically accelerate
- * calls to functions such as ::cuMemcpyHtoD(). Since the memory can be accessed 
- * directly by the device, it can be read or written with much higher bandwidth 
- * than pageable memory that has not been registered. Page-locking excessive
- * amounts of memory may degrade system performance, since it reduces the amount
- * of memory available to the system for paging. As a result, this function is
- * best used sparingly to register staging areas for data exchange between
- * host and device.
- *
- * This function has limited support on Mac OS X. OS 10.7 or higher is required.
- *
- * The \p Flags parameter enables different options to be specified that
- * affect the allocation, as follows.
- *
- * - ::CU_MEMHOSTREGISTER_PORTABLE: The memory returned by this call will be
- * considered as pinned memory by all CUDA contexts, not just the one that
- * performed the allocation.
- *
- * - ::CU_MEMHOSTREGISTER_DEVICEMAP: Maps the allocation into the CUDA address
- * space. The device pointer to the memory may be obtained by calling
- * ::cuMemHostGetDevicePointer(). This feature is available only on GPUs
- * with compute capability greater than or equal to 1.1.
- *
- * - ::CU_MEMHOSTREGISTER_IOMEMORY: The pointer is treated as pointing to some
- * I/O memory space, e.g. the PCI Express resource of a 3rd party device.
- *
- * All of these flags are orthogonal to one another: a developer may page-lock
- * memory that is portable or mapped with no restrictions.
- *
- * The CUDA context must have been created with the ::CU_CTX_MAP_HOST flag in
- * order for the ::CU_MEMHOSTREGISTER_DEVICEMAP flag to have any effect.
- *
- * The ::CU_MEMHOSTREGISTER_DEVICEMAP flag may be specified on CUDA contexts for
- * devices that do not support mapped pinned memory. The failure is deferred
- * to ::cuMemHostGetDevicePointer() because the memory may be mapped into
- * other CUDA contexts via the ::CU_MEMHOSTREGISTER_PORTABLE flag.
- *
- * The memory page-locked by this function must be unregistered with 
- * ::cuMemHostUnregister().
- *
- * \param p - Host pointer to memory to page-lock
- * \param bytesize - Size in bytes of the address range to page-lock
- * \param Flags - Flags for allocation request
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED,
- * ::CUDA_ERROR_NOT_PERMITTED,
- * ::CUDA_ERROR_NOT_SUPPORTED
- * \notefnerr
- *
- * \sa ::cuMemHostUnregister, ::cuMemHostGetFlags, ::cuMemHostGetDevicePointer
- */
-CUresult CUDAAPI cuMemHostRegister(void *p, size_t bytesize, unsigned int Flags);
-
-/**
- * \brief Unregisters a memory range that was registered with cuMemHostRegister.
- *
- * Unmaps the memory range whose base address is specified by \p p, and makes
- * it pageable again.
- *
- * The base address must be the same one specified to ::cuMemHostRegister().
- *
- * \param p - Host pointer to memory to unregister
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED,
- * \notefnerr
- *
- * \sa ::cuMemHostRegister
- */
-CUresult CUDAAPI cuMemHostUnregister(void *p);
-
-/**
- * \brief Copies memory
- *
- * Copies data between two pointers. 
- * \p dst and \p src are base pointers of the destination and source, respectively. 
- * \p ByteCount specifies the number of bytes to copy.
- * Note that this function infers the type of the transfer (host to host, host to 
- * device, device to device, or device to host) from the pointer values. This
- * function is only allowed in contexts which support unified addressing.
- *
- * \param dst - Destination unified virtual address space pointer
- * \param src - Source unified virtual address space pointer
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpy(CUdeviceptr dst, CUdeviceptr src, size_t ByteCount);
-
-/**
- * \brief Copies device memory between two contexts
- *
- * Copies from device memory in one context to device memory in another
- * context. \p dstDevice is the base device pointer of the destination memory 
- * and \p dstContext is the destination context. \p srcDevice is the base 
- * device pointer of the source memory and \p srcContext is the source pointer. 
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstDevice - Destination device pointer
- * \param dstContext - Destination context
- * \param srcDevice - Source device pointer
- * \param srcContext - Source context
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuMemcpyDtoD, ::cuMemcpy3DPeer, ::cuMemcpyDtoDAsync, ::cuMemcpyPeerAsync,
- * ::cuMemcpy3DPeerAsync
- */
-CUresult CUDAAPI cuMemcpyPeer(CUdeviceptr dstDevice, CUcontext dstContext, CUdeviceptr srcDevice, CUcontext srcContext, size_t ByteCount);
-
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Copies memory from Host to Device
- *
- * Copies from host memory to device memory. \p dstDevice and \p srcHost are
- * the base addresses of the destination and source, respectively. \p ByteCount
- * specifies the number of bytes to copy.
- *
- * \param dstDevice - Destination device pointer
- * \param srcHost - Source host pointer
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyHtoD(CUdeviceptr dstDevice, const void *srcHost, size_t ByteCount);
-
-/**
- * \brief Copies memory from Device to Host
- *
- * Copies from device to host memory. \p dstHost and \p srcDevice specify the
- * base pointers of the destination and source, respectively. \p ByteCount
- * specifies the number of bytes to copy.
- *
- * \param dstHost - Destination host pointer
- * \param srcDevice - Source device pointer
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyDtoH(void *dstHost, CUdeviceptr srcDevice, size_t ByteCount);
-
-/**
- * \brief Copies memory from Device to Device
- *
- * Copies from device memory to device memory. \p dstDevice and \p srcDevice
- * are the base pointers of the destination and source, respectively.
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstDevice - Destination device pointer
- * \param srcDevice - Source device pointer
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyDtoD(CUdeviceptr dstDevice, CUdeviceptr srcDevice, size_t ByteCount);
-
-/**
- * \brief Copies memory from Device to Array
- *
- * Copies from device memory to a 1D CUDA array. \p dstArray and \p dstOffset
- * specify the CUDA array handle and starting index of the destination data.
- * \p srcDevice specifies the base pointer of the source. \p ByteCount
- * specifies the number of bytes to copy.
- *
- * \param dstArray - Destination array
- * \param dstOffset - Offset in bytes of destination array
- * \param srcDevice - Source device pointer
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyDtoA(CUarray dstArray, size_t dstOffset, CUdeviceptr srcDevice, size_t ByteCount);
-
-/**
- * \brief Copies memory from Array to Device
- *
- * Copies from one 1D CUDA array to device memory. \p dstDevice specifies the
- * base pointer of the destination and must be naturally aligned with the CUDA
- * array elements. \p srcArray and \p srcOffset specify the CUDA array handle
- * and the offset in bytes into the array where the copy is to begin.
- * \p ByteCount specifies the number of bytes to copy and must be evenly
- * divisible by the array element size.
- *
- * \param dstDevice - Destination device pointer
- * \param srcArray - Source array
- * \param srcOffset - Offset in bytes of source array
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyAtoD(CUdeviceptr dstDevice, CUarray srcArray, size_t srcOffset, size_t ByteCount);
-
-/**
- * \brief Copies memory from Host to Array
- *
- * Copies from host memory to a 1D CUDA array. \p dstArray and \p dstOffset
- * specify the CUDA array handle and starting offset in bytes of the destination
- * data. \p pSrc specifies the base address of the source. \p ByteCount specifies
- * the number of bytes to copy.
- *
- * \param dstArray - Destination array
- * \param dstOffset - Offset in bytes of destination array
- * \param srcHost - Source host pointer
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyHtoA(CUarray dstArray, size_t dstOffset, const void *srcHost, size_t ByteCount);
-
-/**
- * \brief Copies memory from Array to Host
- *
- * Copies from one 1D CUDA array to host memory. \p dstHost specifies the base
- * pointer of the destination. \p srcArray and \p srcOffset specify the CUDA
- * array handle and starting offset in bytes of the source data.
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstHost - Destination device pointer
- * \param srcArray - Source array
- * \param srcOffset - Offset in bytes of source array
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyAtoH(void *dstHost, CUarray srcArray, size_t srcOffset, size_t ByteCount);
-
-/**
- * \brief Copies memory from Array to Array
- *
- * Copies from one 1D CUDA array to another. \p dstArray and \p srcArray
- * specify the handles of the destination and source CUDA arrays for the copy,
- * respectively. \p dstOffset and \p srcOffset specify the destination and
- * source offsets in bytes into the CUDA arrays. \p ByteCount is the number of
- * bytes to be copied. The size of the elements in the CUDA arrays need not be
- * the same format, but the elements must be the same size; and count must be
- * evenly divisible by that size.
- *
- * \param dstArray - Destination array
- * \param dstOffset - Offset in bytes of destination array
- * \param srcArray - Source array
- * \param srcOffset - Offset in bytes of source array
- * \param ByteCount - Size of memory copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpyAtoA(CUarray dstArray, size_t dstOffset, CUarray srcArray, size_t srcOffset, size_t ByteCount);
-
-/**
- * \brief Copies memory for 2D arrays
- *
- * Perform a 2D memory copy according to the parameters specified in \p pCopy.
- * The ::CUDA_MEMCPY2D structure is defined as:
- *
- * \code
- typedef struct CUDA_MEMCPY2D_st {
- unsigned int srcXInBytes, srcY;
- CUmemorytype srcMemoryType;
- const void *srcHost;
- CUdeviceptr srcDevice;
- CUarray srcArray;
- unsigned int srcPitch;
-
- unsigned int dstXInBytes, dstY;
- CUmemorytype dstMemoryType;
- void *dstHost;
- CUdeviceptr dstDevice;
- CUarray dstArray;
- unsigned int dstPitch;
-
- unsigned int WidthInBytes;
- unsigned int Height;
- } CUDA_MEMCPY2D;
- * \endcode
- * where:
- * - ::srcMemoryType and ::dstMemoryType specify the type of memory of the
- * source and destination, respectively; ::CUmemorytype_enum is defined as:
- *
- * \code
- typedef enum CUmemorytype_enum {
- CU_MEMORYTYPE_HOST = 0x01,
- CU_MEMORYTYPE_DEVICE = 0x02,
- CU_MEMORYTYPE_ARRAY = 0x03,
- CU_MEMORYTYPE_UNIFIED = 0x04
- } CUmemorytype;
- * \endcode
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::srcDevice and ::srcPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::srcArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_HOST, ::srcHost and ::srcPitch
- * specify the (host) base address of the source data and the bytes per row to
- * apply. ::srcArray is ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_DEVICE, ::srcDevice and ::srcPitch
- * specify the (device) base address of the source data and the bytes per row
- * to apply. ::srcArray is ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_ARRAY, ::srcArray specifies the
- * handle of the source data. ::srcHost, ::srcDevice and ::srcPitch are
- * ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_HOST, ::dstHost and ::dstPitch
- * specify the (host) base address of the destination data and the bytes per
- * row to apply. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::dstDevice and ::dstPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::dstArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_DEVICE, ::dstDevice and ::dstPitch
- * specify the (device) base address of the destination data and the bytes per
- * row to apply. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_ARRAY, ::dstArray specifies the
- * handle of the destination data. ::dstHost, ::dstDevice and ::dstPitch are
- * ignored.
- *
- * - ::srcXInBytes and ::srcY specify the base address of the source data for
- * the copy.
- *
- * \par
- * For host pointers, the starting address is
- * \code
- void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::srcXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::dstXInBytes and ::dstY specify the base address of the destination data
- * for the copy.
- *
- * \par
- * For host pointers, the base address is
- * \code
- void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::dstXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::WidthInBytes and ::Height specify the width (in bytes) and height of
- * the 2D copy being performed.
- * - If specified, ::srcPitch must be greater than or equal to ::WidthInBytes +
- * ::srcXInBytes, and ::dstPitch must be greater than or equal to
- * ::WidthInBytes + dstXInBytes.
- *
- * \par
- * ::cuMemcpy2D() returns an error if any pitch is greater than the maximum
- * allowed (::CU_DEVICE_ATTRIBUTE_MAX_PITCH). ::cuMemAllocPitch() passes back
- * pitches that always work with ::cuMemcpy2D(). On intra-device memory copies
- * (device to device, CUDA array to device, CUDA array to CUDA array),
- * ::cuMemcpy2D() may fail for pitches not computed by ::cuMemAllocPitch().
- * ::cuMemcpy2DUnaligned() does not have this restriction, but may run
- * significantly slower in the cases where ::cuMemcpy2D() would have returned
- * an error code.
- *
- * \param pCopy - Parameters for the memory copy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpy2D(const CUDA_MEMCPY2D *pCopy);
-
-/**
- * \brief Copies memory for 2D arrays
- *
- * Perform a 2D memory copy according to the parameters specified in \p pCopy.
- * The ::CUDA_MEMCPY2D structure is defined as:
- *
- * \code
- typedef struct CUDA_MEMCPY2D_st {
- unsigned int srcXInBytes, srcY;
- CUmemorytype srcMemoryType;
- const void *srcHost;
- CUdeviceptr srcDevice;
- CUarray srcArray;
- unsigned int srcPitch;
- unsigned int dstXInBytes, dstY;
- CUmemorytype dstMemoryType;
- void *dstHost;
- CUdeviceptr dstDevice;
- CUarray dstArray;
- unsigned int dstPitch;
- unsigned int WidthInBytes;
- unsigned int Height;
- } CUDA_MEMCPY2D;
- * \endcode
- * where:
- * - ::srcMemoryType and ::dstMemoryType specify the type of memory of the
- * source and destination, respectively; ::CUmemorytype_enum is defined as:
- *
- * \code
- typedef enum CUmemorytype_enum {
- CU_MEMORYTYPE_HOST = 0x01,
- CU_MEMORYTYPE_DEVICE = 0x02,
- CU_MEMORYTYPE_ARRAY = 0x03,
- CU_MEMORYTYPE_UNIFIED = 0x04
- } CUmemorytype;
- * \endcode
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::srcDevice and ::srcPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::srcArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_HOST, ::srcHost and ::srcPitch
- * specify the (host) base address of the source data and the bytes per row to
- * apply. ::srcArray is ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_DEVICE, ::srcDevice and ::srcPitch
- * specify the (device) base address of the source data and the bytes per row
- * to apply. ::srcArray is ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_ARRAY, ::srcArray specifies the
- * handle of the source data. ::srcHost, ::srcDevice and ::srcPitch are
- * ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::dstDevice and ::dstPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::dstArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_HOST, ::dstHost and ::dstPitch
- * specify the (host) base address of the destination data and the bytes per
- * row to apply. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_DEVICE, ::dstDevice and ::dstPitch
- * specify the (device) base address of the destination data and the bytes per
- * row to apply. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_ARRAY, ::dstArray specifies the
- * handle of the destination data. ::dstHost, ::dstDevice and ::dstPitch are
- * ignored.
- *
- * - ::srcXInBytes and ::srcY specify the base address of the source data for
- * the copy.
- *
- * \par
- * For host pointers, the starting address is
- * \code
- void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::srcXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::dstXInBytes and ::dstY specify the base address of the destination data
- * for the copy.
- *
- * \par
- * For host pointers, the base address is
- * \code
- void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::dstXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::WidthInBytes and ::Height specify the width (in bytes) and height of
- * the 2D copy being performed.
- * - If specified, ::srcPitch must be greater than or equal to ::WidthInBytes +
- * ::srcXInBytes, and ::dstPitch must be greater than or equal to
- * ::WidthInBytes + dstXInBytes.
- *
- * \par
- * ::cuMemcpy2D() returns an error if any pitch is greater than the maximum
- * allowed (::CU_DEVICE_ATTRIBUTE_MAX_PITCH). ::cuMemAllocPitch() passes back
- * pitches that always work with ::cuMemcpy2D(). On intra-device memory copies
- * (device to device, CUDA array to device, CUDA array to CUDA array),
- * ::cuMemcpy2D() may fail for pitches not computed by ::cuMemAllocPitch().
- * ::cuMemcpy2DUnaligned() does not have this restriction, but may run
- * significantly slower in the cases where ::cuMemcpy2D() would have returned
- * an error code.
- *
- * \param pCopy - Parameters for the memory copy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpy2DUnaligned(const CUDA_MEMCPY2D *pCopy);
-
-/**
- * \brief Copies memory for 3D arrays
- *
- * Perform a 3D memory copy according to the parameters specified in
- * \p pCopy. The ::CUDA_MEMCPY3D structure is defined as:
- *
- * \code
- typedef struct CUDA_MEMCPY3D_st {
-
- unsigned int srcXInBytes, srcY, srcZ;
- unsigned int srcLOD;
- CUmemorytype srcMemoryType;
- const void *srcHost;
- CUdeviceptr srcDevice;
- CUarray srcArray;
- unsigned int srcPitch; // ignored when src is array
- unsigned int srcHeight; // ignored when src is array; may be 0 if Depth==1
-
- unsigned int dstXInBytes, dstY, dstZ;
- unsigned int dstLOD;
- CUmemorytype dstMemoryType;
- void *dstHost;
- CUdeviceptr dstDevice;
- CUarray dstArray;
- unsigned int dstPitch; // ignored when dst is array
- unsigned int dstHeight; // ignored when dst is array; may be 0 if Depth==1
-
- unsigned int WidthInBytes;
- unsigned int Height;
- unsigned int Depth;
- } CUDA_MEMCPY3D;
- * \endcode
- * where:
- * - ::srcMemoryType and ::dstMemoryType specify the type of memory of the
- * source and destination, respectively; ::CUmemorytype_enum is defined as:
- *
- * \code
- typedef enum CUmemorytype_enum {
- CU_MEMORYTYPE_HOST = 0x01,
- CU_MEMORYTYPE_DEVICE = 0x02,
- CU_MEMORYTYPE_ARRAY = 0x03,
- CU_MEMORYTYPE_UNIFIED = 0x04
- } CUmemorytype;
- * \endcode
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::srcDevice and ::srcPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::srcArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_HOST, ::srcHost, ::srcPitch and
- * ::srcHeight specify the (host) base address of the source data, the bytes
- * per row, and the height of each 2D slice of the 3D array. ::srcArray is
- * ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_DEVICE, ::srcDevice, ::srcPitch and
- * ::srcHeight specify the (device) base address of the source data, the bytes
- * per row, and the height of each 2D slice of the 3D array. ::srcArray is
- * ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_ARRAY, ::srcArray specifies the
- * handle of the source data. ::srcHost, ::srcDevice, ::srcPitch and
- * ::srcHeight are ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::dstDevice and ::dstPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::dstArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_HOST, ::dstHost and ::dstPitch
- * specify the (host) base address of the destination data, the bytes per row,
- * and the height of each 2D slice of the 3D array. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_DEVICE, ::dstDevice and ::dstPitch
- * specify the (device) base address of the destination data, the bytes per
- * row, and the height of each 2D slice of the 3D array. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_ARRAY, ::dstArray specifies the
- * handle of the destination data. ::dstHost, ::dstDevice, ::dstPitch and
- * ::dstHeight are ignored.
- *
- * - ::srcXInBytes, ::srcY and ::srcZ specify the base address of the source
- * data for the copy.
- *
- * \par
- * For host pointers, the starting address is
- * \code
- void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::srcXInBytes must be evenly divisible by the array
- * element size.
- *
- * - dstXInBytes, ::dstY and ::dstZ specify the base address of the
- * destination data for the copy.
- *
- * \par
- * For host pointers, the base address is
- * \code
- void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::dstXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::WidthInBytes, ::Height and ::Depth specify the width (in bytes), height
- * and depth of the 3D copy being performed.
- * - If specified, ::srcPitch must be greater than or equal to ::WidthInBytes +
- * ::srcXInBytes, and ::dstPitch must be greater than or equal to
- * ::WidthInBytes + dstXInBytes.
- * - If specified, ::srcHeight must be greater than or equal to ::Height +
- * ::srcY, and ::dstHeight must be greater than or equal to ::Height + ::dstY.
- *
- * \par
- * ::cuMemcpy3D() returns an error if any pitch is greater than the maximum
- * allowed (::CU_DEVICE_ATTRIBUTE_MAX_PITCH).
- *
- * The ::srcLOD and ::dstLOD members of the ::CUDA_MEMCPY3D structure must be
- * set to 0.
- *
- * \param pCopy - Parameters for the memory copy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemcpy3D(const CUDA_MEMCPY3D *pCopy);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Copies memory between contexts
- *
- * Perform a 3D memory copy according to the parameters specified in
- * \p pCopy. See the definition of the ::CUDA_MEMCPY3D_PEER structure
- * for documentation of its parameters.
- *
- * \param pCopy - Parameters for the memory copy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_sync
- *
- * \sa ::cuMemcpyDtoD, ::cuMemcpyPeer, ::cuMemcpyDtoDAsync, ::cuMemcpyPeerAsync,
- * ::cuMemcpy3DPeerAsync
- */
-CUresult CUDAAPI cuMemcpy3DPeer(const CUDA_MEMCPY3D_PEER *pCopy);
-
-/**
- * \brief Copies memory asynchronously
- *
- * Copies data between two pointers. 
- * \p dst and \p src are base pointers of the destination and source, respectively. 
- * \p ByteCount specifies the number of bytes to copy.
- * Note that this function infers the type of the transfer (host to host, host to 
- * device, device to device, or device to host) from the pointer values. This
- * function is only allowed in contexts which support unified addressing.
- *
- * \param dst - Destination unified virtual address space pointer
- * \param src - Source unified virtual address space pointer
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpyAsync(CUdeviceptr dst, CUdeviceptr src, size_t ByteCount, CUstream hStream);
-
-/**
- * \brief Copies device memory between two contexts asynchronously.
- *
- * Copies from device memory in one context to device memory in another
- * context. \p dstDevice is the base device pointer of the destination memory 
- * and \p dstContext is the destination context. \p srcDevice is the base 
- * device pointer of the source memory and \p srcContext is the source pointer. 
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstDevice - Destination device pointer
- * \param dstContext - Destination context
- * \param srcDevice - Source device pointer
- * \param srcContext - Source context
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuMemcpyDtoD, ::cuMemcpyPeer, ::cuMemcpy3DPeer, ::cuMemcpyDtoDAsync, 
- * ::cuMemcpy3DPeerAsync
- */
-CUresult CUDAAPI cuMemcpyPeerAsync(CUdeviceptr dstDevice, CUcontext dstContext, CUdeviceptr srcDevice, CUcontext srcContext, size_t ByteCount, CUstream hStream);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Copies memory from Host to Device
- *
- * Copies from host memory to device memory. \p dstDevice and \p srcHost are
- * the base addresses of the destination and source, respectively. \p ByteCount
- * specifies the number of bytes to copy.
- *
- * \param dstDevice - Destination device pointer
- * \param srcHost - Source host pointer
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpyHtoDAsync(CUdeviceptr dstDevice, const void *srcHost, size_t ByteCount, CUstream hStream);
-
-/**
- * \brief Copies memory from Device to Host
- *
- * Copies from device to host memory. \p dstHost and \p srcDevice specify the
- * base pointers of the destination and source, respectively. \p ByteCount
- * specifies the number of bytes to copy.
- *
- * \param dstHost - Destination host pointer
- * \param srcDevice - Source device pointer
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpyDtoHAsync(void *dstHost, CUdeviceptr srcDevice, size_t ByteCount, CUstream hStream);
-
-/**
- * \brief Copies memory from Device to Device
- *
- * Copies from device memory to device memory. \p dstDevice and \p srcDevice
- * are the base pointers of the destination and source, respectively.
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstDevice - Destination device pointer
- * \param srcDevice - Source device pointer
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpyDtoDAsync(CUdeviceptr dstDevice, CUdeviceptr srcDevice, size_t ByteCount, CUstream hStream);
-
-/**
- * \brief Copies memory from Host to Array
- *
- * Copies from host memory to a 1D CUDA array. \p dstArray and \p dstOffset
- * specify the CUDA array handle and starting offset in bytes of the
- * destination data. \p srcHost specifies the base address of the source.
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstArray - Destination array
- * \param dstOffset - Offset in bytes of destination array
- * \param srcHost - Source host pointer
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpyHtoAAsync(CUarray dstArray, size_t dstOffset, const void *srcHost, size_t ByteCount, CUstream hStream);
-
-/**
- * \brief Copies memory from Array to Host
- *
- * Copies from one 1D CUDA array to host memory. \p dstHost specifies the base
- * pointer of the destination. \p srcArray and \p srcOffset specify the CUDA
- * array handle and starting offset in bytes of the source data.
- * \p ByteCount specifies the number of bytes to copy.
- *
- * \param dstHost - Destination pointer
- * \param srcArray - Source array
- * \param srcOffset - Offset in bytes of source array
- * \param ByteCount - Size of memory copy in bytes
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpyAtoHAsync(void *dstHost, CUarray srcArray, size_t srcOffset, size_t ByteCount, CUstream hStream);
-
-/**
- * \brief Copies memory for 2D arrays
- *
- * Perform a 2D memory copy according to the parameters specified in \p pCopy.
- * The ::CUDA_MEMCPY2D structure is defined as:
- *
- * \code
- typedef struct CUDA_MEMCPY2D_st {
- unsigned int srcXInBytes, srcY;
- CUmemorytype srcMemoryType;
- const void *srcHost;
- CUdeviceptr srcDevice;
- CUarray srcArray;
- unsigned int srcPitch;
- unsigned int dstXInBytes, dstY;
- CUmemorytype dstMemoryType;
- void *dstHost;
- CUdeviceptr dstDevice;
- CUarray dstArray;
- unsigned int dstPitch;
- unsigned int WidthInBytes;
- unsigned int Height;
- } CUDA_MEMCPY2D;
- * \endcode
- * where:
- * - ::srcMemoryType and ::dstMemoryType specify the type of memory of the
- * source and destination, respectively; ::CUmemorytype_enum is defined as:
- *
- * \code
- typedef enum CUmemorytype_enum {
- CU_MEMORYTYPE_HOST = 0x01,
- CU_MEMORYTYPE_DEVICE = 0x02,
- CU_MEMORYTYPE_ARRAY = 0x03,
- CU_MEMORYTYPE_UNIFIED = 0x04
- } CUmemorytype;
- * \endcode
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_HOST, ::srcHost and ::srcPitch
- * specify the (host) base address of the source data and the bytes per row to
- * apply. ::srcArray is ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::srcDevice and ::srcPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::srcArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_DEVICE, ::srcDevice and ::srcPitch
- * specify the (device) base address of the source data and the bytes per row
- * to apply. ::srcArray is ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_ARRAY, ::srcArray specifies the
- * handle of the source data. ::srcHost, ::srcDevice and ::srcPitch are
- * ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::dstDevice and ::dstPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::dstArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_HOST, ::dstHost and ::dstPitch
- * specify the (host) base address of the destination data and the bytes per
- * row to apply. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_DEVICE, ::dstDevice and ::dstPitch
- * specify the (device) base address of the destination data and the bytes per
- * row to apply. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_ARRAY, ::dstArray specifies the
- * handle of the destination data. ::dstHost, ::dstDevice and ::dstPitch are
- * ignored.
- *
- * - ::srcXInBytes and ::srcY specify the base address of the source data for
- * the copy.
- *
- * \par
- * For host pointers, the starting address is
- * \code
- void* Start = (void*)((char*)srcHost+srcY*srcPitch + srcXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr Start = srcDevice+srcY*srcPitch+srcXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::srcXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::dstXInBytes and ::dstY specify the base address of the destination data
- * for the copy.
- *
- * \par
- * For host pointers, the base address is
- * \code
- void* dstStart = (void*)((char*)dstHost+dstY*dstPitch + dstXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr dstStart = dstDevice+dstY*dstPitch+dstXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::dstXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::WidthInBytes and ::Height specify the width (in bytes) and height of
- * the 2D copy being performed.
- * - If specified, ::srcPitch must be greater than or equal to ::WidthInBytes +
- * ::srcXInBytes, and ::dstPitch must be greater than or equal to
- * ::WidthInBytes + dstXInBytes.
- * - If specified, ::srcPitch must be greater than or equal to ::WidthInBytes +
- * ::srcXInBytes, and ::dstPitch must be greater than or equal to
- * ::WidthInBytes + dstXInBytes.
- * - If specified, ::srcHeight must be greater than or equal to ::Height +
- * ::srcY, and ::dstHeight must be greater than or equal to ::Height + ::dstY.
- *
- * \par
- * ::cuMemcpy2DAsync() returns an error if any pitch is greater than the maximum
- * allowed (::CU_DEVICE_ATTRIBUTE_MAX_PITCH). ::cuMemAllocPitch() passes back
- * pitches that always work with ::cuMemcpy2D(). On intra-device memory copies
- * (device to device, CUDA array to device, CUDA array to CUDA array),
- * ::cuMemcpy2DAsync() may fail for pitches not computed by ::cuMemAllocPitch().
- *
- * \param pCopy - Parameters for the memory copy
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpy2DAsync(const CUDA_MEMCPY2D *pCopy, CUstream hStream);
-
-/**
- * \brief Copies memory for 3D arrays
- *
- * Perform a 3D memory copy according to the parameters specified in
- * \p pCopy. The ::CUDA_MEMCPY3D structure is defined as:
- *
- * \code
- typedef struct CUDA_MEMCPY3D_st {
-
- unsigned int srcXInBytes, srcY, srcZ;
- unsigned int srcLOD;
- CUmemorytype srcMemoryType;
- const void *srcHost;
- CUdeviceptr srcDevice;
- CUarray srcArray;
- unsigned int srcPitch; // ignored when src is array
- unsigned int srcHeight; // ignored when src is array; may be 0 if Depth==1
-
- unsigned int dstXInBytes, dstY, dstZ;
- unsigned int dstLOD;
- CUmemorytype dstMemoryType;
- void *dstHost;
- CUdeviceptr dstDevice;
- CUarray dstArray;
- unsigned int dstPitch; // ignored when dst is array
- unsigned int dstHeight; // ignored when dst is array; may be 0 if Depth==1
-
- unsigned int WidthInBytes;
- unsigned int Height;
- unsigned int Depth;
- } CUDA_MEMCPY3D;
- * \endcode
- * where:
- * - ::srcMemoryType and ::dstMemoryType specify the type of memory of the
- * source and destination, respectively; ::CUmemorytype_enum is defined as:
- *
- * \code
- typedef enum CUmemorytype_enum {
- CU_MEMORYTYPE_HOST = 0x01,
- CU_MEMORYTYPE_DEVICE = 0x02,
- CU_MEMORYTYPE_ARRAY = 0x03,
- CU_MEMORYTYPE_UNIFIED = 0x04
- } CUmemorytype;
- * \endcode
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::srcDevice and ::srcPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::srcArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_HOST, ::srcHost, ::srcPitch and
- * ::srcHeight specify the (host) base address of the source data, the bytes
- * per row, and the height of each 2D slice of the 3D array. ::srcArray is
- * ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_DEVICE, ::srcDevice, ::srcPitch and
- * ::srcHeight specify the (device) base address of the source data, the bytes
- * per row, and the height of each 2D slice of the 3D array. ::srcArray is
- * ignored.
- *
- * \par
- * If ::srcMemoryType is ::CU_MEMORYTYPE_ARRAY, ::srcArray specifies the
- * handle of the source data. ::srcHost, ::srcDevice, ::srcPitch and
- * ::srcHeight are ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_UNIFIED, ::dstDevice and ::dstPitch
- * specify the (unified virtual address space) base address of the source data 
- * and the bytes per row to apply. ::dstArray is ignored. 
- * This value may be used only if unified addressing is supported in the calling 
- * context.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_HOST, ::dstHost and ::dstPitch
- * specify the (host) base address of the destination data, the bytes per row,
- * and the height of each 2D slice of the 3D array. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_DEVICE, ::dstDevice and ::dstPitch
- * specify the (device) base address of the destination data, the bytes per
- * row, and the height of each 2D slice of the 3D array. ::dstArray is ignored.
- *
- * \par
- * If ::dstMemoryType is ::CU_MEMORYTYPE_ARRAY, ::dstArray specifies the
- * handle of the destination data. ::dstHost, ::dstDevice, ::dstPitch and
- * ::dstHeight are ignored.
- *
- * - ::srcXInBytes, ::srcY and ::srcZ specify the base address of the source
- * data for the copy.
- *
- * \par
- * For host pointers, the starting address is
- * \code
- void* Start = (void*)((char*)srcHost+(srcZ*srcHeight+srcY)*srcPitch + srcXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr Start = srcDevice+(srcZ*srcHeight+srcY)*srcPitch+srcXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::srcXInBytes must be evenly divisible by the array
- * element size.
- *
- * - dstXInBytes, ::dstY and ::dstZ specify the base address of the
- * destination data for the copy.
- *
- * \par
- * For host pointers, the base address is
- * \code
- void* dstStart = (void*)((char*)dstHost+(dstZ*dstHeight+dstY)*dstPitch + dstXInBytes);
- * \endcode
- *
- * \par
- * For device pointers, the starting address is
- * \code
- CUdeviceptr dstStart = dstDevice+(dstZ*dstHeight+dstY)*dstPitch+dstXInBytes;
- * \endcode
- *
- * \par
- * For CUDA arrays, ::dstXInBytes must be evenly divisible by the array
- * element size.
- *
- * - ::WidthInBytes, ::Height and ::Depth specify the width (in bytes), height
- * and depth of the 3D copy being performed.
- * - If specified, ::srcPitch must be greater than or equal to ::WidthInBytes +
- * ::srcXInBytes, and ::dstPitch must be greater than or equal to
- * ::WidthInBytes + dstXInBytes.
- * - If specified, ::srcHeight must be greater than or equal to ::Height +
- * ::srcY, and ::dstHeight must be greater than or equal to ::Height + ::dstY.
- *
- * \par
- * ::cuMemcpy3DAsync() returns an error if any pitch is greater than the maximum
- * allowed (::CU_DEVICE_ATTRIBUTE_MAX_PITCH).
- *
- * The ::srcLOD and ::dstLOD members of the ::CUDA_MEMCPY3D structure must be
- * set to 0.
- *
- * \param pCopy - Parameters for the memory copy
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemcpy3DAsync(const CUDA_MEMCPY3D *pCopy, CUstream hStream);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Copies memory between contexts asynchronously.
- *
- * Perform a 3D memory copy according to the parameters specified in
- * \p pCopy. See the definition of the ::CUDA_MEMCPY3D_PEER structure
- * for documentation of its parameters.
- *
- * \param pCopy - Parameters for the memory copy
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_async
- * \note_null_stream
- *
- * \sa ::cuMemcpyDtoD, ::cuMemcpyPeer, ::cuMemcpyDtoDAsync, ::cuMemcpyPeerAsync,
- * ::cuMemcpy3DPeerAsync
- */
-CUresult CUDAAPI cuMemcpy3DPeerAsync(const CUDA_MEMCPY3D_PEER *pCopy, CUstream hStream);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Initializes device memory
- *
- * Sets the memory range of \p N 8-bit values to the specified value
- * \p uc.
- *
- * \param dstDevice - Destination device pointer
- * \param uc - Value to set
- * \param N - Number of elements
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD8(CUdeviceptr dstDevice, unsigned char uc, size_t N);
-
-/**
- * \brief Initializes device memory
- *
- * Sets the memory range of \p N 16-bit values to the specified value
- * \p us. The \p dstDevice pointer must be two byte aligned.
- *
- * \param dstDevice - Destination device pointer
- * \param us - Value to set
- * \param N - Number of elements
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD16(CUdeviceptr dstDevice, unsigned short us, size_t N);
-
-/**
- * \brief Initializes device memory
- *
- * Sets the memory range of \p N 32-bit values to the specified value
- * \p ui. The \p dstDevice pointer must be four byte aligned.
- *
- * \param dstDevice - Destination device pointer
- * \param ui - Value to set
- * \param N - Number of elements
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD32(CUdeviceptr dstDevice, unsigned int ui, size_t N);
-
-/**
- * \brief Initializes device memory
- *
- * Sets the 2D memory range of \p Width 8-bit values to the specified value
- * \p uc. \p Height specifies the number of rows to set, and \p dstPitch
- * specifies the number of bytes between each row. This function performs
- * fastest when the pitch is one that has been passed back by
- * ::cuMemAllocPitch().
- *
- * \param dstDevice - Destination device pointer
- * \param dstPitch - Pitch of destination device pointer
- * \param uc - Value to set
- * \param Width - Width of row
- * \param Height - Number of rows
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD2D8(CUdeviceptr dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height);
-
-/**
- * \brief Initializes device memory
- *
- * Sets the 2D memory range of \p Width 16-bit values to the specified value
- * \p us. \p Height specifies the number of rows to set, and \p dstPitch
- * specifies the number of bytes between each row. The \p dstDevice pointer
- * and \p dstPitch offset must be two byte aligned. This function performs
- * fastest when the pitch is one that has been passed back by
- * ::cuMemAllocPitch().
- *
- * \param dstDevice - Destination device pointer
- * \param dstPitch - Pitch of destination device pointer
- * \param us - Value to set
- * \param Width - Width of row
- * \param Height - Number of rows
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD2D16(CUdeviceptr dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height);
-
-/**
- * \brief Initializes device memory
- *
- * Sets the 2D memory range of \p Width 32-bit values to the specified value
- * \p ui. \p Height specifies the number of rows to set, and \p dstPitch
- * specifies the number of bytes between each row. The \p dstDevice pointer
- * and \p dstPitch offset must be four byte aligned. This function performs
- * fastest when the pitch is one that has been passed back by
- * ::cuMemAllocPitch().
- *
- * \param dstDevice - Destination device pointer
- * \param dstPitch - Pitch of destination device pointer
- * \param ui - Value to set
- * \param Width - Width of row
- * \param Height - Number of rows
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD2D32(CUdeviceptr dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height);
-
-/**
- * \brief Sets device memory
- *
- * Sets the memory range of \p N 8-bit values to the specified value
- * \p uc.
- *
- * \param dstDevice - Destination device pointer
- * \param uc - Value to set
- * \param N - Number of elements
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD8Async(CUdeviceptr dstDevice, unsigned char uc, size_t N, CUstream hStream);
-
-/**
- * \brief Sets device memory
- *
- * Sets the memory range of \p N 16-bit values to the specified value
- * \p us. The \p dstDevice pointer must be two byte aligned.
- *
- * \param dstDevice - Destination device pointer
- * \param us - Value to set
- * \param N - Number of elements
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD16Async(CUdeviceptr dstDevice, unsigned short us, size_t N, CUstream hStream);
-
-/**
- * \brief Sets device memory
- *
- * Sets the memory range of \p N 32-bit values to the specified value
- * \p ui. The \p dstDevice pointer must be four byte aligned.
- *
- * \param dstDevice - Destination device pointer
- * \param ui - Value to set
- * \param N - Number of elements
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async, ::cuMemsetD32
- */
-CUresult CUDAAPI cuMemsetD32Async(CUdeviceptr dstDevice, unsigned int ui, size_t N, CUstream hStream);
-
-/**
- * \brief Sets device memory
- *
- * Sets the 2D memory range of \p Width 8-bit values to the specified value
- * \p uc. \p Height specifies the number of rows to set, and \p dstPitch
- * specifies the number of bytes between each row. This function performs
- * fastest when the pitch is one that has been passed back by
- * ::cuMemAllocPitch().
- *
- * \param dstDevice - Destination device pointer
- * \param dstPitch - Pitch of destination device pointer
- * \param uc - Value to set
- * \param Width - Width of row
- * \param Height - Number of rows
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD2D8Async(CUdeviceptr dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height, CUstream hStream);
-
-/**
- * \brief Sets device memory
- *
- * Sets the 2D memory range of \p Width 16-bit values to the specified value
- * \p us. \p Height specifies the number of rows to set, and \p dstPitch
- * specifies the number of bytes between each row. The \p dstDevice pointer 
- * and \p dstPitch offset must be two byte aligned. This function performs
- * fastest when the pitch is one that has been passed back by
- * ::cuMemAllocPitch().
- *
- * \param dstDevice - Destination device pointer
- * \param dstPitch - Pitch of destination device pointer
- * \param us - Value to set
- * \param Width - Width of row
- * \param Height - Number of rows
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D32, ::cuMemsetD2D32Async,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD2D16Async(CUdeviceptr dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height, CUstream hStream);
-
-/**
- * \brief Sets device memory
- *
- * Sets the 2D memory range of \p Width 32-bit values to the specified value
- * \p ui. \p Height specifies the number of rows to set, and \p dstPitch
- * specifies the number of bytes between each row. The \p dstDevice pointer
- * and \p dstPitch offset must be four byte aligned. This function performs
- * fastest when the pitch is one that has been passed back by
- * ::cuMemAllocPitch().
- *
- * \param dstDevice - Destination device pointer
- * \param dstPitch - Pitch of destination device pointer
- * \param ui - Value to set
- * \param Width - Width of row
- * \param Height - Number of rows
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- * \note_memset
- * \note_null_stream
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D8Async,
- * ::cuMemsetD2D16, ::cuMemsetD2D16Async, ::cuMemsetD2D32,
- * ::cuMemsetD8, ::cuMemsetD8Async, ::cuMemsetD16, ::cuMemsetD16Async,
- * ::cuMemsetD32, ::cuMemsetD32Async
- */
-CUresult CUDAAPI cuMemsetD2D32Async(CUdeviceptr dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height, CUstream hStream);
-
-/**
- * \brief Creates a 1D or 2D CUDA array
- *
- * Creates a CUDA array according to the ::CUDA_ARRAY_DESCRIPTOR structure
- * \p pAllocateArray and returns a handle to the new CUDA array in \p *pHandle.
- * The ::CUDA_ARRAY_DESCRIPTOR is defined as:
- *
- * \code
- typedef struct {
- unsigned int Width;
- unsigned int Height;
- CUarray_format Format;
- unsigned int NumChannels;
- } CUDA_ARRAY_DESCRIPTOR;
- * \endcode
- * where:
- *
- * - \p Width, and \p Height are the width, and height of the CUDA array (in
- * elements); the CUDA array is one-dimensional if height is 0, two-dimensional
- * otherwise;
- * - ::Format specifies the format of the elements; ::CUarray_format is
- * defined as:
- * \code
- typedef enum CUarray_format_enum {
- CU_AD_FORMAT_UNSIGNED_INT8 = 0x01,
- CU_AD_FORMAT_UNSIGNED_INT16 = 0x02,
- CU_AD_FORMAT_UNSIGNED_INT32 = 0x03,
- CU_AD_FORMAT_SIGNED_INT8 = 0x08,
- CU_AD_FORMAT_SIGNED_INT16 = 0x09,
- CU_AD_FORMAT_SIGNED_INT32 = 0x0a,
- CU_AD_FORMAT_HALF = 0x10,
- CU_AD_FORMAT_FLOAT = 0x20
- } CUarray_format;
- * \endcode
- * - \p NumChannels specifies the number of packed components per CUDA array
- * element; it may be 1, 2, or 4;
- *
- * Here are examples of CUDA array descriptions:
- *
- * Description for a CUDA array of 2048 floats:
- * \code
- CUDA_ARRAY_DESCRIPTOR desc;
- desc.Format = CU_AD_FORMAT_FLOAT;
- desc.NumChannels = 1;
- desc.Width = 2048;
- desc.Height = 1;
- * \endcode
- *
- * Description for a 64 x 64 CUDA array of floats:
- * \code
- CUDA_ARRAY_DESCRIPTOR desc;
- desc.Format = CU_AD_FORMAT_FLOAT;
- desc.NumChannels = 1;
- desc.Width = 64;
- desc.Height = 64;
- * \endcode
- *
- * Description for a \p width x \p height CUDA array of 64-bit, 4x16-bit
- * float16's:
- * \code
- CUDA_ARRAY_DESCRIPTOR desc;
- desc.FormatFlags = CU_AD_FORMAT_HALF;
- desc.NumChannels = 4;
- desc.Width = width;
- desc.Height = height;
- * \endcode
- *
- * Description for a \p width x \p height CUDA array of 16-bit elements, each
- * of which is two 8-bit unsigned chars:
- * \code
- CUDA_ARRAY_DESCRIPTOR arrayDesc;
- desc.FormatFlags = CU_AD_FORMAT_UNSIGNED_INT8;
- desc.NumChannels = 2;
- desc.Width = width;
- desc.Height = height;
- * \endcode
- *
- * \param pHandle - Returned array
- * \param pAllocateArray - Array descriptor
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuArrayCreate(CUarray *pHandle, const CUDA_ARRAY_DESCRIPTOR *pAllocateArray);
-
-/**
- * \brief Get a 1D or 2D CUDA array descriptor
- *
- * Returns in \p *pArrayDescriptor a descriptor containing information on the
- * format and dimensions of the CUDA array \p hArray. It is useful for
- * subroutines that have been passed a CUDA array, but need to know the CUDA
- * array parameters for validation or other purposes.
- *
- * \param pArrayDescriptor - Returned array descriptor
- * \param hArray - Array to get descriptor of
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuArrayGetDescriptor(CUDA_ARRAY_DESCRIPTOR *pArrayDescriptor, CUarray hArray);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-
-/**
- * \brief Destroys a CUDA array
- *
- * Destroys the CUDA array \p hArray.
- *
- * \param hArray - Array to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_ARRAY_IS_MAPPED
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuArrayDestroy(CUarray hArray);
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Creates a 3D CUDA array
- *
- * Creates a CUDA array according to the ::CUDA_ARRAY3D_DESCRIPTOR structure
- * \p pAllocateArray and returns a handle to the new CUDA array in \p *pHandle.
- * The ::CUDA_ARRAY3D_DESCRIPTOR is defined as:
- *
- * \code
- typedef struct {
- unsigned int Width;
- unsigned int Height;
- unsigned int Depth;
- CUarray_format Format;
- unsigned int NumChannels;
- unsigned int Flags;
- } CUDA_ARRAY3D_DESCRIPTOR;
- * \endcode
- * where:
- *
- * - \p Width, \p Height, and \p Depth are the width, height, and depth of the
- * CUDA array (in elements); the following types of CUDA arrays can be allocated:
- * - A 1D array is allocated if \p Height and \p Depth extents are both zero.
- * - A 2D array is allocated if only \p Depth extent is zero.
- * - A 3D array is allocated if all three extents are non-zero.
- * - A 1D layered CUDA array is allocated if only \p Height is zero and the 
- * ::CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number 
- * of layers is determined by the depth extent.
- * - A 2D layered CUDA array is allocated if all three extents are non-zero and 
- * the ::CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number 
- * of layers is determined by the depth extent.
- * - A cubemap CUDA array is allocated if all three extents are non-zero and the
- * ::CUDA_ARRAY3D_CUBEMAP flag is set. \p Width must be equal to \p Height, and 
- * \p Depth must be six. A cubemap is a special type of 2D layered CUDA array, 
- * where the six layers represent the six faces of a cube. The order of the six 
- * layers in memory is the same as that listed in ::CUarray_cubemap_face.
- * - A cubemap layered CUDA array is allocated if all three extents are non-zero, 
- * and both, ::CUDA_ARRAY3D_CUBEMAP and ::CUDA_ARRAY3D_LAYERED flags are set. 
- * \p Width must be equal to \p Height, and \p Depth must be a multiple of six. 
- * A cubemap layered CUDA array is a special type of 2D layered CUDA array that 
- * consists of a collection of cubemaps. The first six layers represent the first 
- * cubemap, the next six layers form the second cubemap, and so on.
- *
- * - ::Format specifies the format of the elements; ::CUarray_format is
- * defined as:
- * \code
- typedef enum CUarray_format_enum {
- CU_AD_FORMAT_UNSIGNED_INT8 = 0x01,
- CU_AD_FORMAT_UNSIGNED_INT16 = 0x02,
- CU_AD_FORMAT_UNSIGNED_INT32 = 0x03,
- CU_AD_FORMAT_SIGNED_INT8 = 0x08,
- CU_AD_FORMAT_SIGNED_INT16 = 0x09,
- CU_AD_FORMAT_SIGNED_INT32 = 0x0a,
- CU_AD_FORMAT_HALF = 0x10,
- CU_AD_FORMAT_FLOAT = 0x20
- } CUarray_format;
- * \endcode
- *
- * - \p NumChannels specifies the number of packed components per CUDA array
- * element; it may be 1, 2, or 4;
- *
- * - ::Flags may be set to 
- * - ::CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA arrays. If this flag is set, 
- * \p Depth specifies the number of layers, not the depth of a 3D array.
- * - ::CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to the CUDA array. 
- * If this flag is not set, ::cuSurfRefSetArray will fail when attempting to bind the CUDA array 
- * to a surface reference.
- * - ::CUDA_ARRAY3D_CUBEMAP to enable creation of cubemaps. If this flag is set, \p Width must be
- * equal to \p Height, and \p Depth must be six. If the ::CUDA_ARRAY3D_LAYERED flag is also set,
- * then \p Depth must be a multiple of six.
- * - ::CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA array will be used for texture gather.
- * Texture gather can only be performed on 2D CUDA arrays.
- *
- * \p Width, \p Height and \p Depth must meet certain size requirements as listed in the following table. 
- * All values are specified in elements. Note that for brevity's sake, the full name of the device attribute 
- * is not specified. For ex., TEXTURE1D_WIDTH refers to the device attribute 
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH.
- *
- * Note that 2D CUDA arrays have different size requirements if the ::CUDA_ARRAY3D_TEXTURE_GATHER flag 
- * is set. \p Width and \p Height must not be greater than ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_WIDTH 
- * and ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_GATHER_HEIGHT respectively, in that case.
- *
- * <table>
- * <tr><td>CUDA array type</td>
- * <td>Valid extents that must always be met {(width range in elements), (height range), 
- * (depth range)}</td>
- * <td>Valid extents with CUDA_ARRAY3D_SURFACE_LDST set 
- * {(width range in elements), (height range), (depth range)}</td></tr>
- * <tr><td>1D</td>
- * <td>{ (1,TEXTURE1D_WIDTH), 0, 0 }</td>
- * <td>{ (1,SURFACE1D_WIDTH), 0, 0 }</td></tr>
- * <tr><td>2D</td>
- * <td>{ (1,TEXTURE2D_WIDTH), (1,TEXTURE2D_HEIGHT), 0 }</td>
- * <td>{ (1,SURFACE2D_WIDTH), (1,SURFACE2D_HEIGHT), 0 }</td></tr>
- * <tr><td>3D</td>
- * <td>{ (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) }
- * OR { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), 
- * (1,TEXTURE3D_DEPTH_ALTERNATE) }</td>
- * <td>{ (1,SURFACE3D_WIDTH), (1,SURFACE3D_HEIGHT), 
- * (1,SURFACE3D_DEPTH) }</td></tr>
- * <tr><td>1D Layered</td>
- * <td>{ (1,TEXTURE1D_LAYERED_WIDTH), 0, 
- * (1,TEXTURE1D_LAYERED_LAYERS) }</td>
- * <td>{ (1,SURFACE1D_LAYERED_WIDTH), 0, 
- * (1,SURFACE1D_LAYERED_LAYERS) }</td></tr>
- * <tr><td>2D Layered</td>
- * <td>{ (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), 
- * (1,TEXTURE2D_LAYERED_LAYERS) }</td>
- * <td>{ (1,SURFACE2D_LAYERED_WIDTH), (1,SURFACE2D_LAYERED_HEIGHT), 
- * (1,SURFACE2D_LAYERED_LAYERS) }</td></tr>
- * <tr><td>Cubemap</td>
- * <td>{ (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 }</td>
- * <td>{ (1,SURFACECUBEMAP_WIDTH), 
- * (1,SURFACECUBEMAP_WIDTH), 6 }</td></tr>
- * <tr><td>Cubemap Layered</td>
- * <td>{ (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), 
- * (1,TEXTURECUBEMAP_LAYERED_LAYERS) }</td>
- * <td>{ (1,SURFACECUBEMAP_LAYERED_WIDTH), (1,SURFACECUBEMAP_LAYERED_WIDTH), 
- * (1,SURFACECUBEMAP_LAYERED_LAYERS) }</td></tr>
- * </table>
- *
- * Here are examples of CUDA array descriptions:
- *
- * Description for a CUDA array of 2048 floats:
- * \code
- CUDA_ARRAY3D_DESCRIPTOR desc;
- desc.Format = CU_AD_FORMAT_FLOAT;
- desc.NumChannels = 1;
- desc.Width = 2048;
- desc.Height = 0;
- desc.Depth = 0;
- * \endcode
- *
- * Description for a 64 x 64 CUDA array of floats:
- * \code
- CUDA_ARRAY3D_DESCRIPTOR desc;
- desc.Format = CU_AD_FORMAT_FLOAT;
- desc.NumChannels = 1;
- desc.Width = 64;
- desc.Height = 64;
- desc.Depth = 0;
- * \endcode
- *
- * Description for a \p width x \p height x \p depth CUDA array of 64-bit,
- * 4x16-bit float16's:
- * \code
- CUDA_ARRAY3D_DESCRIPTOR desc;
- desc.FormatFlags = CU_AD_FORMAT_HALF;
- desc.NumChannels = 4;
- desc.Width = width;
- desc.Height = height;
- desc.Depth = depth;
- * \endcode
- *
- * \param pHandle - Returned array
- * \param pAllocateArray - 3D array descriptor
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa ::cuArray3DGetDescriptor, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuArray3DCreate(CUarray *pHandle, const CUDA_ARRAY3D_DESCRIPTOR *pAllocateArray);
-
-/**
- * \brief Get a 3D CUDA array descriptor
- *
- * Returns in \p *pArrayDescriptor a descriptor containing information on the
- * format and dimensions of the CUDA array \p hArray. It is useful for
- * subroutines that have been passed a CUDA array, but need to know the CUDA
- * array parameters for validation or other purposes.
- *
- * This function may be called on 1D and 2D arrays, in which case the \p Height
- * and/or \p Depth members of the descriptor struct will be set to 0.
- *
- * \param pArrayDescriptor - Returned 3D array descriptor
- * \param hArray - 3D array to get descriptor of
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE
- * \notefnerr
- *
- * \sa ::cuArray3DCreate, ::cuArrayCreate,
- * ::cuArrayDestroy, ::cuArrayGetDescriptor, ::cuMemAlloc, ::cuMemAllocHost,
- * ::cuMemAllocPitch, ::cuMemcpy2D, ::cuMemcpy2DAsync, ::cuMemcpy2DUnaligned,
- * ::cuMemcpy3D, ::cuMemcpy3DAsync, ::cuMemcpyAtoA, ::cuMemcpyAtoD,
- * ::cuMemcpyAtoH, ::cuMemcpyAtoHAsync, ::cuMemcpyDtoA, ::cuMemcpyDtoD, ::cuMemcpyDtoDAsync,
- * ::cuMemcpyDtoH, ::cuMemcpyDtoHAsync, ::cuMemcpyHtoA, ::cuMemcpyHtoAAsync,
- * ::cuMemcpyHtoD, ::cuMemcpyHtoDAsync, ::cuMemFree, ::cuMemFreeHost,
- * ::cuMemGetAddressRange, ::cuMemGetInfo, ::cuMemHostAlloc,
- * ::cuMemHostGetDevicePointer, ::cuMemsetD2D8, ::cuMemsetD2D16,
- * ::cuMemsetD2D32, ::cuMemsetD8, ::cuMemsetD16, ::cuMemsetD32
- */
-CUresult CUDAAPI cuArray3DGetDescriptor(CUDA_ARRAY3D_DESCRIPTOR *pArrayDescriptor, CUarray hArray);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-#if __CUDA_API_VERSION >= 5000
-
-/**
- * \brief Creates a CUDA mipmapped array
- *
- * Creates a CUDA mipmapped array according to the ::CUDA_ARRAY3D_DESCRIPTOR structure
- * \p pMipmappedArrayDesc and returns a handle to the new CUDA mipmapped array in \p *pHandle.
- * \p numMipmapLevels specifies the number of mipmap levels to be allocated. This value is
- * clamped to the range [1, 1 + floor(log2(max(width, height, depth)))].
- *
- * The ::CUDA_ARRAY3D_DESCRIPTOR is defined as:
- *
- * \code
- typedef struct {
- unsigned int Width;
- unsigned int Height;
- unsigned int Depth;
- CUarray_format Format;
- unsigned int NumChannels;
- unsigned int Flags;
- } CUDA_ARRAY3D_DESCRIPTOR;
- * \endcode
- * where:
- *
- * - \p Width, \p Height, and \p Depth are the width, height, and depth of the
- * CUDA array (in elements); the following types of CUDA arrays can be allocated:
- * - A 1D mipmapped array is allocated if \p Height and \p Depth extents are both zero.
- * - A 2D mipmapped array is allocated if only \p Depth extent is zero.
- * - A 3D mipmapped array is allocated if all three extents are non-zero.
- * - A 1D layered CUDA mipmapped array is allocated if only \p Height is zero and the 
- * ::CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 1D array. The number 
- * of layers is determined by the depth extent.
- * - A 2D layered CUDA mipmapped array is allocated if all three extents are non-zero and 
- * the ::CUDA_ARRAY3D_LAYERED flag is set. Each layer is a 2D array. The number 
- * of layers is determined by the depth extent.
- * - A cubemap CUDA mipmapped array is allocated if all three extents are non-zero and the
- * ::CUDA_ARRAY3D_CUBEMAP flag is set. \p Width must be equal to \p Height, and 
- * \p Depth must be six. A cubemap is a special type of 2D layered CUDA array, 
- * where the six layers represent the six faces of a cube. The order of the six 
- * layers in memory is the same as that listed in ::CUarray_cubemap_face.
- * - A cubemap layered CUDA mipmapped array is allocated if all three extents are non-zero, 
- * and both, ::CUDA_ARRAY3D_CUBEMAP and ::CUDA_ARRAY3D_LAYERED flags are set. 
- * \p Width must be equal to \p Height, and \p Depth must be a multiple of six. 
- * A cubemap layered CUDA array is a special type of 2D layered CUDA array that 
- * consists of a collection of cubemaps. The first six layers represent the first 
- * cubemap, the next six layers form the second cubemap, and so on.
- *
- * - ::Format specifies the format of the elements; ::CUarray_format is
- * defined as:
- * \code
- typedef enum CUarray_format_enum {
- CU_AD_FORMAT_UNSIGNED_INT8 = 0x01,
- CU_AD_FORMAT_UNSIGNED_INT16 = 0x02,
- CU_AD_FORMAT_UNSIGNED_INT32 = 0x03,
- CU_AD_FORMAT_SIGNED_INT8 = 0x08,
- CU_AD_FORMAT_SIGNED_INT16 = 0x09,
- CU_AD_FORMAT_SIGNED_INT32 = 0x0a,
- CU_AD_FORMAT_HALF = 0x10,
- CU_AD_FORMAT_FLOAT = 0x20
- } CUarray_format;
- * \endcode
- *
- * - \p NumChannels specifies the number of packed components per CUDA array
- * element; it may be 1, 2, or 4;
- *
- * - ::Flags may be set to 
- * - ::CUDA_ARRAY3D_LAYERED to enable creation of layered CUDA mipmapped arrays. If this flag is set, 
- * \p Depth specifies the number of layers, not the depth of a 3D array.
- * - ::CUDA_ARRAY3D_SURFACE_LDST to enable surface references to be bound to individual mipmap levels of
- * the CUDA mipmapped array. If this flag is not set, ::cuSurfRefSetArray will fail when attempting to 
- * bind a mipmap level of the CUDA mipmapped array to a surface reference.
- * - ::CUDA_ARRAY3D_CUBEMAP to enable creation of mipmapped cubemaps. If this flag is set, \p Width must be
- * equal to \p Height, and \p Depth must be six. If the ::CUDA_ARRAY3D_LAYERED flag is also set,
- * then \p Depth must be a multiple of six.
- * - ::CUDA_ARRAY3D_TEXTURE_GATHER to indicate that the CUDA mipmapped array will be used for texture gather.
- * Texture gather can only be performed on 2D CUDA mipmapped arrays.
- *
- * \p Width, \p Height and \p Depth must meet certain size requirements as listed in the following table. 
- * All values are specified in elements. Note that for brevity's sake, the full name of the device attribute 
- * is not specified. For ex., TEXTURE1D_MIPMAPPED_WIDTH refers to the device attribute 
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH.
- *
- * <table>
- * <tr><td>CUDA array type</td>
- * <td>Valid extents that must always be met {(width range in elements), (height range), 
- * (depth range)}</td></tr>
- * <tr><td>1D</td>
- * <td>{ (1,TEXTURE1D_MIPMAPPED_WIDTH), 0, 0 }</td></tr>
- * <tr><td>2D</td>
- * <td>{ (1,TEXTURE2D_MIPMAPPED_WIDTH), (1,TEXTURE2D_MIPMAPPED_HEIGHT), 0 }</td></tr>
- * <tr><td>3D</td>
- * <td>{ (1,TEXTURE3D_WIDTH), (1,TEXTURE3D_HEIGHT), (1,TEXTURE3D_DEPTH) }
- * OR { (1,TEXTURE3D_WIDTH_ALTERNATE), (1,TEXTURE3D_HEIGHT_ALTERNATE), 
- * (1,TEXTURE3D_DEPTH_ALTERNATE) }</td></tr>
- * <tr><td>1D Layered</td>
- * <td>{ (1,TEXTURE1D_LAYERED_WIDTH), 0, 
- * (1,TEXTURE1D_LAYERED_LAYERS) }</td></tr>
- * <tr><td>2D Layered</td>
- * <td>{ (1,TEXTURE2D_LAYERED_WIDTH), (1,TEXTURE2D_LAYERED_HEIGHT), 
- * (1,TEXTURE2D_LAYERED_LAYERS) }</td></tr>
- * <tr><td>Cubemap</td>
- * <td>{ (1,TEXTURECUBEMAP_WIDTH), (1,TEXTURECUBEMAP_WIDTH), 6 }</td></tr>
- * <tr><td>Cubemap Layered</td>
- * <td>{ (1,TEXTURECUBEMAP_LAYERED_WIDTH), (1,TEXTURECUBEMAP_LAYERED_WIDTH), 
- * (1,TEXTURECUBEMAP_LAYERED_LAYERS) }</td></tr>
- * </table>
- *
- *
- * \param pHandle - Returned mipmapped array
- * \param pMipmappedArrayDesc - mipmapped array descriptor
- * \param numMipmapLevels - Number of mipmap levels
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa ::cuMipmappedArrayDestroy, ::cuMipmappedArrayGetLevel, ::cuArrayCreate,
- */
-CUresult CUDAAPI cuMipmappedArrayCreate(CUmipmappedArray *pHandle, const CUDA_ARRAY3D_DESCRIPTOR *pMipmappedArrayDesc, unsigned int numMipmapLevels);
-
-/**
- * \brief Gets a mipmap level of a CUDA mipmapped array
- *
- * Returns in \p *pLevelArray a CUDA array that represents a single mipmap level
- * of the CUDA mipmapped array \p hMipmappedArray.
- *
- * If \p level is greater than the maximum number of levels in this mipmapped array,
- * ::CUDA_ERROR_INVALID_VALUE is returned.
- *
- * \param pLevelArray - Returned mipmap level CUDA array
- * \param hMipmappedArray - CUDA mipmapped array
- * \param level - Mipmap level
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE
- * \notefnerr
- *
- * \sa ::cuMipmappedArrayCreate, ::cuMipmappedArrayDestroy, ::cuArrayCreate,
- */
-CUresult CUDAAPI cuMipmappedArrayGetLevel(CUarray *pLevelArray, CUmipmappedArray hMipmappedArray, unsigned int level);
-
-/**
- * \brief Destroys a CUDA mipmapped array
- *
- * Destroys the CUDA mipmapped array \p hMipmappedArray.
- *
- * \param hMipmappedArray - Mipmapped array to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_ARRAY_IS_MAPPED
- * \notefnerr
- *
- * \sa ::cuMipmappedArrayCreate, ::cuMipmappedArrayGetLevel, ::cuArrayCreate,
- */
-CUresult CUDAAPI cuMipmappedArrayDestroy(CUmipmappedArray hMipmappedArray);
-
-#endif /* __CUDA_API_VERSION >= 5000 */
-
-/** @} */ /* END CUDA_MEM */
-
-/**
- * \defgroup CUDA_UNIFIED Unified Addressing
- *
- * ___MANBRIEF___ unified addressing functions of the low-level CUDA driver
- * API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the unified addressing functions of the 
- * low-level CUDA driver application programming interface.
- *
- * @{
- *
- * \section CUDA_UNIFIED_overview Overview
- *
- * CUDA devices can share a unified address space with the host. 
- * For these devices there is no distinction between a device
- * pointer and a host pointer -- the same pointer value may be 
- * used to access memory from the host program and from a kernel 
- * running on the device (with exceptions enumerated below).
- *
- * \section CUDA_UNIFIED_support Supported Platforms
- * 
- * Whether or not a device supports unified addressing may be 
- * queried by calling ::cuDeviceGetAttribute() with the device 
- * attribute ::CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING.
- *
- * Unified addressing is automatically enabled in 64-bit processes 
- * on devices with compute capability greater than or equal to 2.0.
- *
- * \section CUDA_UNIFIED_lookup Looking Up Information from Pointer Values
- *
- * It is possible to look up information about the memory which backs a 
- * pointer value. For instance, one may want to know if a pointer points
- * to host or device memory. As another example, in the case of device 
- * memory, one may want to know on which CUDA device the memory 
- * resides. These properties may be queried using the function 
- * ::cuPointerGetAttribute()
- *
- * Since pointers are unique, it is not necessary to specify information
- * about the pointers specified to the various copy functions in the 
- * CUDA API. The function ::cuMemcpy() may be used to perform a copy
- * between two pointers, ignoring whether they point to host or device
- * memory (making ::cuMemcpyHtoD(), ::cuMemcpyDtoD(), and ::cuMemcpyDtoH()
- * unnecessary for devices supporting unified addressing). For 
- * multidimensional copies, the memory type ::CU_MEMORYTYPE_UNIFIED may be
- * used to specify that the CUDA driver should infer the location of the
- * pointer from its value.
- *
- * \section CUDA_UNIFIED_automaphost Automatic Mapping of Host Allocated Host Memory
- *
- * All host memory allocated in all contexts using ::cuMemAllocHost() and
- * ::cuMemHostAlloc() is always directly accessible from all contexts on
- * all devices that support unified addressing. This is the case regardless 
- * of whether or not the flags ::CU_MEMHOSTALLOC_PORTABLE and
- * ::CU_MEMHOSTALLOC_DEVICEMAP are specified.
- *
- * The pointer value through which allocated host memory may be accessed 
- * in kernels on all devices that support unified addressing is the same 
- * as the pointer value through which that memory is accessed on the host,
- * so it is not necessary to call ::cuMemHostGetDevicePointer() to get the device 
- * pointer for these allocations.
- * 
- * Note that this is not the case for memory allocated using the flag
- * ::CU_MEMHOSTALLOC_WRITECOMBINED, as discussed below.
- *
- * \section CUDA_UNIFIED_autopeerregister Automatic Registration of Peer Memory
- *
- * Upon enabling direct access from a context that supports unified addressing 
- * to another peer context that supports unified addressing using 
- * ::cuCtxEnablePeerAccess() all memory allocated in the peer context using 
- * ::cuMemAlloc() and ::cuMemAllocPitch() will immediately be accessible 
- * by the current context. The device pointer value through
- * which any peer memory may be accessed in the current context
- * is the same pointer value through which that memory may be
- * accessed in the peer context.
- *
- * \section CUDA_UNIFIED_exceptions Exceptions, Disjoint Addressing
- * 
- * Not all memory may be accessed on devices through the same pointer
- * value through which they are accessed on the host. These exceptions
- * are host memory registered using ::cuMemHostRegister() and host memory
- * allocated using the flag ::CU_MEMHOSTALLOC_WRITECOMBINED. For these 
- * exceptions, there exists a distinct host and device address for the
- * memory. The device address is guaranteed to not overlap any valid host
- * pointer range and is guaranteed to have the same value across all 
- * contexts that support unified addressing. 
- * 
- * This device address may be queried using ::cuMemHostGetDevicePointer() 
- * when a context using unified addressing is current. Either the host 
- * or the unified device pointer value may be used to refer to this memory 
- * through ::cuMemcpy() and similar functions using the 
- * ::CU_MEMORYTYPE_UNIFIED memory type.
- *
- */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Returns information about a pointer
- * 
- * The supported attributes are:
- * 
- * - ::CU_POINTER_ATTRIBUTE_CONTEXT: 
- * 
- * Returns in \p *data the ::CUcontext in which \p ptr was allocated or 
- * registered. 
- * The type of \p data must be ::CUcontext *. 
- * 
- * If \p ptr was not allocated by, mapped by, or registered with
- * a ::CUcontext which uses unified virtual addressing then 
- * ::CUDA_ERROR_INVALID_VALUE is returned.
- * 
- * - ::CU_POINTER_ATTRIBUTE_MEMORY_TYPE: 
- * 
- * Returns in \p *data the physical memory type of the memory that 
- * \p ptr addresses as a ::CUmemorytype enumerated value.
- * The type of \p data must be unsigned int.
- * 
- * If \p ptr addresses device memory then \p *data is set to 
- * ::CU_MEMORYTYPE_DEVICE. The particular ::CUdevice on which the 
- * memory resides is the ::CUdevice of the ::CUcontext returned by the 
- * ::CU_POINTER_ATTRIBUTE_CONTEXT attribute of \p ptr.
- * 
- * If \p ptr addresses host memory then \p *data is set to 
- * ::CU_MEMORYTYPE_HOST.
- * 
- * If \p ptr was not allocated by, mapped by, or registered with
- * a ::CUcontext which uses unified virtual addressing then 
- * ::CUDA_ERROR_INVALID_VALUE is returned.
- *
- * If the current ::CUcontext does not support unified virtual 
- * addressing then ::CUDA_ERROR_INVALID_CONTEXT is returned.
- * 
- * - ::CU_POINTER_ATTRIBUTE_DEVICE_POINTER:
- * 
- * Returns in \p *data the device pointer value through which
- * \p ptr may be accessed by kernels running in the current 
- * ::CUcontext.
- * The type of \p data must be CUdeviceptr *.
- * 
- * If there exists no device pointer value through which
- * kernels running in the current ::CUcontext may access
- * \p ptr then ::CUDA_ERROR_INVALID_VALUE is returned.
- * 
- * If there is no current ::CUcontext then 
- * ::CUDA_ERROR_INVALID_CONTEXT is returned.
- * 
- * Except in the exceptional disjoint addressing cases discussed 
- * below, the value returned in \p *data will equal the input 
- * value \p ptr.
- * 
- * - ::CU_POINTER_ATTRIBUTE_HOST_POINTER:
- * 
- * Returns in \p *data the host pointer value through which 
- * \p ptr may be accessed by by the host program.
- * The type of \p data must be void **.
- * If there exists no host pointer value through which
- * the host program may directly access \p ptr then 
- * ::CUDA_ERROR_INVALID_VALUE is returned.
- * 
- * Except in the exceptional disjoint addressing cases discussed 
- * below, the value returned in \p *data will equal the input 
- * value \p ptr.
- *
- * - ::CU_POINTER_ATTRIBUTE_P2P_TOKENS:
- *
- * Returns in \p *data two tokens for use with the nv-p2p.h Linux
- * kernel interface. \p data must be a struct of type
- * CUDA_POINTER_ATTRIBUTE_P2P_TOKENS.
- *
- * \p ptr must be a pointer to memory obtained from :cuMemAlloc().
- * Note that p2pToken and vaSpaceToken are only valid for the
- * lifetime of the source allocation. A subsequent allocation at
- * the same address may return completely different tokens.
- * Querying this attribute has a side effect of setting the attribute
- * ::CU_POINTER_ATTRIBUTE_SYNC_MEMOPS for the region of memory that
- * \p ptr points to.
- * 
- * - ::CU_POINTER_ATTRIBUTE_SYNC_MEMOPS:
- *
- * A boolean attribute which when set, ensures that synchronous memory operations
- * initiated on the region of memory that \p ptr points to will always synchronize.
- * See further documentation in the section titled "API synchronization behavior"
- * to learn more about cases when synchronous memory operations can
- * exhibit asynchronous behavior.
- *
- * - ::CU_POINTER_ATTRIBUTE_BUFFER_ID:
- *
- * Returns in \p *data a buffer ID which is guaranteed to be unique within the process.
- * \p data must point to an unsigned long long.
- *
- * \p ptr must be a pointer to memory obtained from a CUDA memory allocation API.
- * Every memory allocation from any of the CUDA memory allocation APIs will
- * have a unique ID over a process lifetime. Subsequent allocations do not reuse IDs
- * from previous freed allocations. IDs are only unique within a single process.
- *
- *
- * - ::CU_POINTER_ATTRIBUTE_IS_MANAGED:
- *
- * Returns in \p *data a boolean that indicates whether the pointer points to
- * managed memory or not.
- *
- * \par
- *
- * Note that for most allocations in the unified virtual address space
- * the host and device pointer for accessing the allocation will be the 
- * same. The exceptions to this are
- * - user memory registered using ::cuMemHostRegister 
- * - host memory allocated using ::cuMemHostAlloc with the 
- * ::CU_MEMHOSTALLOC_WRITECOMBINED flag
- * For these types of allocation there will exist separate, disjoint host 
- * and device addresses for accessing the allocation. In particular 
- * - The host address will correspond to an invalid unmapped device address 
- * (which will result in an exception if accessed from the device) 
- * - The device address will correspond to an invalid unmapped host address 
- * (which will result in an exception if accessed from the host).
- * For these types of allocations, querying ::CU_POINTER_ATTRIBUTE_HOST_POINTER 
- * and ::CU_POINTER_ATTRIBUTE_DEVICE_POINTER may be used to retrieve the host 
- * and device addresses from either address.
- *
- * \param data - Returned pointer attribute value
- * \param attribute - Pointer attribute to query
- * \param ptr - Pointer
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa cuPointerSetAttribute,
- * ::cuMemAlloc,
- * ::cuMemFree,
- * ::cuMemAllocHost,
- * ::cuMemFreeHost,
- * ::cuMemHostAlloc,
- * ::cuMemHostRegister,
- * ::cuMemHostUnregister
- */
-CUresult CUDAAPI cuPointerGetAttribute(void *data, CUpointer_attribute attribute, CUdeviceptr ptr);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-#if __CUDA_API_VERSION >= 6000
-/**
- * \brief Set attributes on a previously allocated memory region
- *
- * The supported attributes are:
- *
- * - ::CU_POINTER_ATTRIBUTE_SYNC_MEMOPS:
- *
- * A boolean attribute that can either be set (1) or unset (0). When set,
- * the region of memory that \p ptr points to is guaranteed to always synchronize
- * memory operations that are synchronous. If there are some previously initiated
- * synchronous memory operations that are pending when this attribute is set, the
- * function does not return until those memory operations are complete.
- * See further documentation in the section titled "API synchronization behavior"
- * to learn more about cases when synchronous memory operations can
- * exhibit asynchronous behavior.
- * \p value will be considered as a pointer to an unsigned integer to which this attribute is to be set.
- *
- * \param value - Pointer to memory containing the value to be set
- * \param attribute - Pointer attribute to set
- * \param ptr - Pointer to a memory region allocated using CUDA memory allocation APIs
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa ::cuPointerGetAttribute,
- * ::cuPointerGetAttributes,
- * ::cuMemAlloc,
- * ::cuMemFree,
- * ::cuMemAllocHost,
- * ::cuMemFreeHost,
- * ::cuMemHostAlloc,
- * ::cuMemHostRegister,
- * ::cuMemHostUnregister
- */
-CUresult CUDAAPI cuPointerSetAttribute(const void *value, CUpointer_attribute attribute, CUdeviceptr ptr);
-#endif /* __CUDA_API_VERSION >= 6000 */
-
-#if __CUDA_API_VERSION >= 7000
-/**
- * \brief Returns information about a pointer.
- *
- * The supported attributes are (refer to ::cuPointerGetAttribute for attribute descriptions and restrictions):
- *
- * - ::CU_POINTER_ATTRIBUTE_CONTEXT
- * - ::CU_POINTER_ATTRIBUTE_MEMORY_TYPE
- * - ::CU_POINTER_ATTRIBUTE_DEVICE_POINTER
- * - ::CU_POINTER_ATTRIBUTE_HOST_POINTER
- * - ::CU_POINTER_ATTRIBUTE_SYNC_MEMOPS
- * - ::CU_POINTER_ATTRIBUTE_BUFFER_ID
- * - ::CU_POINTER_ATTRIBUTE_IS_MANAGED
- *
- * \param numAttributes - Number of attributes to query
- * \param attributes - An array of attributes to query
- * (numAttributes and the number of attributes in this array should match)
- * \param data - A two-dimensional array containing pointers to memory
- * locations where the result of each attribute query will be written to.
- * \param ptr - Pointer to query
- *
- * Unlike ::cuPointerGetAttribute, this function will not return an error when the \p ptr
- * encountered is not a valid CUDA pointer. Instead, the attributes are assigned default NULL values
- * and CUDA_SUCCESS is returned.
- *
- * If \p ptr was not allocated by, mapped by, or registered with a ::CUcontext which uses UVA
- * (Unified Virtual Addressing), ::CUDA_ERROR_INVALID_CONTEXT is returned.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa ::cuPointerGetAttribute,
- * ::cuPointerSetAttribute
- */
-CUresult CUDAAPI cuPointerGetAttributes(unsigned int numAttributes, CUpointer_attribute *attributes, void **data, CUdeviceptr ptr);
-#endif /* __CUDA_API_VERSION >= 7000 */
-
-/** @} */ /* END CUDA_UNIFIED */
-
-/**
- * \defgroup CUDA_STREAM Stream Management
- *
- * ___MANBRIEF___ stream management functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the stream management functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Create a stream
- *
- * Creates a stream and returns a handle in \p phStream. The \p Flags argument
- * determines behaviors of the stream. Valid values for \p Flags are:
- * - ::CU_STREAM_DEFAULT: Default stream creation flag.
- * - ::CU_STREAM_NON_BLOCKING: Specifies that work running in the created 
- * stream may run concurrently with work in stream 0 (the NULL stream), and that
- * the created stream should perform no implicit synchronization with stream 0.
- *
- * \param phStream - Returned newly created stream
- * \param Flags - Parameters for stream creation
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuStreamDestroy,
- * ::cuStreamCreateWithPriority,
- * ::cuStreamGetPriority,
- * ::cuStreamGetFlags,
- * ::cuStreamWaitEvent,
- * ::cuStreamQuery,
- * ::cuStreamSynchronize,
- * ::cuStreamAddCallback
- */
-CUresult CUDAAPI cuStreamCreate(CUstream *phStream, unsigned int Flags);
-
-/**
- * \brief Create a stream with the given priority
- *
- * Creates a stream with the specified priority and returns a handle in \p phStream.
- * This API alters the scheduler priority of work in the stream. Work in a higher
- * priority stream may preempt work already executing in a low priority stream.
- *
- * \p priority follows a convention where lower numbers represent higher priorities.
- * '0' represents default priority. The range of meaningful numerical priorities can
- * be queried using ::cuCtxGetStreamPriorityRange. If the specified priority is
- * outside the numerical range returned by ::cuCtxGetStreamPriorityRange,
- * it will automatically be clamped to the lowest or the highest number in the range.
- *
- * \param phStream - Returned newly created stream
- * \param flags - Flags for stream creation. See ::cuStreamCreate for a list of
- * valid flags
- * \param priority - Stream priority. Lower numbers represent higher priorities.
- * See ::cuCtxGetStreamPriorityRange for more information about
- * meaningful stream priorities that can be passed.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \note Stream priorities are supported only on Quadro and Tesla GPUs
- * with compute capability 3.5 or higher.
- *
- * \note In the current implementation, only compute kernels launched in
- * priority streams are affected by the stream's priority. Stream priorities have
- * no effect on host-to-device and device-to-host memory operations.
- *
- * \sa ::cuStreamDestroy,
- * ::cuStreamCreate,
- * ::cuStreamGetPriority,
- * ::cuCtxGetStreamPriorityRange,
- * ::cuStreamGetFlags,
- * ::cuStreamWaitEvent,
- * ::cuStreamQuery,
- * ::cuStreamSynchronize,
- * ::cuStreamAddCallback
- */
-CUresult CUDAAPI cuStreamCreateWithPriority(CUstream *phStream, unsigned int flags, int priority);
-
-
-/**
- * \brief Query the priority of a given stream
- *
- * Query the priority of a stream created using ::cuStreamCreate or ::cuStreamCreateWithPriority
- * and return the priority in \p priority. Note that if the stream was created with a
- * priority outside the numerical range returned by ::cuCtxGetStreamPriorityRange,
- * this function returns the clamped priority.
- * See ::cuStreamCreateWithPriority for details about priority clamping.
- *
- * \param hStream - Handle to the stream to be queried
- * \param priority - Pointer to a signed integer in which the stream's priority is returned
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuStreamDestroy,
- * ::cuStreamCreate,
- * ::cuStreamCreateWithPriority,
- * ::cuCtxGetStreamPriorityRange,
- * ::cuStreamGetFlags
- */
-CUresult CUDAAPI cuStreamGetPriority(CUstream hStream, int *priority);
-
-/**
- * \brief Query the flags of a given stream
- *
- * Query the flags of a stream created using ::cuStreamCreate or ::cuStreamCreateWithPriority
- * and return the flags in \p flags.
- *
- * \param hStream - Handle to the stream to be queried
- * \param flags - Pointer to an unsigned integer in which the stream's flags are returned
- * The value returned in \p flags is a logical 'OR' of all flags that
- * were used while creating this stream. See ::cuStreamCreate for the list
- * of valid flags
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa ::cuStreamDestroy,
- * ::cuStreamCreate,
- * ::cuStreamGetPriority
- */
-CUresult CUDAAPI cuStreamGetFlags(CUstream hStream, unsigned int *flags);
-
-
-/**
- * \brief Make a compute stream wait on an event
- *
- * Makes all future work submitted to \p hStream wait until \p hEvent
- * reports completion before beginning execution. This synchronization
- * will be performed efficiently on the device. The event \p hEvent may
- * be from a different context than \p hStream, in which case this function
- * will perform cross-device synchronization.
- *
- * The stream \p hStream will wait only for the completion of the most recent
- * host call to ::cuEventRecord() on \p hEvent. Once this call has returned,
- * any functions (including ::cuEventRecord() and ::cuEventDestroy()) may be
- * called on \p hEvent again, and subsequent calls will not have any
- * effect on \p hStream.
- *
- * If ::cuEventRecord() has not been called on \p hEvent, this call acts as if
- * the record has already completed, and so is a functional no-op.
- *
- * \param hStream - Stream to wait
- * \param hEvent - Event to wait on (may not be NULL)
- * \param Flags - Parameters for the operation (must be 0)
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuStreamCreate,
- * ::cuEventRecord,
- * ::cuStreamQuery,
- * ::cuStreamSynchronize,
- * ::cuStreamAddCallback,
- * ::cuStreamDestroy
- */
-CUresult CUDAAPI cuStreamWaitEvent(CUstream hStream, CUevent hEvent, unsigned int Flags);
-
-/**
- * \brief Add a callback to a compute stream
- *
- * Adds a callback to be called on the host after all currently enqueued
- * items in the stream have completed. For each 
- * cuStreamAddCallback call, the callback will be executed exactly once.
- * The callback will block later work in the stream until it is finished.
- *
- * The callback may be passed ::CUDA_SUCCESS or an error code. In the event
- * of a device error, all subsequently executed callbacks will receive an
- * appropriate ::CUresult.
- *
- * Callbacks must not make any CUDA API calls. Attempting to use a CUDA API
- * will result in ::CUDA_ERROR_NOT_PERMITTED. Callbacks must not perform any
- * synchronization that may depend on outstanding device work or other callbacks
- * that are not mandated to run earlier. Callbacks without a mandated order
- * (in independent streams) execute in undefined order and may be serialized.
- *
- * This API requires compute capability 1.1 or greater. See
- * ::cuDeviceGetAttribute or ::cuDeviceGetProperties to query compute
- * capability. Attempting to use this API with earlier compute versions will
- * return ::CUDA_ERROR_NOT_SUPPORTED.
- *
- * For the purposes of Unified Memory, callback execution makes a number of
- * guarantees:
- * <ul>
- * <li>The callback stream is considered idle for the duration of the
- * callback. Thus, for example, a callback may always use memory attached
- * to the callback stream.</li>
- * <li>The start of execution of a callback has the same effect as
- * synchronizing an event recorded in the same stream immediately prior to
- * the callback. It thus synchronizes streams which have been "joined"
- * prior to the callback.</li>
- * <li>Adding device work to any stream does not have the effect of making
- * the stream active until all preceding callbacks have executed. Thus, for
- * example, a callback might use global attached memory even if work has
- * been added to another stream, if it has been properly ordered with an
- * event.</li>
- * <li>Completion of a callback does not cause a stream to become
- * active except as described above. The callback stream will remain idle
- * if no device work follows the callback, and will remain idle across
- * consecutive callbacks without device work in between. Thus, for example,
- * stream synchronization can be done by signaling from a callback at the
- * end of the stream.</li>
- * </ul>
- *
- * \param hStream - Stream to add callback to
- * \param callback - The function to call once preceding stream operations are complete
- * \param userData - User specified data to be passed to the callback function
- * \param flags - Reserved for future use, must be 0
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_SUPPORTED
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuStreamCreate,
- * ::cuStreamQuery,
- * ::cuStreamSynchronize,
- * ::cuStreamWaitEvent,
- * ::cuStreamDestroy,
- * ::cuMemAllocManaged,
- * ::cuStreamAttachMemAsync
- */
-CUresult CUDAAPI cuStreamAddCallback(CUstream hStream, CUstreamCallback callback, void *userData, unsigned int flags);
-
-#if __CUDA_API_VERSION >= 6000
-
-/**
- * \brief Attach memory to a stream asynchronously
- *
- * Enqueues an operation in \p hStream to specify stream association of
- * \p length bytes of memory starting from \p dptr. This function is a
- * stream-ordered operation, meaning that it is dependent on, and will
- * only take effect when, previous work in stream has completed. Any
- * previous association is automatically replaced.
- *
- * \p dptr must point to an address within managed memory space declared
- * using the __managed__ keyword or allocated with ::cuMemAllocManaged.
- *
- * \p length must be zero, to indicate that the entire allocation's
- * stream association is being changed. Currently, it's not possible
- * to change stream association for a portion of an allocation.
- *
- * The stream association is specified using \p flags which must be
- * one of ::CUmemAttach_flags.
- * If the ::CU_MEM_ATTACH_GLOBAL flag is specified, the memory can be accessed
- * by any stream on any device.
- * If the ::CU_MEM_ATTACH_HOST flag is specified, the program makes a guarantee
- * that it won't access the memory on the device from any stream.
- * If the ::CU_MEM_ATTACH_SINGLE flag is specified, the program makes a guarantee
- * that it will only access the memory on the device from \p hStream. It is illegal
- * to attach singly to the NULL stream, because the NULL stream is a virtual global
- * stream and not a specific stream. An error will be returned in this case.
- *
- * When memory is associated with a single stream, the Unified Memory system will
- * allow CPU access to this memory region so long as all operations in \p hStream
- * have completed, regardless of whether other streams are active. In effect,
- * this constrains exclusive ownership of the managed memory region by
- * an active GPU to per-stream activity instead of whole-GPU activity.
- *
- * Accessing memory on the device from streams that are not associated with
- * it will produce undefined results. No error checking is performed by the
- * Unified Memory system to ensure that kernels launched into other streams
- * do not access this region. 
- *
- * It is a program's responsibility to order calls to ::cuStreamAttachMemAsync
- * via events, synchronization or other means to ensure legal access to memory
- * at all times. Data visibility and coherency will be changed appropriately
- * for all kernels which follow a stream-association change.
- *
- * If \p hStream is destroyed while data is associated with it, the association is
- * removed and the association reverts to the default visibility of the allocation
- * as specified at ::cuMemAllocManaged. For __managed__ variables, the default
- * association is always ::CU_MEM_ATTACH_GLOBAL. Note that destroying a stream is an
- * asynchronous operation, and as a result, the change to default association won't
- * happen until all work in the stream has completed.
- *
- * \param hStream - Stream in which to enqueue the attach operation
- * \param dptr - Pointer to memory (must be a pointer to managed memory)
- * \param length - Length of memory (must be zero)
- * \param flags - Must be one of ::CUmemAttach_flags
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_SUPPORTED
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuStreamCreate,
- * ::cuStreamQuery,
- * ::cuStreamSynchronize,
- * ::cuStreamWaitEvent,
- * ::cuStreamDestroy,
- * ::cuMemAllocManaged
- */
-CUresult CUDAAPI cuStreamAttachMemAsync(CUstream hStream, CUdeviceptr dptr, size_t length, unsigned int flags);
-
-#endif /* __CUDA_API_VERSION >= 6000 */
-
-/**
- * \brief Determine status of a compute stream
- *
- * Returns ::CUDA_SUCCESS if all operations in the stream specified by
- * \p hStream have completed, or ::CUDA_ERROR_NOT_READY if not.
- *
- * For the purposes of Unified Memory, a return value of ::CUDA_SUCCESS
- * is equivalent to having called ::cuStreamSynchronize().
- *
- * \param hStream - Stream to query status of
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_READY
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuStreamCreate,
- * ::cuStreamWaitEvent,
- * ::cuStreamDestroy,
- * ::cuStreamSynchronize,
- * ::cuStreamAddCallback
- */
-CUresult CUDAAPI cuStreamQuery(CUstream hStream);
-
-/**
- * \brief Wait until a stream's tasks are completed
- *
- * Waits until the device has completed all operations in the stream specified
- * by \p hStream. If the context was created with the 
- * ::CU_CTX_SCHED_BLOCKING_SYNC flag, the CPU thread will block until the
- * stream is finished with all of its tasks.
- *
- * \param hStream - Stream to wait for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuStreamCreate,
- * ::cuStreamDestroy,
- * ::cuStreamWaitEvent,
- * ::cuStreamQuery,
- * ::cuStreamAddCallback
- */
-CUresult CUDAAPI cuStreamSynchronize(CUstream hStream);
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Destroys a stream
- *
- * Destroys the stream specified by \p hStream. 
- *
- * In case the device is still doing work in the stream \p hStream
- * when ::cuStreamDestroy() is called, the function will return immediately 
- * and the resources associated with \p hStream will be released automatically 
- * once the device has completed all work in \p hStream.
- *
- * \param hStream - Stream to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuStreamCreate,
- * ::cuStreamWaitEvent,
- * ::cuStreamQuery,
- * ::cuStreamSynchronize,
- * ::cuStreamAddCallback
- */
-CUresult CUDAAPI cuStreamDestroy(CUstream hStream);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-/** @} */ /* END CUDA_STREAM */
-
-
-/**
- * \defgroup CUDA_EVENT Event Management
- *
- * ___MANBRIEF___ event management functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the event management functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Creates an event
- *
- * Creates an event *phEvent with the flags specified via \p Flags. Valid flags
- * include:
- * - ::CU_EVENT_DEFAULT: Default event creation flag.
- * - ::CU_EVENT_BLOCKING_SYNC: Specifies that the created event should use blocking
- * synchronization. A CPU thread that uses ::cuEventSynchronize() to wait on
- * an event created with this flag will block until the event has actually
- * been recorded.
- * - ::CU_EVENT_DISABLE_TIMING: Specifies that the created event does not need
- * to record timing data. Events created with this flag specified and
- * the ::CU_EVENT_BLOCKING_SYNC flag not specified will provide the best
- * performance when used with ::cuStreamWaitEvent() and ::cuEventQuery().
- * - ::CU_EVENT_INTERPROCESS: Specifies that the created event may be used as an
- * interprocess event by ::cuIpcGetEventHandle(). ::CU_EVENT_INTERPROCESS must
- * be specified along with ::CU_EVENT_DISABLE_TIMING.
- *
- * \param phEvent - Returns newly created event
- * \param Flags - Event creation flags
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_OUT_OF_MEMORY
- * \notefnerr
- *
- * \sa
- * ::cuEventRecord,
- * ::cuEventQuery,
- * ::cuEventSynchronize,
- * ::cuEventDestroy,
- * ::cuEventElapsedTime
- */
-CUresult CUDAAPI cuEventCreate(CUevent *phEvent, unsigned int Flags);
-
-/**
- * \brief Records an event
- *
- * Records an event. See note on NULL stream behavior. Since operation is
- * asynchronous, ::cuEventQuery or ::cuEventSynchronize() must be used
- * to determine when the event has actually been recorded.
- *
- * If ::cuEventRecord() has previously been called on \p hEvent, then this
- * call will overwrite any existing state in \p hEvent. Any subsequent calls
- * which examine the status of \p hEvent will only examine the completion of
- * this most recent call to ::cuEventRecord().
- *
- * It is necessary that \p hEvent and \p hStream be created on the same context.
- *
- * \param hEvent - Event to record
- * \param hStream - Stream to record event for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuEventCreate,
- * ::cuEventQuery,
- * ::cuEventSynchronize,
- * ::cuStreamWaitEvent,
- * ::cuEventDestroy,
- * ::cuEventElapsedTime
- */
-CUresult CUDAAPI cuEventRecord(CUevent hEvent, CUstream hStream);
-
-/**
- * \brief Queries an event's status
- *
- * Query the status of all device work preceding the most recent
- * call to ::cuEventRecord() (in the appropriate compute streams,
- * as specified by the arguments to ::cuEventRecord()).
- *
- * If this work has successfully been completed by the device, or if
- * ::cuEventRecord() has not been called on \p hEvent, then ::CUDA_SUCCESS is
- * returned. If this work has not yet been completed by the device then
- * ::CUDA_ERROR_NOT_READY is returned.
- *
- * For the purposes of Unified Memory, a return value of ::CUDA_SUCCESS
- * is equivalent to having called ::cuEventSynchronize().
- *
- * \param hEvent - Event to query
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_NOT_READY
- * \notefnerr
- *
- * \sa ::cuEventCreate,
- * ::cuEventRecord,
- * ::cuEventSynchronize,
- * ::cuEventDestroy,
- * ::cuEventElapsedTime
- */
-CUresult CUDAAPI cuEventQuery(CUevent hEvent);
-
-/**
- * \brief Waits for an event to complete
- *
- * Wait until the completion of all device work preceding the most recent
- * call to ::cuEventRecord() (in the appropriate compute streams, as specified
- * by the arguments to ::cuEventRecord()).
- *
- * If ::cuEventRecord() has not been called on \p hEvent, ::CUDA_SUCCESS is
- * returned immediately.
- *
- * Waiting for an event that was created with the ::CU_EVENT_BLOCKING_SYNC
- * flag will cause the calling CPU thread to block until the event has
- * been completed by the device. If the ::CU_EVENT_BLOCKING_SYNC flag has
- * not been set, then the CPU thread will busy-wait until the event has
- * been completed by the device.
- *
- * \param hEvent - Event to wait for
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE
- * \notefnerr
- *
- * \sa ::cuEventCreate,
- * ::cuEventRecord,
- * ::cuEventQuery,
- * ::cuEventDestroy,
- * ::cuEventElapsedTime
- */
-CUresult CUDAAPI cuEventSynchronize(CUevent hEvent);
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Destroys an event
- *
- * Destroys the event specified by \p hEvent.
- *
- * In case \p hEvent has been recorded but has not yet been completed
- * when ::cuEventDestroy() is called, the function will return immediately and 
- * the resources associated with \p hEvent will be released automatically once
- * the device has completed \p hEvent.
- *
- * \param hEvent - Event to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE
- * \notefnerr
- *
- * \sa ::cuEventCreate,
- * ::cuEventRecord,
- * ::cuEventQuery,
- * ::cuEventSynchronize,
- * ::cuEventElapsedTime
- */
-CUresult CUDAAPI cuEventDestroy(CUevent hEvent);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-/**
- * \brief Computes the elapsed time between two events
- *
- * Computes the elapsed time between two events (in milliseconds with a
- * resolution of around 0.5 microseconds).
- *
- * If either event was last recorded in a non-NULL stream, the resulting time
- * may be greater than expected (even if both used the same stream handle). This
- * happens because the ::cuEventRecord() operation takes place asynchronously
- * and there is no guarantee that the measured latency is actually just between
- * the two events. Any number of other different stream operations could execute
- * in between the two measured events, thus altering the timing in a significant
- * way.
- *
- * If ::cuEventRecord() has not been called on either event then
- * ::CUDA_ERROR_INVALID_HANDLE is returned. If ::cuEventRecord() has been called
- * on both events but one or both of them has not yet been completed (that is,
- * ::cuEventQuery() would return ::CUDA_ERROR_NOT_READY on at least one of the
- * events), ::CUDA_ERROR_NOT_READY is returned. If either event was created with
- * the ::CU_EVENT_DISABLE_TIMING flag, then this function will return
- * ::CUDA_ERROR_INVALID_HANDLE.
- *
- * \param pMilliseconds - Time between \p hStart and \p hEnd in ms
- * \param hStart - Starting event
- * \param hEnd - Ending event
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_READY
- * \notefnerr
- *
- * \sa ::cuEventCreate,
- * ::cuEventRecord,
- * ::cuEventQuery,
- * ::cuEventSynchronize,
- * ::cuEventDestroy
- */
-CUresult CUDAAPI cuEventElapsedTime(float *pMilliseconds, CUevent hStart, CUevent hEnd);
-
-/** @} */ /* END CUDA_EVENT */
-
-/**
- * \defgroup CUDA_EXEC Execution Control
- *
- * ___MANBRIEF___ execution control functions of the low-level CUDA driver API
- * (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the execution control functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Returns information about a function
- *
- * Returns in \p *pi the integer value of the attribute \p attrib on the kernel
- * given by \p hfunc. The supported attributes are:
- * - ::CU_FUNC_ATTRIBUTE_MAX_THREADS_PER_BLOCK: The maximum number of threads
- * per block, beyond which a launch of the function would fail. This number
- * depends on both the function and the device on which the function is
- * currently loaded.
- * - ::CU_FUNC_ATTRIBUTE_SHARED_SIZE_BYTES: The size in bytes of
- * statically-allocated shared memory per block required by this function.
- * This does not include dynamically-allocated shared memory requested by
- * the user at runtime.
- * - ::CU_FUNC_ATTRIBUTE_CONST_SIZE_BYTES: The size in bytes of user-allocated
- * constant memory required by this function.
- * - ::CU_FUNC_ATTRIBUTE_LOCAL_SIZE_BYTES: The size in bytes of local memory
- * used by each thread of this function.
- * - ::CU_FUNC_ATTRIBUTE_NUM_REGS: The number of registers used by each thread
- * of this function.
- * - ::CU_FUNC_ATTRIBUTE_PTX_VERSION: The PTX virtual architecture version for
- * which the function was compiled. This value is the major PTX version * 10
- * + the minor PTX version, so a PTX version 1.3 function would return the
- * value 13. Note that this may return the undefined value of 0 for cubins
- * compiled prior to CUDA 3.0.
- * - ::CU_FUNC_ATTRIBUTE_BINARY_VERSION: The binary architecture version for
- * which the function was compiled. This value is the major binary
- * version * 10 + the minor binary version, so a binary version 1.3 function
- * would return the value 13. Note that this will return a value of 10 for
- * legacy cubins that do not have a properly-encoded binary architecture
- * version.
- * - ::CU_FUNC_CACHE_MODE_CA: The attribute to indicate whether the function has 
- * been compiled with user specified option "-Xptxas --dlcm=ca" set .
- *
- * \param pi - Returned attribute value
- * \param attrib - Attribute requested
- * \param hfunc - Function to query attribute of
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuCtxGetCacheConfig,
- * ::cuCtxSetCacheConfig,
- * ::cuFuncSetCacheConfig,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuFuncGetAttribute(int *pi, CUfunction_attribute attrib, CUfunction hfunc);
-
-/**
- * \brief Sets the preferred cache configuration for a device function
- *
- * On devices where the L1 cache and shared memory use the same hardware
- * resources, this sets through \p config the preferred cache configuration for
- * the device function \p hfunc. This is only a preference. The driver will use
- * the requested configuration if possible, but it is free to choose a different
- * configuration if required to execute \p hfunc. Any context-wide preference
- * set via ::cuCtxSetCacheConfig() will be overridden by this per-function
- * setting unless the per-function setting is ::CU_FUNC_CACHE_PREFER_NONE. In
- * that case, the current context-wide setting will be used.
- *
- * This setting does nothing on devices where the size of the L1 cache and
- * shared memory are fixed.
- *
- * Launching a kernel with a different preference than the most recent
- * preference setting may insert a device-side synchronization point.
- *
- *
- * The supported cache configurations are:
- * - ::CU_FUNC_CACHE_PREFER_NONE: no preference for shared memory or L1 (default)
- * - ::CU_FUNC_CACHE_PREFER_SHARED: prefer larger shared memory and smaller L1 cache
- * - ::CU_FUNC_CACHE_PREFER_L1: prefer larger L1 cache and smaller shared memory
- * - ::CU_FUNC_CACHE_PREFER_EQUAL: prefer equal sized L1 cache and shared memory
- *
- * \param hfunc - Kernel to configure cache for
- * \param config - Requested cache configuration
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT
- * \notefnerr
- *
- * \sa ::cuCtxGetCacheConfig,
- * ::cuCtxSetCacheConfig,
- * ::cuFuncGetAttribute,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuFuncSetCacheConfig(CUfunction hfunc, CUfunc_cache config);
-
-#if __CUDA_API_VERSION >= 4020
-/**
- * \brief Sets the shared memory configuration for a device function.
- *
- * On devices with configurable shared memory banks, this function will 
- * force all subsequent launches of the specified device function to have
- * the given shared memory bank size configuration. On any given launch of the
- * function, the shared memory configuration of the device will be temporarily
- * changed if needed to suit the function's preferred configuration. Changes in
- * shared memory configuration between subsequent launches of functions, 
- * may introduce a device side synchronization point.
- *
- * Any per-function setting of shared memory bank size set via 
- * ::cuFuncSetSharedMemConfig will override the context wide setting set with
- * ::cuCtxSetSharedMemConfig.
- *
- * Changing the shared memory bank size will not increase shared memory usage
- * or affect occupancy of kernels, but may have major effects on performance. 
- * Larger bank sizes will allow for greater potential bandwidth to shared memory,
- * but will change what kinds of accesses to shared memory will result in bank 
- * conflicts.
- *
- * This function will do nothing on devices with fixed shared memory bank size.
- *
- * The supported bank configurations are:
- * - ::CU_SHARED_MEM_CONFIG_DEFAULT_BANK_SIZE: use the context's shared memory 
- * configuration when launching this function.
- * - ::CU_SHARED_MEM_CONFIG_FOUR_BYTE_BANK_SIZE: set shared memory bank width to
- * be natively four bytes when launching this function.
- * - ::CU_SHARED_MEM_CONFIG_EIGHT_BYTE_BANK_SIZE: set shared memory bank width to
- * be natively eight bytes when launching this function.
- *
- * \param hfunc - kernel to be given a shared memory config
- * \param config - requested shared memory configuration
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT
- * \notefnerr
- *
- * \sa ::cuCtxGetCacheConfig,
- * ::cuCtxSetCacheConfig,
- * ::cuCtxGetSharedMemConfig,
- * ::cuCtxSetSharedMemConfig,
- * ::cuFuncGetAttribute,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuFuncSetSharedMemConfig(CUfunction hfunc, CUsharedconfig config);
-#endif
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \brief Launches a CUDA function
- *
- * Invokes the kernel \p f on a \p gridDimX x \p gridDimY x \p gridDimZ
- * grid of blocks. Each block contains \p blockDimX x \p blockDimY x
- * \p blockDimZ threads.
- *
- * \p sharedMemBytes sets the amount of dynamic shared memory that will be
- * available to each thread block.
- *
- * Kernel parameters to \p f can be specified in one of two ways:
- *
- * 1) Kernel parameters can be specified via \p kernelParams. If \p f
- * has N parameters, then \p kernelParams needs to be an array of N
- * pointers. Each of \p kernelParams[0] through \p kernelParams[N-1]
- * must point to a region of memory from which the actual kernel
- * parameter will be copied. The number of kernel parameters and their
- * offsets and sizes do not need to be specified as that information is
- * retrieved directly from the kernel's image.
- *
- * 2) Kernel parameters can also be packaged by the application into
- * a single buffer that is passed in via the \p extra parameter.
- * This places the burden on the application of knowing each kernel
- * parameter's size and alignment/padding within the buffer. Here is
- * an example of using the \p extra parameter in this manner:
- * \code
- size_t argBufferSize;
- char argBuffer[256];
-
- // populate argBuffer and argBufferSize
-
- void *config[] = {
- CU_LAUNCH_PARAM_BUFFER_POINTER, argBuffer,
- CU_LAUNCH_PARAM_BUFFER_SIZE, &argBufferSize,
- CU_LAUNCH_PARAM_END
- };
- status = cuLaunchKernel(f, gx, gy, gz, bx, by, bz, sh, s, NULL, config);
- * \endcode
- *
- * The \p extra parameter exists to allow ::cuLaunchKernel to take
- * additional less commonly used arguments. \p extra specifies a list of
- * names of extra settings and their corresponding values. Each extra
- * setting name is immediately followed by the corresponding value. The
- * list must be terminated with either NULL or ::CU_LAUNCH_PARAM_END.
- *
- * - ::CU_LAUNCH_PARAM_END, which indicates the end of the \p extra
- * array;
- * - ::CU_LAUNCH_PARAM_BUFFER_POINTER, which specifies that the next
- * value in \p extra will be a pointer to a buffer containing all
- * the kernel parameters for launching kernel \p f;
- * - ::CU_LAUNCH_PARAM_BUFFER_SIZE, which specifies that the next
- * value in \p extra will be a pointer to a size_t containing the
- * size of the buffer specified with ::CU_LAUNCH_PARAM_BUFFER_POINTER;
- *
- * The error ::CUDA_ERROR_INVALID_VALUE will be returned if kernel
- * parameters are specified with both \p kernelParams and \p extra
- * (i.e. both \p kernelParams and \p extra are non-NULL).
- *
- * Calling ::cuLaunchKernel() sets persistent function state that is
- * the same as function state set through the following deprecated APIs:
- * ::cuFuncSetBlockShape(),
- * ::cuFuncSetSharedSize(),
- * ::cuParamSetSize(),
- * ::cuParamSeti(),
- * ::cuParamSetf(),
- * ::cuParamSetv().
- *
- * When the kernel \p f is launched via ::cuLaunchKernel(), the previous
- * block shape, shared size and parameter info associated with \p f
- * is overwritten.
- *
- * Note that to use ::cuLaunchKernel(), the kernel \p f must either have
- * been compiled with toolchain version 3.2 or later so that it will
- * contain kernel parameter information, or have no kernel parameters.
- * If either of these conditions is not met, then ::cuLaunchKernel() will
- * return ::CUDA_ERROR_INVALID_IMAGE.
- *
- * \param f - Kernel to launch
- * \param gridDimX - Width of grid in blocks
- * \param gridDimY - Height of grid in blocks
- * \param gridDimZ - Depth of grid in blocks
- * \param blockDimX - X dimension of each thread block
- * \param blockDimY - Y dimension of each thread block
- * \param blockDimZ - Z dimension of each thread block
- * \param sharedMemBytes - Dynamic shared-memory size per thread block in bytes
- * \param hStream - Stream identifier
- * \param kernelParams - Array of pointers to kernel parameters
- * \param extra - Extra options
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_IMAGE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_LAUNCH_FAILED,
- * ::CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES,
- * ::CUDA_ERROR_LAUNCH_TIMEOUT,
- * ::CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuCtxGetCacheConfig,
- * ::cuCtxSetCacheConfig,
- * ::cuFuncSetCacheConfig,
- * ::cuFuncGetAttribute
- */
-CUresult CUDAAPI cuLaunchKernel(CUfunction f,
- unsigned int gridDimX,
- unsigned int gridDimY,
- unsigned int gridDimZ,
- unsigned int blockDimX,
- unsigned int blockDimY,
- unsigned int blockDimZ,
- unsigned int sharedMemBytes,
- CUstream hStream,
- void **kernelParams,
- void **extra);
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-/** @} */ /* END CUDA_EXEC */
-
-/**
- * \defgroup CUDA_EXEC_DEPRECATED Execution Control [DEPRECATED]
- *
- * ___MANBRIEF___ deprecated execution control functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the deprecated execution control functions of the
- * low-level CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Sets the block-dimensions for the function
- *
- * \deprecated
- *
- * Specifies the \p x, \p y, and \p z dimensions of the thread blocks that are
- * created when the kernel given by \p hfunc is launched.
- *
- * \param hfunc - Kernel to specify dimensions of
- * \param x - X dimension
- * \param y - Y dimension
- * \param z - Z dimension
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuFuncSetSharedSize,
- * ::cuFuncSetCacheConfig,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSeti,
- * ::cuParamSetf,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuFuncSetBlockShape(CUfunction hfunc, int x, int y, int z);
-
-/**
- * \brief Sets the dynamic shared-memory size for the function
- *
- * \deprecated
- *
- * Sets through \p bytes the amount of dynamic shared memory that will be
- * available to each thread block when the kernel given by \p hfunc is launched.
- *
- * \param hfunc - Kernel to specify dynamic shared-memory size for
- * \param bytes - Dynamic shared-memory size per thread in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetCacheConfig,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSeti,
- * ::cuParamSetf,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuFuncSetSharedSize(CUfunction hfunc, unsigned int bytes);
-
-/**
- * \brief Sets the parameter size for the function
- *
- * \deprecated
- *
- * Sets through \p numbytes the total size in bytes needed by the function
- * parameters of the kernel corresponding to \p hfunc.
- *
- * \param hfunc - Kernel to set parameter size for
- * \param numbytes - Size of parameter list in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetf,
- * ::cuParamSeti,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuParamSetSize(CUfunction hfunc, unsigned int numbytes);
-
-/**
- * \brief Adds an integer parameter to the function's argument list
- *
- * \deprecated
- *
- * Sets an integer parameter that will be specified the next time the
- * kernel corresponding to \p hfunc will be invoked. \p offset is a byte offset.
- *
- * \param hfunc - Kernel to add parameter to
- * \param offset - Offset to add parameter to argument list
- * \param value - Value of parameter
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSetf,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuParamSeti(CUfunction hfunc, int offset, unsigned int value);
-
-/**
- * \brief Adds a floating-point parameter to the function's argument list
- *
- * \deprecated
- *
- * Sets a floating-point parameter that will be specified the next time the
- * kernel corresponding to \p hfunc will be invoked. \p offset is a byte offset.
- *
- * \param hfunc - Kernel to add parameter to
- * \param offset - Offset to add parameter to argument list
- * \param value - Value of parameter
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSeti,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuParamSetf(CUfunction hfunc, int offset, float value);
-
-/**
- * \brief Adds arbitrary data to the function's argument list
- *
- * \deprecated
- *
- * Copies an arbitrary amount of data (specified in \p numbytes) from \p ptr
- * into the parameter space of the kernel corresponding to \p hfunc. \p offset
- * is a byte offset.
- *
- * \param hfunc - Kernel to add data to
- * \param offset - Offset to add data to argument list
- * \param ptr - Pointer to arbitrary data
- * \param numbytes - Size of data to copy in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSetf,
- * ::cuParamSeti,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuParamSetv(CUfunction hfunc, int offset, void *ptr, unsigned int numbytes);
-
-/**
- * \brief Launches a CUDA function
- *
- * \deprecated
- *
- * Invokes the kernel \p f on a 1 x 1 x 1 grid of blocks. The block
- * contains the number of threads specified by a previous call to
- * ::cuFuncSetBlockShape().
- *
- * \param f - Kernel to launch
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_LAUNCH_FAILED,
- * ::CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES,
- * ::CUDA_ERROR_LAUNCH_TIMEOUT,
- * ::CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSetf,
- * ::cuParamSeti,
- * ::cuParamSetv,
- * ::cuLaunchGrid,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuLaunch(CUfunction f);
-
-/**
- * \brief Launches a CUDA function
- *
- * \deprecated
- *
- * Invokes the kernel \p f on a \p grid_width x \p grid_height grid of
- * blocks. Each block contains the number of threads specified by a previous
- * call to ::cuFuncSetBlockShape().
- *
- * \param f - Kernel to launch
- * \param grid_width - Width of grid in blocks
- * \param grid_height - Height of grid in blocks
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_LAUNCH_FAILED,
- * ::CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES,
- * ::CUDA_ERROR_LAUNCH_TIMEOUT,
- * ::CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSetf,
- * ::cuParamSeti,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGridAsync,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuLaunchGrid(CUfunction f, int grid_width, int grid_height);
-
-/**
- * \brief Launches a CUDA function
- *
- * \deprecated
- *
- * Invokes the kernel \p f on a \p grid_width x \p grid_height grid of
- * blocks. Each block contains the number of threads specified by a previous
- * call to ::cuFuncSetBlockShape().
- *
- * \param f - Kernel to launch
- * \param grid_width - Width of grid in blocks
- * \param grid_height - Height of grid in blocks
- * \param hStream - Stream identifier
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_LAUNCH_FAILED,
- * ::CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES,
- * ::CUDA_ERROR_LAUNCH_TIMEOUT,
- * ::CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING,
- * ::CUDA_ERROR_SHARED_OBJECT_INIT_FAILED
- *
- * \note In certain cases where cubins are created with no ABI (i.e., using \p ptxas \p --abi-compile \p no), 
- * this function may serialize kernel launches. In order to force the CUDA driver to retain 
- *		 asynchronous behavior, set the ::CU_CTX_LMEM_RESIZE_TO_MAX flag during context creation (see ::cuCtxCreate).
- * 
- * \note_null_stream
- * \notefnerr
- *
- * \sa ::cuFuncSetBlockShape,
- * ::cuFuncSetSharedSize,
- * ::cuFuncGetAttribute,
- * ::cuParamSetSize,
- * ::cuParamSetf,
- * ::cuParamSeti,
- * ::cuParamSetv,
- * ::cuLaunch,
- * ::cuLaunchGrid,
- * ::cuLaunchKernel
- */
-CUresult CUDAAPI cuLaunchGridAsync(CUfunction f, int grid_width, int grid_height, CUstream hStream);
-
-
-/**
- * \brief Adds a texture-reference to the function's argument list
- *
- * \deprecated
- *
- * Makes the CUDA array or linear memory bound to the texture reference
- * \p hTexRef available to a device program as a texture. In this version of
- * CUDA, the texture-reference must be obtained via ::cuModuleGetTexRef() and
- * the \p texunit parameter must be set to ::CU_PARAM_TR_DEFAULT.
- *
- * \param hfunc - Kernel to add texture-reference to
- * \param texunit - Texture unit (must be ::CU_PARAM_TR_DEFAULT)
- * \param hTexRef - Texture-reference to add to argument list
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- */
-CUresult CUDAAPI cuParamSetTexRef(CUfunction hfunc, int texunit, CUtexref hTexRef);
-/** @} */ /* END CUDA_EXEC_DEPRECATED */
-
-
-#if __CUDA_API_VERSION >= 6050
-/**
- * \defgroup CUDA_OCCUPANCY Occupancy
- *
- * ___MANBRIEF___ occupancy calculation functions of the low-level CUDA driver
- * API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the occupancy calculation functions of the low-level CUDA
- * driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Returns occupancy of a function
- *
- * Returns in \p *numBlocks the number of the maximum active blocks per
- * streaming multiprocessor.
- *
- * \param numBlocks - Returned occupancy
- * \param func - Kernel for which occupancy is calculated
- * \param blockSize - Block size the kernel is intended to be launched with
- * \param dynamicSMemSize - Per-block dynamic shared memory usage intended, in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- */
-CUresult CUDAAPI cuOccupancyMaxActiveBlocksPerMultiprocessor(int *numBlocks, CUfunction func, int blockSize, size_t dynamicSMemSize);
-
-/**
- * \brief Returns occupancy of a function
- *
- * Returns in \p *numBlocks the number of the maximum active blocks per
- * streaming multiprocessor.
- *
- * The \p Flags parameter controls how special cases are handled. The
- * valid flags are:
- *
- * - ::CU_OCCUPANCY_DEFAULT, which maintains the default behavior as
- * ::cuOccupancyMaxActiveBlocksPerMultiprocessor;
- *
- * - ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the
- * default behavior on platform where global caching affects
- * occupancy. On such platforms, if caching is enabled, but
- * per-block SM resource usage would result in zero occupancy, the
- * occupancy calculator will calculate the occupancy as if caching
- * is disabled. Setting ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE makes
- * the occupancy calculator to return 0 in such cases. More information
- * can be found about this feature in the "Unified L1/Texture Cache"
- * section of the Maxwell tuning guide.
- *
- * \param numBlocks - Returned occupancy
- * \param func - Kernel for which occupancy is calculated
- * \param blockSize - Block size the kernel is intended to be launched with
- * \param dynamicSMemSize - Per-block dynamic shared memory usage intended, in bytes
- * \param flags - Requested behavior for the occupancy calculator
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- */
-CUresult CUDAAPI cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(int *numBlocks, CUfunction func, int blockSize, size_t dynamicSMemSize, unsigned int flags);
- 
-/**
- * \brief Suggest a launch configuration with reasonable occupancy
- *
- * Returns in \p *blockSize a reasonable block size that can achieve
- * the maximum occupancy (or, the maximum number of active warps with
- * the fewest blocks per multiprocessor), and in \p *minGridSize the
- * minimum grid size to achieve the maximum occupancy.
- *
- * If \p blockSizeLimit is 0, the configurator will use the maximum
- * block size permitted by the device / function instead.
- *
- * If per-block dynamic shared memory allocation is not needed, the
- * user should leave both \p blockSizeToDynamicSMemSize and \p
- * dynamicSMemSize as 0.
- *
- * If per-block dynamic shared memory allocation is needed, then if
- * the dynamic shared memory size is constant regardless of block
- * size, the size should be passed through \p dynamicSMemSize, and \p
- * blockSizeToDynamicSMemSize should be NULL.
- *
- * Otherwise, if the per-block dynamic shared memory size varies with
- * different block sizes, the user needs to provide a unary function
- * through \p blockSizeToDynamicSMemSize that computes the dynamic
- * shared memory needed by \p func for any given block size. \p
- * dynamicSMemSize is ignored. An example signature is:
- *
- * \code
- * // Take block size, returns dynamic shared memory needed
- * size_t blockToSmem(int blockSize);
- * \endcode
- *
- * \param minGridSize - Returned minimum grid size needed to achieve the maximum occupancy
- * \param blockSize - Returned maximum block size that can achieve the maximum occupancy
- * \param func - Kernel for which launch configuration is calculated
- * \param blockSizeToDynamicSMemSize - A function that calculates how much per-block dynamic shared memory \p func uses based on the block size
- * \param dynamicSMemSize - Dynamic shared memory usage intended, in bytes
- * \param blockSizeLimit - The maximum block size \p func is designed to handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- */
-CUresult CUDAAPI cuOccupancyMaxPotentialBlockSize(int *minGridSize, int *blockSize, CUfunction func, CUoccupancyB2DSize blockSizeToDynamicSMemSize, size_t dynamicSMemSize, int blockSizeLimit);
-
-/**
- * \brief Suggest a launch configuration with reasonable occupancy
- *
- * An extended version of ::cuOccupancyMaxPotentialBlockSize. In
- * addition to arguments passed to ::cuOccupancyMaxPotentialBlockSize,
- * ::cuOccupancyMaxPotentialBlockSizeWithFlags also takes a \p Flags
- * parameter.
- *
- * The \p Flags parameter controls how special cases are handled. The
- * valid flags are:
- *
- * - ::CU_OCCUPANCY_DEFAULT, which maintains the default behavior as
- * ::cuOccupancyMaxPotentialBlockSize;
- *
- * - ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the
- * default behavior on platform where global caching affects
- * occupancy. On such platforms, the launch configurations that
- * produces maximal occupancy might not support global
- * caching. Setting ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE
- * guarantees that the the produced launch configuration is global
- * caching compatible at a potential cost of occupancy. More information
- * can be found about this feature in the "Unified L1/Texture Cache"
- * section of the Maxwell tuning guide.
- *
- * \param minGridSize - Returned minimum grid size needed to achieve the maximum occupancy
- * \param blockSize - Returned maximum block size that can achieve the maximum occupancy
- * \param func - Kernel for which launch configuration is calculated
- * \param blockSizeToDynamicSMemSize - A function that calculates how much per-block dynamic shared memory \p func uses based on the block size
- * \param dynamicSMemSize - Dynamic shared memory usage intended, in bytes
- * \param blockSizeLimit - The maximum block size \p func is designed to handle
- * \param flags - Options
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- */
-CUresult CUDAAPI cuOccupancyMaxPotentialBlockSizeWithFlags(int *minGridSize, int *blockSize, CUfunction func, CUoccupancyB2DSize blockSizeToDynamicSMemSize, size_t dynamicSMemSize, int blockSizeLimit, unsigned int flags);
-
-/** @} */ /* END CUDA_OCCUPANCY */
-#endif /* __CUDA_API_VERSION >= 6050 */
-
-/**
- * \defgroup CUDA_TEXREF Texture Reference Management
- *
- * ___MANBRIEF___ texture reference management functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the texture reference management functions of the
- * low-level CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Binds an array as a texture reference
- *
- * Binds the CUDA array \p hArray to the texture reference \p hTexRef. Any
- * previous address or CUDA array state associated with the texture reference
- * is superseded by this function. \p Flags must be set to
- * ::CU_TRSA_OVERRIDE_FORMAT. Any CUDA array previously bound to \p hTexRef is
- * unbound.
- *
- * \param hTexRef - Texture reference to bind
- * \param hArray - Array to bind
- * \param Flags - Options (must be ::CU_TRSA_OVERRIDE_FORMAT)
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetArray(CUtexref hTexRef, CUarray hArray, unsigned int Flags);
-
-/**
- * \brief Binds a mipmapped array to a texture reference
- *
- * Binds the CUDA mipmapped array \p hMipmappedArray to the texture reference \p hTexRef.
- * Any previous address or CUDA array state associated with the texture reference
- * is superseded by this function. \p Flags must be set to ::CU_TRSA_OVERRIDE_FORMAT. 
- * Any CUDA array previously bound to \p hTexRef is unbound.
- *
- * \param hTexRef - Texture reference to bind
- * \param hMipmappedArray - Mipmapped array to bind
- * \param Flags - Options (must be ::CU_TRSA_OVERRIDE_FORMAT)
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetMipmappedArray(CUtexref hTexRef, CUmipmappedArray hMipmappedArray, unsigned int Flags);
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Binds an address as a texture reference
- *
- * Binds a linear address range to the texture reference \p hTexRef. Any
- * previous address or CUDA array state associated with the texture reference
- * is superseded by this function. Any memory previously bound to \p hTexRef
- * is unbound.
- *
- * Since the hardware enforces an alignment requirement on texture base
- * addresses, ::cuTexRefSetAddress() passes back a byte offset in
- * \p *ByteOffset that must be applied to texture fetches in order to read from
- * the desired memory. This offset must be divided by the texel size and
- * passed to kernels that read from the texture so they can be applied to the
- * ::tex1Dfetch() function.
- *
- * If the device memory pointer was returned from ::cuMemAlloc(), the offset
- * is guaranteed to be 0 and NULL may be passed as the \p ByteOffset parameter.
- *
- * The total number of elements (or texels) in the linear address range
- * cannot exceed ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH.
- * The number of elements is computed as (\p bytes / bytesPerElement),
- * where bytesPerElement is determined from the data format and number of 
- * components set using ::cuTexRefSetFormat().
- *
- * \param ByteOffset - Returned byte offset
- * \param hTexRef - Texture reference to bind
- * \param dptr - Device pointer to bind
- * \param bytes - Size of memory to bind in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetAddress(size_t *ByteOffset, CUtexref hTexRef, CUdeviceptr dptr, size_t bytes);
-
-/**
- * \brief Binds an address as a 2D texture reference
- *
- * Binds a linear address range to the texture reference \p hTexRef. Any
- * previous address or CUDA array state associated with the texture reference
- * is superseded by this function. Any memory previously bound to \p hTexRef
- * is unbound.
- *
- * Using a ::tex2D() function inside a kernel requires a call to either
- * ::cuTexRefSetArray() to bind the corresponding texture reference to an
- * array, or ::cuTexRefSetAddress2D() to bind the texture reference to linear
- * memory.
- *
- * Function calls to ::cuTexRefSetFormat() cannot follow calls to
- * ::cuTexRefSetAddress2D() for the same texture reference.
- *
- * It is required that \p dptr be aligned to the appropriate hardware-specific
- * texture alignment. You can query this value using the device attribute
- * ::CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT. If an unaligned \p dptr is
- * supplied, ::CUDA_ERROR_INVALID_VALUE is returned.
- *
- * \p Pitch has to be aligned to the hardware-specific texture pitch alignment.
- * This value can be queried using the device attribute 
- * ::CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. If an unaligned \p Pitch is 
- * supplied, ::CUDA_ERROR_INVALID_VALUE is returned.
- *
- * Width and Height, which are specified in elements (or texels), cannot exceed
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH and
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT respectively.
- * \p Pitch, which is specified in bytes, cannot exceed 
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH.
- *
- * \param hTexRef - Texture reference to bind
- * \param desc - Descriptor of CUDA array
- * \param dptr - Device pointer to bind
- * \param Pitch - Line pitch in bytes
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetAddress2D(CUtexref hTexRef, const CUDA_ARRAY_DESCRIPTOR *desc, CUdeviceptr dptr, size_t Pitch);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Sets the format for a texture reference
- *
- * Specifies the format of the data to be read by the texture reference
- * \p hTexRef. \p fmt and \p NumPackedComponents are exactly analogous to the
- * ::Format and ::NumChannels members of the ::CUDA_ARRAY_DESCRIPTOR structure:
- * They specify the format of each component and the number of components per
- * array element.
- *
- * \param hTexRef - Texture reference
- * \param fmt - Format to set
- * \param NumPackedComponents - Number of components per array element
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetFormat(CUtexref hTexRef, CUarray_format fmt, int NumPackedComponents);
-
-/**
- * \brief Sets the addressing mode for a texture reference
- *
- * Specifies the addressing mode \p am for the given dimension \p dim of the
- * texture reference \p hTexRef. If \p dim is zero, the addressing mode is
- * applied to the first parameter of the functions used to fetch from the
- * texture; if \p dim is 1, the second, and so on. ::CUaddress_mode is defined
- * as:
- * \code
- typedef enum CUaddress_mode_enum {
- CU_TR_ADDRESS_MODE_WRAP = 0,
- CU_TR_ADDRESS_MODE_CLAMP = 1,
- CU_TR_ADDRESS_MODE_MIRROR = 2,
- CU_TR_ADDRESS_MODE_BORDER = 3
- } CUaddress_mode;
- * \endcode
- *
- * Note that this call has no effect if \p hTexRef is bound to linear memory.
- * Also, if the flag, ::CU_TRSF_NORMALIZED_COORDINATES, is not set, the only 
- * supported address mode is ::CU_TR_ADDRESS_MODE_CLAMP.
- *
- * \param hTexRef - Texture reference
- * \param dim - Dimension
- * \param am - Addressing mode to set
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetAddressMode(CUtexref hTexRef, int dim, CUaddress_mode am);
-
-/**
- * \brief Sets the filtering mode for a texture reference
- *
- * Specifies the filtering mode \p fm to be used when reading memory through
- * the texture reference \p hTexRef. ::CUfilter_mode_enum is defined as:
- *
- * \code
- typedef enum CUfilter_mode_enum {
- CU_TR_FILTER_MODE_POINT = 0,
- CU_TR_FILTER_MODE_LINEAR = 1
- } CUfilter_mode;
- * \endcode
- *
- * Note that this call has no effect if \p hTexRef is bound to linear memory.
- *
- * \param hTexRef - Texture reference
- * \param fm - Filtering mode to set
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetFilterMode(CUtexref hTexRef, CUfilter_mode fm);
-
-/**
- * \brief Sets the mipmap filtering mode for a texture reference
- *
- * Specifies the mipmap filtering mode \p fm to be used when reading memory through
- * the texture reference \p hTexRef. ::CUfilter_mode_enum is defined as:
- *
- * \code
- typedef enum CUfilter_mode_enum {
- CU_TR_FILTER_MODE_POINT = 0,
- CU_TR_FILTER_MODE_LINEAR = 1
- } CUfilter_mode;
- * \endcode
- *
- * Note that this call has no effect if \p hTexRef is not bound to a mipmapped array.
- *
- * \param hTexRef - Texture reference
- * \param fm - Filtering mode to set
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetMipmapFilterMode(CUtexref hTexRef, CUfilter_mode fm);
-
-/**
- * \brief Sets the mipmap level bias for a texture reference
- *
- * Specifies the mipmap level bias \p bias to be added to the specified mipmap level when 
- * reading memory through the texture reference \p hTexRef.
- *
- * Note that this call has no effect if \p hTexRef is not bound to a mipmapped array.
- *
- * \param hTexRef - Texture reference
- * \param bias - Mipmap level bias
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetMipmapLevelBias(CUtexref hTexRef, float bias);
-
-/**
- * \brief Sets the mipmap min/max mipmap level clamps for a texture reference
- *
- * Specifies the min/max mipmap level clamps, \p minMipmapLevelClamp and \p maxMipmapLevelClamp
- * respectively, to be used when reading memory through the texture reference 
- * \p hTexRef.
- *
- * Note that this call has no effect if \p hTexRef is not bound to a mipmapped array.
- *
- * \param hTexRef - Texture reference
- * \param minMipmapLevelClamp - Mipmap min level clamp
- * \param maxMipmapLevelClamp - Mipmap max level clamp
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetMipmapLevelClamp(CUtexref hTexRef, float minMipmapLevelClamp, float maxMipmapLevelClamp);
-
-/**
- * \brief Sets the maximum anisotropy for a texture reference
- *
- * Specifies the maximum anisotropy \p maxAniso to be used when reading memory through
- * the texture reference \p hTexRef. 
- *
- * Note that this call has no effect if \p hTexRef is bound to linear memory.
- *
- * \param hTexRef - Texture reference
- * \param maxAniso - Maximum anisotropy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetMaxAnisotropy(CUtexref hTexRef, unsigned int maxAniso);
-
-/**
- * \brief Sets the flags for a texture reference
- *
- * Specifies optional flags via \p Flags to specify the behavior of data
- * returned through the texture reference \p hTexRef. The valid flags are:
- *
- * - ::CU_TRSF_READ_AS_INTEGER, which suppresses the default behavior of
- * having the texture promote integer data to floating point data in the
- * range [0, 1]. Note that texture with 32-bit integer format
- * would not be promoted, regardless of whether or not this
- * flag is specified;
- * - ::CU_TRSF_NORMALIZED_COORDINATES, which suppresses the 
- * default behavior of having the texture coordinates range
- * from [0, Dim) where Dim is the width or height of the CUDA
- * array. Instead, the texture coordinates [0, 1.0) reference
- * the entire breadth of the array dimension;
- *
- * \param hTexRef - Texture reference
- * \param Flags - Optional flags to set
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefSetFlags(CUtexref hTexRef, unsigned int Flags);
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Gets the address associated with a texture reference
- *
- * Returns in \p *pdptr the base address bound to the texture reference
- * \p hTexRef, or returns ::CUDA_ERROR_INVALID_VALUE if the texture reference
- * is not bound to any device memory range.
- *
- * \param pdptr - Returned device address
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetAddress(CUdeviceptr *pdptr, CUtexref hTexRef);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Gets the array bound to a texture reference
- *
- * Returns in \p *phArray the CUDA array bound to the texture reference
- * \p hTexRef, or returns ::CUDA_ERROR_INVALID_VALUE if the texture reference
- * is not bound to any CUDA array.
- *
- * \param phArray - Returned array
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetArray(CUarray *phArray, CUtexref hTexRef);
-
-/**
- * \brief Gets the mipmapped array bound to a texture reference
- *
- * Returns in \p *phMipmappedArray the CUDA mipmapped array bound to the texture 
- * reference \p hTexRef, or returns ::CUDA_ERROR_INVALID_VALUE if the texture reference
- * is not bound to any CUDA mipmapped array.
- *
- * \param phMipmappedArray - Returned mipmapped array
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetMipmappedArray(CUmipmappedArray *phMipmappedArray, CUtexref hTexRef);
-
-/**
- * \brief Gets the addressing mode used by a texture reference
- *
- * Returns in \p *pam the addressing mode corresponding to the
- * dimension \p dim of the texture reference \p hTexRef. Currently, the only
- * valid value for \p dim are 0 and 1.
- *
- * \param pam - Returned addressing mode
- * \param hTexRef - Texture reference
- * \param dim - Dimension
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetAddressMode(CUaddress_mode *pam, CUtexref hTexRef, int dim);
-
-/**
- * \brief Gets the filter-mode used by a texture reference
- *
- * Returns in \p *pfm the filtering mode of the texture reference
- * \p hTexRef.
- *
- * \param pfm - Returned filtering mode
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetFilterMode(CUfilter_mode *pfm, CUtexref hTexRef);
-
-/**
- * \brief Gets the format used by a texture reference
- *
- * Returns in \p *pFormat and \p *pNumChannels the format and number
- * of components of the CUDA array bound to the texture reference \p hTexRef.
- * If \p pFormat or \p pNumChannels is NULL, it will be ignored.
- *
- * \param pFormat - Returned format
- * \param pNumChannels - Returned number of components
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags
- */
-CUresult CUDAAPI cuTexRefGetFormat(CUarray_format *pFormat, int *pNumChannels, CUtexref hTexRef);
-
-/**
- * \brief Gets the mipmap filtering mode for a texture reference
- *
- * Returns the mipmap filtering mode in \p pfm that's used when reading memory through
- * the texture reference \p hTexRef.
- *
- * \param pfm - Returned mipmap filtering mode
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetMipmapFilterMode(CUfilter_mode *pfm, CUtexref hTexRef);
-
-/**
- * \brief Gets the mipmap level bias for a texture reference
- *
- * Returns the mipmap level bias in \p pBias that's added to the specified mipmap
- * level when reading memory through the texture reference \p hTexRef.
- *
- * \param pbias - Returned mipmap level bias
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetMipmapLevelBias(float *pbias, CUtexref hTexRef);
-
-/**
- * \brief Gets the min/max mipmap level clamps for a texture reference
- *
- * Returns the min/max mipmap level clamps in \p pminMipmapLevelClamp and \p pmaxMipmapLevelClamp
- * that's used when reading memory through the texture reference \p hTexRef. 
- *
- * \param pminMipmapLevelClamp - Returned mipmap min level clamp
- * \param pmaxMipmapLevelClamp - Returned mipmap max level clamp
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetMipmapLevelClamp(float *pminMipmapLevelClamp, float *pmaxMipmapLevelClamp, CUtexref hTexRef);
-
-/**
- * \brief Gets the maximum anisotropy for a texture reference
- *
- * Returns the maximum anisotropy in \p pmaxAniso that's used when reading memory through
- * the texture reference \p hTexRef. 
- *
- * \param pmaxAniso - Returned maximum anisotropy
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFlags, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetMaxAnisotropy(int *pmaxAniso, CUtexref hTexRef);
-
-/**
- * \brief Gets the flags used by a texture reference
- *
- * Returns in \p *pFlags the flags of the texture reference \p hTexRef.
- *
- * \param pFlags - Returned flags
- * \param hTexRef - Texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefSetAddress,
- * ::cuTexRefSetAddress2D, ::cuTexRefSetAddressMode, ::cuTexRefSetArray,
- * ::cuTexRefSetFilterMode, ::cuTexRefSetFlags, ::cuTexRefSetFormat,
- * ::cuTexRefGetAddress, ::cuTexRefGetAddressMode, ::cuTexRefGetArray,
- * ::cuTexRefGetFilterMode, ::cuTexRefGetFormat
- */
-CUresult CUDAAPI cuTexRefGetFlags(unsigned int *pFlags, CUtexref hTexRef);
-
-/** @} */ /* END CUDA_TEXREF */
-
-/**
- * \defgroup CUDA_TEXREF_DEPRECATED Texture Reference Management [DEPRECATED]
- *
- * ___MANBRIEF___ deprecated texture reference management functions of the
- * low-level CUDA driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the deprecated texture reference management
- * functions of the low-level CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Creates a texture reference
- *
- * \deprecated
- *
- * Creates a texture reference and returns its handle in \p *pTexRef. Once
- * created, the application must call ::cuTexRefSetArray() or
- * ::cuTexRefSetAddress() to associate the reference with allocated memory.
- * Other texture reference functions are used to specify the format and
- * interpretation (addressing, filtering, etc.) to be used when the memory is
- * read through this texture reference.
- *
- * \param pTexRef - Returned texture reference
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefDestroy
- */
-CUresult CUDAAPI cuTexRefCreate(CUtexref *pTexRef);
-
-/**
- * \brief Destroys a texture reference
- *
- * \deprecated
- *
- * Destroys the texture reference specified by \p hTexRef.
- *
- * \param hTexRef - Texture reference to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexRefCreate
- */
-CUresult CUDAAPI cuTexRefDestroy(CUtexref hTexRef);
-
-/** @} */ /* END CUDA_TEXREF_DEPRECATED */
-
-
-/**
- * \defgroup CUDA_SURFREF Surface Reference Management
- *
- * ___MANBRIEF___ surface reference management functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the surface reference management functions of the
- * low-level CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Sets the CUDA array for a surface reference.
- *
- * Sets the CUDA array \p hArray to be read and written by the surface reference
- * \p hSurfRef. Any previous CUDA array state associated with the surface
- * reference is superseded by this function. \p Flags must be set to 0.
- * The ::CUDA_ARRAY3D_SURFACE_LDST flag must have been set for the CUDA array.
- * Any CUDA array previously bound to \p hSurfRef is unbound.
-
- * \param hSurfRef - Surface reference handle
- * \param hArray - CUDA array handle
- * \param Flags - set to 0
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuModuleGetSurfRef, ::cuSurfRefGetArray
- */
-CUresult CUDAAPI cuSurfRefSetArray(CUsurfref hSurfRef, CUarray hArray, unsigned int Flags);
-
-/**
- * \brief Passes back the CUDA array bound to a surface reference.
- *
- * Returns in \p *phArray the CUDA array bound to the surface reference
- * \p hSurfRef, or returns ::CUDA_ERROR_INVALID_VALUE if the surface reference
- * is not bound to any CUDA array.
-
- * \param phArray - Surface reference handle
- * \param hSurfRef - Surface reference handle
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuModuleGetSurfRef, ::cuSurfRefSetArray
- */
-CUresult CUDAAPI cuSurfRefGetArray(CUarray *phArray, CUsurfref hSurfRef);
-
-/** @} */ /* END CUDA_SURFREF */
-
-#if __CUDA_API_VERSION >= 5000
-/**
- * \defgroup CUDA_TEXOBJECT Texture Object Management
- *
- * ___MANBRIEF___ texture object management functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the texture object management functions of the
- * low-level CUDA driver application programming interface. The texture
- * object API is only supported on devices of compute capability 3.0 or higher.
- *
- * @{
- */
-
-/**
- * \brief Creates a texture object
- *
- * Creates a texture object and returns it in \p pTexObject. \p pResDesc describes
- * the data to texture from. \p pTexDesc describes how the data should be sampled.
- * \p pResViewDesc is an optional argument that specifies an alternate format for
- * the data described by \p pResDesc, and also describes the subresource region
- * to restrict access to when texturing. \p pResViewDesc can only be specified if
- * the type of resource is a CUDA array or a CUDA mipmapped array.
- *
- * Texture objects are only supported on devices of compute capability 3.0 or higher.
- * Additionally, a texture object is an opaque value, and, as such, should only be
- * accessed through CUDA API calls.
- *
- * The ::CUDA_RESOURCE_DESC structure is defined as:
- * \code
- typedef struct CUDA_RESOURCE_DESC_st
- {
- CUresourcetype resType;
-
- union {
- struct {
- CUarray hArray;
- } array;
- struct {
- CUmipmappedArray hMipmappedArray;
- } mipmap;
- struct {
- CUdeviceptr devPtr;
- CUarray_format format;
- unsigned int numChannels;
- size_t sizeInBytes;
- } linear;
- struct {
- CUdeviceptr devPtr;
- CUarray_format format;
- unsigned int numChannels;
- size_t width;
- size_t height;
- size_t pitchInBytes;
- } pitch2D;
- } res;
-
- unsigned int flags;
- } CUDA_RESOURCE_DESC;
-
- * \endcode
- * where:
- * - ::CUDA_RESOURCE_DESC::resType specifies the type of resource to texture from.
- * CUresourceType is defined as:
- * \code
- typedef enum CUresourcetype_enum {
- CU_RESOURCE_TYPE_ARRAY = 0x00,
- CU_RESOURCE_TYPE_MIPMAPPED_ARRAY = 0x01,
- CU_RESOURCE_TYPE_LINEAR = 0x02,
- CU_RESOURCE_TYPE_PITCH2D = 0x03
- } CUresourcetype;
- * \endcode
- *
- * \par
- * If ::CUDA_RESOURCE_DESC::resType is set to ::CU_RESOURCE_TYPE_ARRAY, ::CUDA_RESOURCE_DESC::res::array::hArray
- * must be set to a valid CUDA array handle.
- *
- * \par
- * If ::CUDA_RESOURCE_DESC::resType is set to ::CU_RESOURCE_TYPE_MIPMAPPED_ARRAY, ::CUDA_RESOURCE_DESC::res::mipmap::hMipmappedArray
- * must be set to a valid CUDA mipmapped array handle.
- *
- * \par
- * If ::CUDA_RESOURCE_DESC::resType is set to ::CU_RESOURCE_TYPE_LINEAR, ::CUDA_RESOURCE_DESC::res::linear::devPtr
- * must be set to a valid device pointer, that is aligned to ::CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT.
- * ::CUDA_RESOURCE_DESC::res::linear::format and ::CUDA_RESOURCE_DESC::res::linear::numChannels
- * describe the format of each component and the number of components per array element. ::CUDA_RESOURCE_DESC::res::linear::sizeInBytes
- * specifies the size of the array in bytes. The total number of elements in the linear address range cannot exceed 
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LINEAR_WIDTH. The number of elements is computed as (sizeInBytes / (sizeof(format) * numChannels)).
- *
- * \par
- * If ::CUDA_RESOURCE_DESC::resType is set to ::CU_RESOURCE_TYPE_PITCH2D, ::CUDA_RESOURCE_DESC::res::pitch2D::devPtr
- * must be set to a valid device pointer, that is aligned to ::CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT.
- * ::CUDA_RESOURCE_DESC::res::pitch2D::format and ::CUDA_RESOURCE_DESC::res::pitch2D::numChannels
- * describe the format of each component and the number of components per array element. ::CUDA_RESOURCE_DESC::res::pitch2D::width
- * and ::CUDA_RESOURCE_DESC::res::pitch2D::height specify the width and height of the array in elements, and cannot exceed
- * ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_WIDTH and ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_HEIGHT respectively.
- * ::CUDA_RESOURCE_DESC::res::pitch2D::pitchInBytes specifies the pitch between two rows in bytes and has to be aligned to 
- * ::CU_DEVICE_ATTRIBUTE_TEXTURE_PITCH_ALIGNMENT. Pitch cannot exceed ::CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_LINEAR_PITCH.
- *
- * - ::flags must be set to zero.
- *
- *
- * The ::CUDA_TEXTURE_DESC struct is defined as
- * \code
- typedef struct CUDA_TEXTURE_DESC_st {
- CUaddress_mode addressMode[3];
- CUfilter_mode filterMode;
- unsigned int flags;
- unsigned int maxAnisotropy;
- CUfilter_mode mipmapFilterMode;
- float mipmapLevelBias;
- float minMipmapLevelClamp;
- float maxMipmapLevelClamp;
- } CUDA_TEXTURE_DESC;
- * \endcode
- * where
- * - ::CUDA_TEXTURE_DESC::addressMode specifies the addressing mode for each dimension of the texture data. ::CUaddress_mode is defined as:
- * \code
- typedef enum CUaddress_mode_enum {
- CU_TR_ADDRESS_MODE_WRAP = 0,
- CU_TR_ADDRESS_MODE_CLAMP = 1,
- CU_TR_ADDRESS_MODE_MIRROR = 2,
- CU_TR_ADDRESS_MODE_BORDER = 3
- } CUaddress_mode;
- * \endcode
- * This is ignored if ::CUDA_RESOURCE_DESC::resType is ::CU_RESOURCE_TYPE_LINEAR. Also, if the flag, ::CU_TRSF_NORMALIZED_COORDINATES 
- * is not set, the only supported address mode is ::CU_TR_ADDRESS_MODE_CLAMP.
- *
- * - ::CUDA_TEXTURE_DESC::filterMode specifies the filtering mode to be used when fetching from the texture. CUfilter_mode is defined as:
- * \code
- typedef enum CUfilter_mode_enum {
- CU_TR_FILTER_MODE_POINT = 0,
- CU_TR_FILTER_MODE_LINEAR = 1
- } CUfilter_mode;
- * \endcode
- * This is ignored if ::CUDA_RESOURCE_DESC::resType is ::CU_RESOURCE_TYPE_LINEAR.
- *
- * - ::CUDA_TEXTURE_DESC::flags can be any combination of the following:
- * - ::CU_TRSF_READ_AS_INTEGER, which suppresses the default behavior of having the texture promote integer data to floating point data in the
- * range [0, 1]. Note that texture with 32-bit integer format would not be promoted, regardless of whether or not this flag is specified.
- * - ::CU_TRSF_NORMALIZED_COORDINATES, which suppresses the default behavior of having the texture coordinates range from [0, Dim) where Dim is
- * the width or height of the CUDA array. Instead, the texture coordinates [0, 1.0) reference the entire breadth of the array dimension; Note
- * that for CUDA mipmapped arrays, this flag has to be set.
- *
- * - ::CUDA_TEXTURE_DESC::maxAnisotropy specifies the maximum anisotropy ratio to be used when doing anisotropic filtering. This value will be
- * clamped to the range [1,16].
- *
- * - ::CUDA_TEXTURE_DESC::mipmapFilterMode specifies the filter mode when the calculated mipmap level lies between two defined mipmap levels.
- *
- * - ::CUDA_TEXTURE_DESC::mipmapLevelBias specifies the offset to be applied to the calculated mipmap level.
- *
- * - ::CUDA_TEXTURE_DESC::minMipmapLevelClamp specifies the lower end of the mipmap level range to clamp access to.
- *
- * - ::CUDA_TEXTURE_DESC::maxMipmapLevelClamp specifies the upper end of the mipmap level range to clamp access to.
- *
- *
- * The ::CUDA_RESOURCE_VIEW_DESC struct is defined as
- * \code
- typedef struct CUDA_RESOURCE_VIEW_DESC_st
- {
- CUresourceViewFormat format;
- size_t width;
- size_t height;
- size_t depth;
- unsigned int firstMipmapLevel;
- unsigned int lastMipmapLevel;
- unsigned int firstLayer;
- unsigned int lastLayer;
- } CUDA_RESOURCE_VIEW_DESC;
- * \endcode
- * where:
- * - ::CUDA_RESOURCE_VIEW_DESC::format specifies how the data contained in the CUDA array or CUDA mipmapped array should
- * be interpreted. Note that this can incur a change in size of the texture data. If the resource view format is a block
- * compressed format, then the underlying CUDA array or CUDA mipmapped array has to have a base of format ::CU_AD_FORMAT_UNSIGNED_INT32.
- * with 2 or 4 channels, depending on the block compressed format. For ex., BC1 and BC4 require the underlying CUDA array to have
- * a format of ::CU_AD_FORMAT_UNSIGNED_INT32 with 2 channels. The other BC formats require the underlying resource to have the same base
- * format but with 4 channels.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::width specifies the new width of the texture data. If the resource view format is a block
- * compressed format, this value has to be 4 times the original width of the resource. For non block compressed formats,
- * this value has to be equal to that of the original resource.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::height specifies the new height of the texture data. If the resource view format is a block
- * compressed format, this value has to be 4 times the original height of the resource. For non block compressed formats,
- * this value has to be equal to that of the original resource.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::depth specifies the new depth of the texture data. This value has to be equal to that of the
- * original resource.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::firstMipmapLevel specifies the most detailed mipmap level. This will be the new mipmap level zero.
- * For non-mipmapped resources, this value has to be zero.::CUDA_TEXTURE_DESC::minMipmapLevelClamp and ::CUDA_TEXTURE_DESC::maxMipmapLevelClamp
- * will be relative to this value. For ex., if the firstMipmapLevel is set to 2, and a minMipmapLevelClamp of 1.2 is specified,
- * then the actual minimum mipmap level clamp will be 3.2.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::lastMipmapLevel specifies the least detailed mipmap level. For non-mipmapped resources, this value
- * has to be zero.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::firstLayer specifies the first layer index for layered textures. This will be the new layer zero.
- * For non-layered resources, this value has to be zero.
- *
- * - ::CUDA_RESOURCE_VIEW_DESC::lastLayer specifies the last layer index for layered textures. For non-layered resources, 
- * this value has to be zero.
- *
- *
- * \param pTexObject - Texture object to create
- * \param pResDesc - Resource descriptor
- * \param pTexDesc - Texture descriptor
- * \param pResViewDesc - Resource view descriptor 
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexObjectDestroy
- */
-CUresult CUDAAPI cuTexObjectCreate(CUtexObject *pTexObject, const CUDA_RESOURCE_DESC *pResDesc, const CUDA_TEXTURE_DESC *pTexDesc, const CUDA_RESOURCE_VIEW_DESC *pResViewDesc);
-
-/**
- * \brief Destroys a texture object
- *
- * Destroys the texture object specified by \p texObject.
- *
- * \param texObject - Texture object to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexObjectCreate
- */
-CUresult CUDAAPI cuTexObjectDestroy(CUtexObject texObject);
-
-/**
- * \brief Returns a texture object's resource descriptor
- *
- * Returns the resource descriptor for the texture object specified by \p texObject.
- *
- * \param pResDesc - Resource descriptor
- * \param texObject - Texture object
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexObjectCreate
- */
-CUresult CUDAAPI cuTexObjectGetResourceDesc(CUDA_RESOURCE_DESC *pResDesc, CUtexObject texObject);
-
-/**
- * \brief Returns a texture object's texture descriptor
- *
- * Returns the texture descriptor for the texture object specified by \p texObject.
- *
- * \param pTexDesc - Texture descriptor
- * \param texObject - Texture object
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexObjectCreate
- */
-CUresult CUDAAPI cuTexObjectGetTextureDesc(CUDA_TEXTURE_DESC *pTexDesc, CUtexObject texObject);
-
-/**
- * \brief Returns a texture object's resource view descriptor
- *
- * Returns the resource view descriptor for the texture object specified by \p texObject.
- * If no resource view was set for \p texObject, the ::CUDA_ERROR_INVALID_VALUE is returned.
- *
- * \param pResViewDesc - Resource view descriptor
- * \param texObject - Texture object
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuTexObjectCreate
- */
-CUresult CUDAAPI cuTexObjectGetResourceViewDesc(CUDA_RESOURCE_VIEW_DESC *pResViewDesc, CUtexObject texObject);
-
-/** @} */ /* END CUDA_TEXOBJECT */
-
-/**
- * \defgroup CUDA_SURFOBJECT Surface Object Management
- *
- * ___MANBRIEF___ surface object management functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the surface object management functions of the
- * low-level CUDA driver application programming interface. The surface
- * object API is only supported on devices of compute capability 3.0 or higher.
- *
- * @{
- */
-
-/**
- * \brief Creates a surface object
- *
- * Creates a surface object and returns it in \p pSurfObject. \p pResDesc describes
- * the data to perform surface load/stores on. ::CUDA_RESOURCE_DESC::resType must be 
- * ::CU_RESOURCE_TYPE_ARRAY and ::CUDA_RESOURCE_DESC::res::array::hArray
- * must be set to a valid CUDA array handle. ::CUDA_RESOURCE_DESC::flags must be set to zero.
- *
- * Surface objects are only supported on devices of compute capability 3.0 or higher.
- * Additionally, a surface object is an opaque value, and, as such, should only be
- * accessed through CUDA API calls.
- *
- * \param pSurfObject - Surface object to create
- * \param pResDesc - Resource descriptor
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuSurfObjectDestroy
- */
-CUresult CUDAAPI cuSurfObjectCreate(CUsurfObject *pSurfObject, const CUDA_RESOURCE_DESC *pResDesc);
-
-/**
- * \brief Destroys a surface object
- *
- * Destroys the surface object specified by \p surfObject.
- *
- * \param surfObject - Surface object to destroy
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuSurfObjectCreate
- */
-CUresult CUDAAPI cuSurfObjectDestroy(CUsurfObject surfObject);
-
-/**
- * \brief Returns a surface object's resource descriptor
- *
- * Returns the resource descriptor for the surface object specified by \p surfObject.
- *
- * \param pResDesc - Resource descriptor
- * \param surfObject - Surface object
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE
- *
- * \sa ::cuSurfObjectCreate
- */
-CUresult CUDAAPI cuSurfObjectGetResourceDesc(CUDA_RESOURCE_DESC *pResDesc, CUsurfObject surfObject);
-
-/** @} */ /* END CUDA_SURFOBJECT */
-#endif /* __CUDA_API_VERSION >= 5000 */
-
-#if __CUDA_API_VERSION >= 4000
-/**
- * \defgroup CUDA_PEER_ACCESS Peer Context Memory Access
- *
- * ___MANBRIEF___ direct peer context memory access functions of the low-level
- * CUDA driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the direct peer context memory access functions 
- * of the low-level CUDA driver application programming interface.
- *
- * @{
- */
- 
-/**
- * \brief Queries if a device may directly access a peer device's memory.
- *
- * Returns in \p *canAccessPeer a value of 1 if contexts on \p dev are capable of
- * directly accessing memory from contexts on \p peerDev and 0 otherwise.
- * If direct access of \p peerDev from \p dev is possible, then access may be
- * enabled on two specific contexts by calling ::cuCtxEnablePeerAccess().
- *
- * \param canAccessPeer - Returned access capability
- * \param dev - Device from which allocations on \p peerDev are to
- * be directly accessed.
- * \param peerDev - Device on which the allocations to be directly accessed 
- * by \p dev reside.
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_DEVICE
- * \notefnerr
- *
- * \sa ::cuCtxEnablePeerAccess,
- * ::cuCtxDisablePeerAccess
- */
-CUresult CUDAAPI cuDeviceCanAccessPeer(int *canAccessPeer, CUdevice dev, CUdevice peerDev);
-
-/**
- * \brief Enables direct access to memory allocations in a peer context.
- *
- * If both the current context and \p peerContext are on devices which support unified
- * addressing (as may be queried using ::CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING) and same
- * major compute capability, then on success all allocations from \p peerContext will
- * immediately be accessible by the current context. See \ref CUDA_UNIFIED for additional
- * details.
- *
- * Note that access granted by this call is unidirectional and that in order to access
- * memory from the current context in \p peerContext, a separate symmetric call 
- * to ::cuCtxEnablePeerAccess() is required.
- *
- * There is a system-wide maximum of eight peer connections per device.
- *
- * Returns ::CUDA_ERROR_PEER_ACCESS_UNSUPPORTED if ::cuDeviceCanAccessPeer() indicates
- * that the ::CUdevice of the current context cannot directly access memory
- * from the ::CUdevice of \p peerContext.
- *
- * Returns ::CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED if direct access of
- * \p peerContext from the current context has already been enabled.
- *
- * Returns ::CUDA_ERROR_TOO_MANY_PEERS if direct peer access is not possible 
- * because hardware resources required for peer access have been exhausted.
- *
- * Returns ::CUDA_ERROR_INVALID_CONTEXT if there is no current context, \p peerContext
- * is not a valid context, or if the current context is \p peerContext.
- *
- * Returns ::CUDA_ERROR_INVALID_VALUE if \p Flags is not 0.
- *
- * \param peerContext - Peer context to enable direct access to from the current context
- * \param Flags - Reserved for future use and must be set to 0
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED,
- * ::CUDA_ERROR_TOO_MANY_PEERS,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_PEER_ACCESS_UNSUPPORTED,
- * ::CUDA_ERROR_INVALID_VALUE
- * \notefnerr
- *
- * \sa ::cuDeviceCanAccessPeer,
- * ::cuCtxDisablePeerAccess
- */
-CUresult CUDAAPI cuCtxEnablePeerAccess(CUcontext peerContext, unsigned int Flags);
-
-/**
- * \brief Disables direct access to memory allocations in a peer context and 
- * unregisters any registered allocations.
- *
- Returns ::CUDA_ERROR_PEER_ACCESS_NOT_ENABLED if direct peer access has 
- * not yet been enabled from \p peerContext to the current context.
- *
- * Returns ::CUDA_ERROR_INVALID_CONTEXT if there is no current context, or if
- * \p peerContext is not a valid context.
- *
- * \param peerContext - Peer context to disable direct access to
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_PEER_ACCESS_NOT_ENABLED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * \notefnerr
- *
- * \sa ::cuDeviceCanAccessPeer,
- * ::cuCtxEnablePeerAccess
- */
-CUresult CUDAAPI cuCtxDisablePeerAccess(CUcontext peerContext);
-
-/** @} */ /* END CUDA_PEER_ACCESS */
-#endif /* __CUDA_API_VERSION >= 4000 */
-
-/**
- * \defgroup CUDA_GRAPHICS Graphics Interoperability
- *
- * ___MANBRIEF___ graphics interoperability functions of the low-level CUDA
- * driver API (___CURRENT_FILE___) ___ENDMANBRIEF___
- *
- * This section describes the graphics interoperability functions of the
- * low-level CUDA driver application programming interface.
- *
- * @{
- */
-
-/**
- * \brief Unregisters a graphics resource for access by CUDA
- *
- * Unregisters the graphics resource \p resource so it is not accessible by
- * CUDA unless registered again.
- *
- * If \p resource is invalid then ::CUDA_ERROR_INVALID_HANDLE is
- * returned.
- *
- * \param resource - Resource to unregister
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_UNKNOWN
- * \notefnerr
- *
- * \sa
- * ::cuGraphicsD3D9RegisterResource,
- * ::cuGraphicsD3D10RegisterResource,
- * ::cuGraphicsD3D11RegisterResource,
- * ::cuGraphicsGLRegisterBuffer,
- * ::cuGraphicsGLRegisterImage
- */
-CUresult CUDAAPI cuGraphicsUnregisterResource(CUgraphicsResource resource);
-
-/**
- * \brief Get an array through which to access a subresource of a mapped graphics resource.
- *
- * Returns in \p *pArray an array through which the subresource of the mapped
- * graphics resource \p resource which corresponds to array index \p arrayIndex
- * and mipmap level \p mipLevel may be accessed. The value set in \p *pArray may
- * change every time that \p resource is mapped.
- *
- * If \p resource is not a texture then it cannot be accessed via an array and
- * ::CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned.
- * If \p arrayIndex is not a valid array index for \p resource then
- * ::CUDA_ERROR_INVALID_VALUE is returned.
- * If \p mipLevel is not a valid mipmap level for \p resource then
- * ::CUDA_ERROR_INVALID_VALUE is returned.
- * If \p resource is not mapped then ::CUDA_ERROR_NOT_MAPPED is returned.
- *
- * \param pArray - Returned array through which a subresource of \p resource may be accessed
- * \param resource - Mapped resource to access
- * \param arrayIndex - Array index for array textures or cubemap face
- * index as defined by ::CUarray_cubemap_face for
- * cubemap textures for the subresource to access
- * \param mipLevel - Mipmap level for the subresource to access
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_MAPPED,
- * ::CUDA_ERROR_NOT_MAPPED_AS_ARRAY
- * \notefnerr
- *
- * \sa ::cuGraphicsResourceGetMappedPointer
- */
-CUresult CUDAAPI cuGraphicsSubResourceGetMappedArray(CUarray *pArray, CUgraphicsResource resource, unsigned int arrayIndex, unsigned int mipLevel);
-
-#if __CUDA_API_VERSION >= 5000
-
-/**
- * \brief Get a mipmapped array through which to access a mapped graphics resource.
- *
- * Returns in \p *pMipmappedArray a mipmapped array through which the mapped graphics 
- * resource \p resource. The value set in \p *pMipmappedArray may change every time 
- * that \p resource is mapped.
- *
- * If \p resource is not a texture then it cannot be accessed via a mipmapped array and
- * ::CUDA_ERROR_NOT_MAPPED_AS_ARRAY is returned.
- * If \p resource is not mapped then ::CUDA_ERROR_NOT_MAPPED is returned.
- *
- * \param pMipmappedArray - Returned mipmapped array through which \p resource may be accessed
- * \param resource - Mapped resource to access
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_MAPPED,
- * ::CUDA_ERROR_NOT_MAPPED_AS_ARRAY
- * \notefnerr
- *
- * \sa ::cuGraphicsResourceGetMappedPointer
- */
-CUresult CUDAAPI cuGraphicsResourceGetMappedMipmappedArray(CUmipmappedArray *pMipmappedArray, CUgraphicsResource resource);
-
-#endif /* __CUDA_API_VERSION >= 5000 */
-
-#if __CUDA_API_VERSION >= 3020
-/**
- * \brief Get a device pointer through which to access a mapped graphics resource.
- *
- * Returns in \p *pDevPtr a pointer through which the mapped graphics resource
- * \p resource may be accessed.
- * Returns in \p pSize the size of the memory in bytes which may be accessed from that pointer.
- * The value set in \p pPointer may change every time that \p resource is mapped.
- *
- * If \p resource is not a buffer then it cannot be accessed via a pointer and
- * ::CUDA_ERROR_NOT_MAPPED_AS_POINTER is returned.
- * If \p resource is not mapped then ::CUDA_ERROR_NOT_MAPPED is returned.
- * *
- * \param pDevPtr - Returned pointer through which \p resource may be accessed
- * \param pSize - Returned size of the buffer accessible starting at \p *pPointer
- * \param resource - Mapped resource to access
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_MAPPED,
- * ::CUDA_ERROR_NOT_MAPPED_AS_POINTER
- * \notefnerr
- *
- * \sa
- * ::cuGraphicsMapResources,
- * ::cuGraphicsSubResourceGetMappedArray
- */
-CUresult CUDAAPI cuGraphicsResourceGetMappedPointer(CUdeviceptr *pDevPtr, size_t *pSize, CUgraphicsResource resource);
-#endif /* __CUDA_API_VERSION >= 3020 */
-
-/**
- * \brief Set usage flags for mapping a graphics resource
- *
- * Set \p flags for mapping the graphics resource \p resource.
- *
- * Changes to \p flags will take effect the next time \p resource is mapped.
- * The \p flags argument may be any of the following:
-
- * - ::CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE: Specifies no hints about how this
- * resource will be used. It is therefore assumed that this resource will be
- * read from and written to by CUDA kernels. This is the default value.
- * - ::CU_GRAPHICS_MAP_RESOURCE_FLAGS_READONLY: Specifies that CUDA kernels which
- * access this resource will not write to this resource.
- * - ::CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITEDISCARD: Specifies that CUDA kernels
- * which access this resource will not read from this resource and will
- * write over the entire contents of the resource, so none of the data
- * previously stored in the resource will be preserved.
- *
- * If \p resource is presently mapped for access by CUDA then
- * ::CUDA_ERROR_ALREADY_MAPPED is returned.
- * If \p flags is not one of the above values then ::CUDA_ERROR_INVALID_VALUE is returned.
- *
- * \param resource - Registered resource to set flags for
- * \param flags - Parameters for resource mapping
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_VALUE,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_ALREADY_MAPPED
- * \notefnerr
- *
- * \sa
- * ::cuGraphicsMapResources
- */
-CUresult CUDAAPI cuGraphicsResourceSetMapFlags(CUgraphicsResource resource, unsigned int flags);
-
-/**
- * \brief Map graphics resources for access by CUDA
- *
- * Maps the \p count graphics resources in \p resources for access by CUDA.
- *
- * The resources in \p resources may be accessed by CUDA until they
- * are unmapped. The graphics API from which \p resources were registered
- * should not access any resources while they are mapped by CUDA. If an
- * application does so, the results are undefined.
- *
- * This function provides the synchronization guarantee that any graphics calls
- * issued before ::cuGraphicsMapResources() will complete before any subsequent CUDA
- * work issued in \p stream begins.
- *
- * If \p resources includes any duplicate entries then ::CUDA_ERROR_INVALID_HANDLE is returned.
- * If any of \p resources are presently mapped for access by CUDA then ::CUDA_ERROR_ALREADY_MAPPED is returned.
- *
- * \param count - Number of resources to map
- * \param resources - Resources to map for CUDA usage
- * \param hStream - Stream with which to synchronize
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_ALREADY_MAPPED,
- * ::CUDA_ERROR_UNKNOWN
- * \note_null_stream
- * \notefnerr
- *
- * \sa
- * ::cuGraphicsResourceGetMappedPointer,
- * ::cuGraphicsSubResourceGetMappedArray,
- * ::cuGraphicsUnmapResources
- */
-CUresult CUDAAPI cuGraphicsMapResources(unsigned int count, CUgraphicsResource *resources, CUstream hStream);
-
-/**
- * \brief Unmap graphics resources.
- *
- * Unmaps the \p count graphics resources in \p resources.
- *
- * Once unmapped, the resources in \p resources may not be accessed by CUDA
- * until they are mapped again.
- *
- * This function provides the synchronization guarantee that any CUDA work issued
- * in \p stream before ::cuGraphicsUnmapResources() will complete before any
- * subsequently issued graphics work begins.
- *
- *
- * If \p resources includes any duplicate entries then ::CUDA_ERROR_INVALID_HANDLE is returned.
- * If any of \p resources are not presently mapped for access by CUDA then ::CUDA_ERROR_NOT_MAPPED is returned.
- *
- * \param count - Number of resources to unmap
- * \param resources - Resources to unmap
- * \param hStream - Stream with which to synchronize
- *
- * \return
- * ::CUDA_SUCCESS,
- * ::CUDA_ERROR_DEINITIALIZED,
- * ::CUDA_ERROR_NOT_INITIALIZED,
- * ::CUDA_ERROR_INVALID_CONTEXT,
- * ::CUDA_ERROR_INVALID_HANDLE,
- * ::CUDA_ERROR_NOT_MAPPED,
- * ::CUDA_ERROR_UNKNOWN
- * \note_null_stream
- * \notefnerr
- *
- * \sa
- * ::cuGraphicsMapResources
- */
-CUresult CUDAAPI cuGraphicsUnmapResources(unsigned int count, CUgraphicsResource *resources, CUstream hStream);
-
-/** @} */ /* END CUDA_GRAPHICS */
-
-CUresult CUDAAPI cuGetExportTable(const void **ppExportTable, const CUuuid *pExportTableId);
-
-
-/**
- * CUDA API versioning support
- */
-#if defined(__CUDA_API_VERSION_INTERNAL)
- #undef cuMemHostRegister
- #undef cuGraphicsResourceSetMapFlags
- #undef cuLinkCreate
- #undef cuLinkAddData
- #undef cuLinkAddFile
- #undef cuDeviceTotalMem
- #undef cuCtxCreate
- #undef cuModuleGetGlobal
- #undef cuMemGetInfo
- #undef cuMemAlloc
- #undef cuMemAllocPitch
- #undef cuMemFree
- #undef cuMemGetAddressRange
- #undef cuMemAllocHost
- #undef cuMemHostGetDevicePointer
- #undef cuMemcpyHtoD
- #undef cuMemcpyDtoH
- #undef cuMemcpyDtoD
- #undef cuMemcpyDtoA
- #undef cuMemcpyAtoD
- #undef cuMemcpyHtoA
- #undef cuMemcpyAtoH
- #undef cuMemcpyAtoA
- #undef cuMemcpyHtoAAsync
- #undef cuMemcpyAtoHAsync
- #undef cuMemcpy2D
- #undef cuMemcpy2DUnaligned
- #undef cuMemcpy3D
- #undef cuMemcpyHtoDAsync
- #undef cuMemcpyDtoHAsync
- #undef cuMemcpyDtoDAsync
- #undef cuMemcpy2DAsync
- #undef cuMemcpy3DAsync
- #undef cuMemsetD8
- #undef cuMemsetD16
- #undef cuMemsetD32
- #undef cuMemsetD2D8
- #undef cuMemsetD2D16
- #undef cuMemsetD2D32
- #undef cuArrayCreate
- #undef cuArrayGetDescriptor
- #undef cuArray3DCreate
- #undef cuArray3DGetDescriptor
- #undef cuTexRefSetAddress
- #undef cuTexRefSetAddress2D
- #undef cuTexRefGetAddress
- #undef cuGraphicsResourceGetMappedPointer
- #undef cuCtxDestroy
- #undef cuCtxPopCurrent
- #undef cuCtxPushCurrent
- #undef cuStreamDestroy
- #undef cuEventDestroy
- #undef cuMemcpy
- #undef cuMemcpyAsync
- #undef cuMemcpyPeer
- #undef cuMemcpyPeerAsync
- #undef cuMemcpy3DPeer
- #undef cuMemcpy3DPeerAsync
- #undef cuMemsetD8Async
- #undef cuMemsetD16Async
- #undef cuMemsetD32Async
- #undef cuMemsetD2D8Async
- #undef cuMemsetD2D16Async
- #undef cuMemsetD2D32Async
- #undef cuStreamGetPriority
- #undef cuStreamGetFlags
- #undef cuStreamWaitEvent
- #undef cuStreamAddCallback
- #undef cuStreamAttachMemAsync
- #undef cuStreamQuery
- #undef cuStreamSynchronize
- #undef cuEventRecord
- #undef cuLaunchKernel
- #undef cuGraphicsMapResources
- #undef cuGraphicsUnmapResources
-#endif /* __CUDA_API_VERSION_INTERNAL */
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || (__CUDA_API_VERSION >= 4000 && __CUDA_API_VERSION < 6050)
-CUresult CUDAAPI cuMemHostRegister(void *p, size_t bytesize, unsigned int Flags);
-#endif /* defined(__CUDA_API_VERSION_INTERNAL) || (__CUDA_API_VERSION >= 4000 && __CUDA_API_VERSION < 6050) */
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION < 6050
-CUresult CUDAAPI cuGraphicsResourceSetMapFlags(CUgraphicsResource resource, unsigned int flags);
-#endif /* defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION < 6050 */
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || (__CUDA_API_VERSION >= 5050 && __CUDA_API_VERSION < 6050)
-CUresult CUDAAPI cuLinkCreate(unsigned int numOptions, CUjit_option *options, void **optionValues, CUlinkState *stateOut);
-CUresult CUDAAPI cuLinkAddData(CUlinkState state, CUjitInputType type, void *data, size_t size, const char *name,
- unsigned int numOptions, CUjit_option *options, void **optionValues);
-CUresult CUDAAPI cuLinkAddFile(CUlinkState state, CUjitInputType type, const char *path,
- unsigned int numOptions, CUjit_option *options, void **optionValues);
-#endif /* __CUDA_API_VERSION_INTERNAL || (__CUDA_API_VERSION >= 5050 && __CUDA_API_VERSION < 6050) */
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || (__CUDA_API_VERSION >= 3020 && __CUDA_API_VERSION < 4010)
-CUresult CUDAAPI cuTexRefSetAddress2D_v2(CUtexref hTexRef, const CUDA_ARRAY_DESCRIPTOR *desc, CUdeviceptr dptr, size_t Pitch);
-#endif /* __CUDA_API_VERSION_INTERNAL || (__CUDA_API_VERSION >= 3020 && __CUDA_API_VERSION < 4010) */
-
-/**
- * CUDA API made obselete at API version 3020
- */
-#if defined(__CUDA_API_VERSION_INTERNAL)
- #define CUdeviceptr CUdeviceptr_v1
- #define CUDA_MEMCPY2D_st CUDA_MEMCPY2D_v1_st
- #define CUDA_MEMCPY2D CUDA_MEMCPY2D_v1
- #define CUDA_MEMCPY3D_st CUDA_MEMCPY3D_v1_st
- #define CUDA_MEMCPY3D CUDA_MEMCPY3D_v1
- #define CUDA_ARRAY_DESCRIPTOR_st CUDA_ARRAY_DESCRIPTOR_v1_st
- #define CUDA_ARRAY_DESCRIPTOR CUDA_ARRAY_DESCRIPTOR_v1
- #define CUDA_ARRAY3D_DESCRIPTOR_st CUDA_ARRAY3D_DESCRIPTOR_v1_st
- #define CUDA_ARRAY3D_DESCRIPTOR CUDA_ARRAY3D_DESCRIPTOR_v1
-#endif /* CUDA_FORCE_LEGACY32_INTERNAL */
-
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION < 3020
-
-typedef unsigned int CUdeviceptr;
-
-typedef struct CUDA_MEMCPY2D_st
-{
- unsigned int srcXInBytes; /**< Source X in bytes */
- unsigned int srcY; /**< Source Y */
- CUmemorytype srcMemoryType; /**< Source memory type (host, device, array) */
- const void *srcHost; /**< Source host pointer */
- CUdeviceptr srcDevice; /**< Source device pointer */
- CUarray srcArray; /**< Source array reference */
- unsigned int srcPitch; /**< Source pitch (ignored when src is array) */
-
- unsigned int dstXInBytes; /**< Destination X in bytes */
- unsigned int dstY; /**< Destination Y */
- CUmemorytype dstMemoryType; /**< Destination memory type (host, device, array) */
- void *dstHost; /**< Destination host pointer */
- CUdeviceptr dstDevice; /**< Destination device pointer */
- CUarray dstArray; /**< Destination array reference */
- unsigned int dstPitch; /**< Destination pitch (ignored when dst is array) */
-
- unsigned int WidthInBytes; /**< Width of 2D memory copy in bytes */
- unsigned int Height; /**< Height of 2D memory copy */
-} CUDA_MEMCPY2D;
-
-typedef struct CUDA_MEMCPY3D_st
-{
- unsigned int srcXInBytes; /**< Source X in bytes */
- unsigned int srcY; /**< Source Y */
- unsigned int srcZ; /**< Source Z */
- unsigned int srcLOD; /**< Source LOD */
- CUmemorytype srcMemoryType; /**< Source memory type (host, device, array) */
- const void *srcHost; /**< Source host pointer */
- CUdeviceptr srcDevice; /**< Source device pointer */
- CUarray srcArray; /**< Source array reference */
- void *reserved0; /**< Must be NULL */
- unsigned int srcPitch; /**< Source pitch (ignored when src is array) */
- unsigned int srcHeight; /**< Source height (ignored when src is array; may be 0 if Depth==1) */
-
- unsigned int dstXInBytes; /**< Destination X in bytes */
- unsigned int dstY; /**< Destination Y */
- unsigned int dstZ; /**< Destination Z */
- unsigned int dstLOD; /**< Destination LOD */
- CUmemorytype dstMemoryType; /**< Destination memory type (host, device, array) */
- void *dstHost; /**< Destination host pointer */
- CUdeviceptr dstDevice; /**< Destination device pointer */
- CUarray dstArray; /**< Destination array reference */
- void *reserved1; /**< Must be NULL */
- unsigned int dstPitch; /**< Destination pitch (ignored when dst is array) */
- unsigned int dstHeight; /**< Destination height (ignored when dst is array; may be 0 if Depth==1) */
-
- unsigned int WidthInBytes; /**< Width of 3D memory copy in bytes */
- unsigned int Height; /**< Height of 3D memory copy */
- unsigned int Depth; /**< Depth of 3D memory copy */
-} CUDA_MEMCPY3D;
-
-typedef struct CUDA_ARRAY_DESCRIPTOR_st
-{
- unsigned int Width; /**< Width of array */
- unsigned int Height; /**< Height of array */
-
- CUarray_format Format; /**< Array format */
- unsigned int NumChannels; /**< Channels per array element */
-} CUDA_ARRAY_DESCRIPTOR;
-
-typedef struct CUDA_ARRAY3D_DESCRIPTOR_st
-{
- unsigned int Width; /**< Width of 3D array */
- unsigned int Height; /**< Height of 3D array */
- unsigned int Depth; /**< Depth of 3D array */
-
- CUarray_format Format; /**< Array format */
- unsigned int NumChannels; /**< Channels per array element */
- unsigned int Flags; /**< Flags */
-} CUDA_ARRAY3D_DESCRIPTOR;
-
-CUresult CUDAAPI cuDeviceTotalMem(unsigned int *bytes, CUdevice dev);
-CUresult CUDAAPI cuCtxCreate(CUcontext *pctx, unsigned int flags, CUdevice dev);
-CUresult CUDAAPI cuModuleGetGlobal(CUdeviceptr *dptr, unsigned int *bytes, CUmodule hmod, const char *name);
-CUresult CUDAAPI cuMemGetInfo(unsigned int *free, unsigned int *total);
-CUresult CUDAAPI cuMemAlloc(CUdeviceptr *dptr, unsigned int bytesize);
-CUresult CUDAAPI cuMemAllocPitch(CUdeviceptr *dptr, unsigned int *pPitch, unsigned int WidthInBytes, unsigned int Height, unsigned int ElementSizeBytes);
-CUresult CUDAAPI cuMemFree(CUdeviceptr dptr);
-CUresult CUDAAPI cuMemGetAddressRange(CUdeviceptr *pbase, unsigned int *psize, CUdeviceptr dptr);
-CUresult CUDAAPI cuMemAllocHost(void **pp, unsigned int bytesize);
-CUresult CUDAAPI cuMemHostGetDevicePointer(CUdeviceptr *pdptr, void *p, unsigned int Flags);
-CUresult CUDAAPI cuMemcpyHtoD(CUdeviceptr dstDevice, const void *srcHost, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyDtoH(void *dstHost, CUdeviceptr srcDevice, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyDtoD(CUdeviceptr dstDevice, CUdeviceptr srcDevice, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyDtoA(CUarray dstArray, unsigned int dstOffset, CUdeviceptr srcDevice, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyAtoD(CUdeviceptr dstDevice, CUarray srcArray, unsigned int srcOffset, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyHtoA(CUarray dstArray, unsigned int dstOffset, const void *srcHost, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyAtoH(void *dstHost, CUarray srcArray, unsigned int srcOffset, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyAtoA(CUarray dstArray, unsigned int dstOffset, CUarray srcArray, unsigned int srcOffset, unsigned int ByteCount);
-CUresult CUDAAPI cuMemcpyHtoAAsync(CUarray dstArray, unsigned int dstOffset, const void *srcHost, unsigned int ByteCount, CUstream hStream);
-CUresult CUDAAPI cuMemcpyAtoHAsync(void *dstHost, CUarray srcArray, unsigned int srcOffset, unsigned int ByteCount, CUstream hStream);
-CUresult CUDAAPI cuMemcpy2D(const CUDA_MEMCPY2D *pCopy);
-CUresult CUDAAPI cuMemcpy2DUnaligned(const CUDA_MEMCPY2D *pCopy);
-CUresult CUDAAPI cuMemcpy3D(const CUDA_MEMCPY3D *pCopy);
-CUresult CUDAAPI cuMemcpyHtoDAsync(CUdeviceptr dstDevice, const void *srcHost, unsigned int ByteCount, CUstream hStream);
-CUresult CUDAAPI cuMemcpyDtoHAsync(void *dstHost, CUdeviceptr srcDevice, unsigned int ByteCount, CUstream hStream);
-CUresult CUDAAPI cuMemcpyDtoDAsync(CUdeviceptr dstDevice, CUdeviceptr srcDevice, unsigned int ByteCount, CUstream hStream);
-CUresult CUDAAPI cuMemcpy2DAsync(const CUDA_MEMCPY2D *pCopy, CUstream hStream);
-CUresult CUDAAPI cuMemcpy3DAsync(const CUDA_MEMCPY3D *pCopy, CUstream hStream);
-CUresult CUDAAPI cuMemsetD8(CUdeviceptr dstDevice, unsigned char uc, unsigned int N);
-CUresult CUDAAPI cuMemsetD16(CUdeviceptr dstDevice, unsigned short us, unsigned int N);
-CUresult CUDAAPI cuMemsetD32(CUdeviceptr dstDevice, unsigned int ui, unsigned int N);
-CUresult CUDAAPI cuMemsetD2D8(CUdeviceptr dstDevice, unsigned int dstPitch, unsigned char uc, unsigned int Width, unsigned int Height);
-CUresult CUDAAPI cuMemsetD2D16(CUdeviceptr dstDevice, unsigned int dstPitch, unsigned short us, unsigned int Width, unsigned int Height);
-CUresult CUDAAPI cuMemsetD2D32(CUdeviceptr dstDevice, unsigned int dstPitch, unsigned int ui, unsigned int Width, unsigned int Height);
-CUresult CUDAAPI cuArrayCreate(CUarray *pHandle, const CUDA_ARRAY_DESCRIPTOR *pAllocateArray);
-CUresult CUDAAPI cuArrayGetDescriptor(CUDA_ARRAY_DESCRIPTOR *pArrayDescriptor, CUarray hArray);
-CUresult CUDAAPI cuArray3DCreate(CUarray *pHandle, const CUDA_ARRAY3D_DESCRIPTOR *pAllocateArray);
-CUresult CUDAAPI cuArray3DGetDescriptor(CUDA_ARRAY3D_DESCRIPTOR *pArrayDescriptor, CUarray hArray);
-CUresult CUDAAPI cuTexRefSetAddress(unsigned int *ByteOffset, CUtexref hTexRef, CUdeviceptr dptr, unsigned int bytes);
-CUresult CUDAAPI cuTexRefSetAddress2D(CUtexref hTexRef, const CUDA_ARRAY_DESCRIPTOR *desc, CUdeviceptr dptr, unsigned int Pitch);
-CUresult CUDAAPI cuTexRefGetAddress(CUdeviceptr *pdptr, CUtexref hTexRef);
-CUresult CUDAAPI cuGraphicsResourceGetMappedPointer(CUdeviceptr *pDevPtr, unsigned int *pSize, CUgraphicsResource resource);
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION < 3020 */
-#if defined(__CUDA_API_VERSION_INTERNAL) || __CUDA_API_VERSION < 4000
-CUresult CUDAAPI cuCtxDestroy(CUcontext ctx);
-CUresult CUDAAPI cuCtxPopCurrent(CUcontext *pctx);
-CUresult CUDAAPI cuCtxPushCurrent(CUcontext ctx);
-CUresult CUDAAPI cuStreamDestroy(CUstream hStream);
-CUresult CUDAAPI cuEventDestroy(CUevent hEvent);
-#endif /* __CUDA_API_VERSION_INTERNAL || __CUDA_API_VERSION < 4000 */
-#if defined(__CUDA_API_VERSION_INTERNAL)
- #undef CUdeviceptr
- #undef CUDA_MEMCPY2D_st
- #undef CUDA_MEMCPY2D
- #undef CUDA_MEMCPY3D_st
- #undef CUDA_MEMCPY3D
- #undef CUDA_ARRAY_DESCRIPTOR_st
- #undef CUDA_ARRAY_DESCRIPTOR
- #undef CUDA_ARRAY3D_DESCRIPTOR_st
- #undef CUDA_ARRAY3D_DESCRIPTOR
-#endif /* __CUDA_API_VERSION_INTERNAL */
-
-#if defined(__CUDA_API_VERSION_INTERNAL)
- CUresult CUDAAPI cuMemcpyHtoD_v2(CUdeviceptr dstDevice, const void *srcHost, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyDtoH_v2(void *dstHost, CUdeviceptr srcDevice, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyDtoD_v2(CUdeviceptr dstDevice, CUdeviceptr srcDevice, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyDtoA_v2(CUarray dstArray, size_t dstOffset, CUdeviceptr srcDevice, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyAtoD_v2(CUdeviceptr dstDevice, CUarray srcArray, size_t srcOffset, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyHtoA_v2(CUarray dstArray, size_t dstOffset, const void *srcHost, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyAtoH_v2(void *dstHost, CUarray srcArray, size_t srcOffset, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyAtoA_v2(CUarray dstArray, size_t dstOffset, CUarray srcArray, size_t srcOffset, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyHtoAAsync_v2(CUarray dstArray, size_t dstOffset, const void *srcHost, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpyAtoHAsync_v2(void *dstHost, CUarray srcArray, size_t srcOffset, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpy2D_v2(const CUDA_MEMCPY2D *pCopy);
- CUresult CUDAAPI cuMemcpy2DUnaligned_v2(const CUDA_MEMCPY2D *pCopy);
- CUresult CUDAAPI cuMemcpy3D_v2(const CUDA_MEMCPY3D *pCopy);
- CUresult CUDAAPI cuMemcpyHtoDAsync_v2(CUdeviceptr dstDevice, const void *srcHost, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpyDtoHAsync_v2(void *dstHost, CUdeviceptr srcDevice, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpyDtoDAsync_v2(CUdeviceptr dstDevice, CUdeviceptr srcDevice, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpy2DAsync_v2(const CUDA_MEMCPY2D *pCopy, CUstream hStream);
- CUresult CUDAAPI cuMemcpy3DAsync_v2(const CUDA_MEMCPY3D *pCopy, CUstream hStream);
- CUresult CUDAAPI cuMemsetD8_v2(CUdeviceptr dstDevice, unsigned char uc, size_t N);
- CUresult CUDAAPI cuMemsetD16_v2(CUdeviceptr dstDevice, unsigned short us, size_t N);
- CUresult CUDAAPI cuMemsetD32_v2(CUdeviceptr dstDevice, unsigned int ui, size_t N);
- CUresult CUDAAPI cuMemsetD2D8_v2(CUdeviceptr dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height);
- CUresult CUDAAPI cuMemsetD2D16_v2(CUdeviceptr dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height);
- CUresult CUDAAPI cuMemsetD2D32_v2(CUdeviceptr dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height);
- CUresult CUDAAPI cuMemcpy(CUdeviceptr dst, CUdeviceptr src, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyAsync(CUdeviceptr dst, CUdeviceptr src, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpyPeer(CUdeviceptr dstDevice, CUcontext dstContext, CUdeviceptr srcDevice, CUcontext srcContext, size_t ByteCount);
- CUresult CUDAAPI cuMemcpyPeerAsync(CUdeviceptr dstDevice, CUcontext dstContext, CUdeviceptr srcDevice, CUcontext srcContext, size_t ByteCount, CUstream hStream);
- CUresult CUDAAPI cuMemcpy3DPeer(const CUDA_MEMCPY3D_PEER *pCopy);
- CUresult CUDAAPI cuMemcpy3DPeerAsync(const CUDA_MEMCPY3D_PEER *pCopy, CUstream hStream);
-
- CUresult CUDAAPI cuMemsetD8Async(CUdeviceptr dstDevice, unsigned char uc, size_t N, CUstream hStream);
- CUresult CUDAAPI cuMemsetD16Async(CUdeviceptr dstDevice, unsigned short us, size_t N, CUstream hStream);
- CUresult CUDAAPI cuMemsetD32Async(CUdeviceptr dstDevice, unsigned int ui, size_t N, CUstream hStream);
- CUresult CUDAAPI cuMemsetD2D8Async(CUdeviceptr dstDevice, size_t dstPitch, unsigned char uc, size_t Width, size_t Height, CUstream hStream);
- CUresult CUDAAPI cuMemsetD2D16Async(CUdeviceptr dstDevice, size_t dstPitch, unsigned short us, size_t Width, size_t Height, CUstream hStream);
- CUresult CUDAAPI cuMemsetD2D32Async(CUdeviceptr dstDevice, size_t dstPitch, unsigned int ui, size_t Width, size_t Height, CUstream hStream);
-
- CUresult CUDAAPI cuStreamGetPriority(CUstream hStream, int *priority);
- CUresult CUDAAPI cuStreamGetFlags(CUstream hStream, unsigned int *flags);
- CUresult CUDAAPI cuStreamWaitEvent(CUstream hStream, CUevent hEvent, unsigned int Flags);
- CUresult CUDAAPI cuStreamAddCallback(CUstream hStream, CUstreamCallback callback, void *userData, unsigned int flags);
- CUresult CUDAAPI cuStreamAttachMemAsync(CUstream hStream, CUdeviceptr dptr, size_t length, unsigned int flags);
- CUresult CUDAAPI cuStreamQuery(CUstream hStream);
- CUresult CUDAAPI cuStreamSynchronize(CUstream hStream);
- CUresult CUDAAPI cuEventRecord(CUevent hEvent, CUstream hStream);
- CUresult CUDAAPI cuLaunchKernel(CUfunction f, unsigned int gridDimX, unsigned int gridDimY, unsigned int gridDimZ, unsigned int blockDimX, unsigned int blockDimY, unsigned int blockDimZ, unsigned int sharedMemBytes, CUstream hStream, void **kernelParams, void **extra);
- CUresult CUDAAPI cuGraphicsMapResources(unsigned int count, CUgraphicsResource *resources, CUstream hStream);
- CUresult CUDAAPI cuGraphicsUnmapResources(unsigned int count, CUgraphicsResource *resources, CUstream hStream);
-#endif
-
-#ifdef __cplusplus
-}
-#endif
-
-#undef __CUDA_API_VERSION
-
-#endif /* __cuda_cuda_h__ */
-

QtAV-1.11.0.tar.gz/src/cuda/dllapi/cuviddec.h Deleted

@@ -1,715 +0,0 @@
-/*
- * Copyright 1993-2008 NVIDIA Corporation. All rights reserved.
- *
- * NOTICE TO USER: 
- *
- * This source code is subject to NVIDIA ownership rights under U.S. and 
- * international Copyright laws. Users and possessors of this source code 
- * are hereby granted a nonexclusive, royalty-free license to use this code 
- * in individual and commercial software.
- *
- * NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE 
- * CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR 
- * IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH 
- * REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF 
- * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
- * IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL, 
- * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS 
- * OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE 
- * OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE 
- * OR PERFORMANCE OF THIS SOURCE CODE. 
- *
- * U.S. Government End Users. This source code is a "commercial item" as 
- * that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting of 
- * "commercial computer software" and "commercial computer software 
- * documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995) 
- * and is provided to the U.S. Government only as a commercial end item. 
- * Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through 
- * 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the 
- * source code with only those rights set forth herein. 
- *
- * Any use of this source code in individual and commercial software must 
- * include, in the user documentation and internal comments to the code,
- * the above Disclaimer and U.S. Government End Users Notice.
- */
- 
-#if !defined(__CUDA_VIDEO_H__)
-#define __CUDA_VIDEO_H__
-
-#ifndef __cuda_cuda_h__
-#include <cuda.h>
-#endif // __cuda_cuda_h__
-
-#if defined(__x86_64) || defined(AMD64) || defined(_M_AMD64)
-#if (CUDA_VERSION >= 3020) && (!defined(CUDA_FORCE_API_VERSION) || (CUDA_FORCE_API_VERSION >= 3020))
-#define __CUVID_DEVPTR64
-#endif
-#endif
-
-#if defined(__cplusplus)
-extern "C" {
-#endif /* __cplusplus */
-
-typedef void *CUvideodecoder;
-typedef struct _CUcontextlock_st *CUvideoctxlock;
-
-typedef enum cudaVideoCodec_enum {
- cudaVideoCodec_MPEG1=0,
- cudaVideoCodec_MPEG2,
- cudaVideoCodec_MPEG4,
- cudaVideoCodec_VC1,
- cudaVideoCodec_H264,
- cudaVideoCodec_JPEG,
- cudaVideoCodec_H264_SVC,
- cudaVideoCodec_H264_MVC,
- cudaVideoCodec_HEVC,
- cudaVideoCodec_VP8,
- cudaVideoCodec_VP9,
- cudaVideoCodec_NumCodecs,
- // Uncompressed YUV
- cudaVideoCodec_YUV420 = (('I'<<24)|('Y'<<16)|('U'<<8)|('V')), // Y,U,V (4:2:0)
- cudaVideoCodec_YV12 = (('Y'<<24)|('V'<<16)|('1'<<8)|('2')), // Y,V,U (4:2:0)
- cudaVideoCodec_NV12 = (('N'<<24)|('V'<<16)|('1'<<8)|('2')), // Y,UV (4:2:0)
- cudaVideoCodec_YUYV = (('Y'<<24)|('U'<<16)|('Y'<<8)|('V')), // YUYV/YUY2 (4:2:2)
- cudaVideoCodec_UYVY = (('U'<<24)|('Y'<<16)|('V'<<8)|('Y')) // UYVY (4:2:2)
-} cudaVideoCodec;
-
-typedef enum cudaVideoSurfaceFormat_enum {
- cudaVideoSurfaceFormat_NV12=0 // NV12 (currently the only supported output format)
-} cudaVideoSurfaceFormat;
-
-typedef enum cudaVideoDeinterlaceMode_enum {
- cudaVideoDeinterlaceMode_Weave=0, // Weave both fields (no deinterlacing)
- cudaVideoDeinterlaceMode_Bob, // Drop one field
- cudaVideoDeinterlaceMode_Adaptive // Adaptive deinterlacing
-} cudaVideoDeinterlaceMode;
-
-typedef enum cudaVideoChromaFormat_enum {
- cudaVideoChromaFormat_Monochrome=0,
- cudaVideoChromaFormat_420,
- cudaVideoChromaFormat_422,
- cudaVideoChromaFormat_444
-} cudaVideoChromaFormat;
-
-typedef enum cudaVideoCreateFlags_enum {
- cudaVideoCreate_Default = 0x00, // Default operation mode: use dedicated video engines
- cudaVideoCreate_PreferCUDA = 0x01, // Use a CUDA-based decoder if faster than dedicated engines (requires a valid vidLock object for multi-threading)
- cudaVideoCreate_PreferDXVA = 0x02, // Go through DXVA internally if possible (requires D3D9 interop)
- cudaVideoCreate_PreferCUVID = 0x04 // Use dedicated video engines directly
-} cudaVideoCreateFlags;
-
-
-typedef struct _CUVIDDECODECREATEINFO
-{
- // Decoding
- unsigned long ulWidth; // Coded Sequence Width
- unsigned long ulHeight; // Coded Sequence Height
- unsigned long ulNumDecodeSurfaces; // Maximum number of internal decode surfaces
- cudaVideoCodec CodecType; // cudaVideoCodec_XXX
- cudaVideoChromaFormat ChromaFormat; // cudaVideoChromaFormat_XXX (only 4:2:0 is currently supported)
- unsigned long ulCreationFlags; // Decoder creation flags (cudaVideoCreateFlags_XXX)
- unsigned long Reserved1[5]; // Reserved for future use - set to zero
- struct { // area of the frame that should be displayed
- short left;
- short top;
- short right;
- short bottom;
- } display_area;
- // Output format
- cudaVideoSurfaceFormat OutputFormat; // cudaVideoSurfaceFormat_XXX
- cudaVideoDeinterlaceMode DeinterlaceMode; // cudaVideoDeinterlaceMode_XXX
- unsigned long ulTargetWidth; // Post-processed Output Width 
- unsigned long ulTargetHeight; // Post-processed Output Height
- unsigned long ulNumOutputSurfaces; // Maximum number of output surfaces simultaneously mapped
- CUvideoctxlock vidLock; // If non-NULL, context lock used for synchronizing ownership of the cuda context
- struct { // target rectangle in the output frame (for aspect ratio conversion)
- short left;
- short top;
- short right;
- short bottom;
- } target_rect; // if a null rectangle is specified, {0,0,ulTargetWidth,ulTargetHeight} will be used
- unsigned long Reserved2[5]; // Reserved for future use - set to zero
-} CUVIDDECODECREATEINFO;
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// H.264 Picture Parameters
-//
-
-typedef struct _CUVIDH264DPBENTRY
-{
- int PicIdx; // picture index of reference frame
- int FrameIdx; // frame_num(short-term) or LongTermFrameIdx(long-term)
- int is_long_term; // 0=short term reference, 1=long term reference
- int not_existing; // non-existing reference frame (corresponding PicIdx should be set to -1)
- int used_for_reference; // 0=unused, 1=top_field, 2=bottom_field, 3=both_fields
- int FieldOrderCnt[2]; // field order count of top and bottom fields
-} CUVIDH264DPBENTRY;
-
-typedef struct _CUVIDH264MVCEXT
-{
- int num_views_minus1;
- int view_id;
- unsigned char inter_view_flag;
- unsigned char num_inter_view_refs_l0;
- unsigned char num_inter_view_refs_l1;
- unsigned char MVCReserved8Bits;
- int InterViewRefsL0[16];
- int InterViewRefsL1[16];
-} CUVIDH264MVCEXT;
-
-typedef struct _CUVIDH264SVCEXT
-{
- unsigned char profile_idc;
- unsigned char level_idc;
- unsigned char DQId;
- unsigned char DQIdMax;
- unsigned char disable_inter_layer_deblocking_filter_idc;
- unsigned char ref_layer_chroma_phase_y_plus1;
- signed char inter_layer_slice_alpha_c0_offset_div2;
- signed char inter_layer_slice_beta_offset_div2;
- 
- unsigned short DPBEntryValidFlag;
- unsigned char inter_layer_deblocking_filter_control_present_flag;
- unsigned char extended_spatial_scalability_idc;
- unsigned char adaptive_tcoeff_level_prediction_flag;
- unsigned char slice_header_restriction_flag;
- unsigned char chroma_phase_x_plus1_flag;
- unsigned char chroma_phase_y_plus1;
- 
- unsigned char tcoeff_level_prediction_flag;
- unsigned char constrained_intra_resampling_flag;
- unsigned char ref_layer_chroma_phase_x_plus1_flag;
- unsigned char store_ref_base_pic_flag;
- unsigned char Reserved8BitsA; 
- unsigned char Reserved8BitsB; 
- // For the 4 scaled_ref_layer_XX fields below,
- // if (extended_spatial_scalability_idc == 1), SPS field, G.7.3.2.1.4, add prefix "seq_"
- // if (extended_spatial_scalability_idc == 2), SLH field, G.7.3.3.4, 
- short scaled_ref_layer_left_offset;
- short scaled_ref_layer_top_offset;
- short scaled_ref_layer_right_offset;
- short scaled_ref_layer_bottom_offset;
- unsigned short Reserved16Bits;
- struct _CUVIDPICPARAMS *pNextLayer; // Points to the picparams for the next layer to be decoded. Linked list ends at the target layer.
- int bRefBaseLayer; // whether to store ref base pic
-} CUVIDH264SVCEXT;
-
-typedef struct _CUVIDH264PICPARAMS
-{
- // SPS
- int log2_max_frame_num_minus4;
- int pic_order_cnt_type;
- int log2_max_pic_order_cnt_lsb_minus4;
- int delta_pic_order_always_zero_flag;
- int frame_mbs_only_flag;
- int direct_8x8_inference_flag;
- int num_ref_frames; // NOTE: shall meet level 4.1 restrictions
- unsigned char residual_colour_transform_flag;
- unsigned char bit_depth_luma_minus8; // Must be 0 (only 8-bit supported)
- unsigned char bit_depth_chroma_minus8; // Must be 0 (only 8-bit supported)
- unsigned char qpprime_y_zero_transform_bypass_flag;
- // PPS
- int entropy_coding_mode_flag;
- int pic_order_present_flag;
- int num_ref_idx_l0_active_minus1;
- int num_ref_idx_l1_active_minus1;
- int weighted_pred_flag;
- int weighted_bipred_idc;
- int pic_init_qp_minus26;
- int deblocking_filter_control_present_flag;
- int redundant_pic_cnt_present_flag;
- int transform_8x8_mode_flag;
- int MbaffFrameFlag;
- int constrained_intra_pred_flag;
- int chroma_qp_index_offset;
- int second_chroma_qp_index_offset;
- int ref_pic_flag;
- int frame_num;
- int CurrFieldOrderCnt[2];
- // DPB
- CUVIDH264DPBENTRY dpb[16]; // List of reference frames within the DPB
- // Quantization Matrices (raster-order)
- unsigned char WeightScale4x4[6][16];
- unsigned char WeightScale8x8[2][64];
- // FMO/ASO
- unsigned char fmo_aso_enable;
- unsigned char num_slice_groups_minus1;
- unsigned char slice_group_map_type;
- signed char pic_init_qs_minus26;
- unsigned int slice_group_change_rate_minus1;
- union
- {
- unsigned long long slice_group_map_addr;
- const unsigned char *pMb2SliceGroupMap;
- } fmo;
- unsigned int Reserved[12];
- // SVC/MVC
- union
- {
- CUVIDH264MVCEXT mvcext;
- CUVIDH264SVCEXT svcext;
- };
-} CUVIDH264PICPARAMS;
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// MPEG-2 Picture Parameters
-//
-
-typedef struct _CUVIDMPEG2PICPARAMS
-{
- int ForwardRefIdx; // Picture index of forward reference (P/B-frames)
- int BackwardRefIdx; // Picture index of backward reference (B-frames)
- int picture_coding_type;
- int full_pel_forward_vector;
- int full_pel_backward_vector;
- int f_code[2][2];
- int intra_dc_precision;
- int frame_pred_frame_dct;
- int concealment_motion_vectors;
- int q_scale_type;
- int intra_vlc_format;
- int alternate_scan;
- int top_field_first;
- // Quantization matrices (raster order)
- unsigned char QuantMatrixIntra[64];
- unsigned char QuantMatrixInter[64];
-} CUVIDMPEG2PICPARAMS;
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// MPEG-4 Picture Parameters
-//
-
-// MPEG-4 has VOP types instead of Picture types
-#define I_VOP 0
-#define P_VOP 1
-#define B_VOP 2
-#define S_VOP 3
-
-typedef struct _CUVIDMPEG4PICPARAMS
-{
- int ForwardRefIdx; // Picture index of forward reference (P/B-frames)
- int BackwardRefIdx; // Picture index of backward reference (B-frames)
- // VOL
- int video_object_layer_width;
- int video_object_layer_height;
- int vop_time_increment_bitcount;
- int top_field_first;
- int resync_marker_disable;
- int quant_type;
- int quarter_sample;
- int short_video_header;
- int divx_flags;
- // VOP
- int vop_coding_type;
- int vop_coded;
- int vop_rounding_type;
- int alternate_vertical_scan_flag;
- int interlaced;
- int vop_fcode_forward;
- int vop_fcode_backward;
- int trd[2];
- int trb[2];
- // Quantization matrices (raster order)
- unsigned char QuantMatrixIntra[64];
- unsigned char QuantMatrixInter[64];
- int gmc_enabled;
-} CUVIDMPEG4PICPARAMS;
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// VC1 Picture Parameters
-//
-
-typedef struct _CUVIDVC1PICPARAMS
-{
- int ForwardRefIdx; // Picture index of forward reference (P/B-frames)
- int BackwardRefIdx; // Picture index of backward reference (B-frames)
- int FrameWidth; // Actual frame width
- int FrameHeight; // Actual frame height
- // PICTURE
- int intra_pic_flag; // Set to 1 for I,BI frames
- int ref_pic_flag; // Set to 1 for I,P frames
- int progressive_fcm; // Progressive frame
- // SEQUENCE
- int profile;
- int postprocflag;
- int pulldown;
- int interlace;
- int tfcntrflag;
- int finterpflag;
- int psf;
- int multires;
- int syncmarker;
- int rangered;
- int maxbframes;
- // ENTRYPOINT
- int panscan_flag;
- int refdist_flag;
- int extended_mv;
- int dquant;
- int vstransform;
- int loopfilter;
- int fastuvmc;
- int overlap;
- int quantizer;
- int extended_dmv;
- int range_mapy_flag;
- int range_mapy;
- int range_mapuv_flag;
- int range_mapuv;
- int rangeredfrm; // range reduction state
-} CUVIDVC1PICPARAMS;
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// JPEG Picture Parameters
-//
-
-typedef struct _CUVIDJPEGPICPARAMS
-{
- int Reserved;
-} CUVIDJPEGPICPARAMS;
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// HEVC Picture Parameters
-//
-
-typedef struct _CUVIDHEVCPICPARAMS
-{
- // sps
- int pic_width_in_luma_samples;
- int pic_height_in_luma_samples;
- unsigned char log2_min_luma_coding_block_size_minus3;
- unsigned char log2_diff_max_min_luma_coding_block_size;
- unsigned char log2_min_transform_block_size_minus2;
- unsigned char log2_diff_max_min_transform_block_size;
- unsigned char pcm_enabled_flag;
- unsigned char log2_min_pcm_luma_coding_block_size_minus3;
- unsigned char log2_diff_max_min_pcm_luma_coding_block_size;
- unsigned char pcm_sample_bit_depth_luma_minus1;
- 
- unsigned char pcm_sample_bit_depth_chroma_minus1;
- unsigned char pcm_loop_filter_disabled_flag;
- unsigned char strong_intra_smoothing_enabled_flag;
- unsigned char max_transform_hierarchy_depth_intra;
- unsigned char max_transform_hierarchy_depth_inter;
- unsigned char amp_enabled_flag;
- unsigned char separate_colour_plane_flag;
- unsigned char log2_max_pic_order_cnt_lsb_minus4;
-
- unsigned char num_short_term_ref_pic_sets;
- unsigned char long_term_ref_pics_present_flag;
- unsigned char num_long_term_ref_pics_sps;
- unsigned char sps_temporal_mvp_enabled_flag;
- unsigned char sample_adaptive_offset_enabled_flag;
- unsigned char scaling_list_enable_flag;
- unsigned char IrapPicFlag;
- unsigned char IdrPicFlag;
- 
- unsigned char bit_depth_luma_minus8;
- unsigned char bit_depth_chroma_minus8;
- unsigned char reserved1[14];
- 
- // pps
- unsigned char dependent_slice_segments_enabled_flag;
- unsigned char slice_segment_header_extension_present_flag;
- unsigned char sign_data_hiding_enabled_flag;
- unsigned char cu_qp_delta_enabled_flag;
- unsigned char diff_cu_qp_delta_depth;
- signed char init_qp_minus26;
- signed char pps_cb_qp_offset;
- signed char pps_cr_qp_offset;
- 
- unsigned char constrained_intra_pred_flag;
- unsigned char weighted_pred_flag;
- unsigned char weighted_bipred_flag;
- unsigned char transform_skip_enabled_flag;
- unsigned char transquant_bypass_enabled_flag;
- unsigned char entropy_coding_sync_enabled_flag;
- unsigned char log2_parallel_merge_level_minus2;
- unsigned char num_extra_slice_header_bits;
- 
- unsigned char loop_filter_across_tiles_enabled_flag;
- unsigned char loop_filter_across_slices_enabled_flag;
- unsigned char output_flag_present_flag;
- unsigned char num_ref_idx_l0_default_active_minus1;
- unsigned char num_ref_idx_l1_default_active_minus1;
- unsigned char lists_modification_present_flag;
- unsigned char cabac_init_present_flag;
- unsigned char pps_slice_chroma_qp_offsets_present_flag;
- 
- unsigned char deblocking_filter_override_enabled_flag;
- unsigned char pps_deblocking_filter_disabled_flag;
- signed char pps_beta_offset_div2;
- signed char pps_tc_offset_div2;
- unsigned char tiles_enabled_flag;
- unsigned char uniform_spacing_flag;
- unsigned char num_tile_columns_minus1;
- unsigned char num_tile_rows_minus1;
- 
- unsigned short column_width_minus1[21];
- unsigned short row_height_minus1[21];
- unsigned int reserved3[15];
-
- // RefPicSets
- int NumBitsForShortTermRPSInSlice;
- int NumDeltaPocsOfRefRpsIdx;
- int NumPocTotalCurr;
- int NumPocStCurrBefore;
- int NumPocStCurrAfter;
- int NumPocLtCurr;
- int CurrPicOrderCntVal;
- int RefPicIdx[16]; // [refpic] Indices of valid reference pictures (-1 if unused for reference)
- int PicOrderCntVal[16]; // [refpic]
- unsigned char IsLongTerm[16]; // [refpic] 0=not a long-term reference, 1=long-term reference
- unsigned char RefPicSetStCurrBefore[8]; // [0..NumPocStCurrBefore-1] -> refpic (0..15)
- unsigned char RefPicSetStCurrAfter[8]; // [0..NumPocStCurrAfter-1] -> refpic (0..15)
- unsigned char RefPicSetLtCurr[8]; // [0..NumPocLtCurr-1] -> refpic (0..15)
- unsigned int reserved4[16];
-
- // scaling lists (diag order)
- unsigned char ScalingList4x4[6][16]; // [matrixId][i]
- unsigned char ScalingList8x8[6][64]; // [matrixId][i]
- unsigned char ScalingList16x16[6][64]; // [matrixId][i]
- unsigned char ScalingList32x32[2][64]; // [matrixId][i]
- unsigned char ScalingListDCCoeff16x16[6]; // [matrixId]
- unsigned char ScalingListDCCoeff32x32[2]; // [matrixId]
-} CUVIDHEVCPICPARAMS;
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// VP9 Picture Parameters for Decoding 
-//
-typedef struct _CUVIDVP9PICPARAMS
-{
- unsigned int width;
- unsigned int height;
-
- //Frame Indexes
- unsigned char reserved1;
- unsigned char LastRefIdx;
- unsigned char GoldenRefIdx;
- unsigned char AltRefIdx;
-
- unsigned short ref0_width; //ref_last coded width
- unsigned short ref0_height; //ref_last coded height
- unsigned short ref1_width; //ref_golden coded width
- unsigned short ref1_height; //ref_golden coded height
- unsigned short ref2_width; //ref_alt coded width
- unsigned short ref2_height; //ref_alt coded height
-
- unsigned int keyFrame;
- unsigned int version;
- unsigned int showFrame;
- unsigned int errorResilient;
- unsigned int colorSpace;
- unsigned int subsamplingX;
- unsigned int subsamplingY;
- unsigned int activeRefIdx[3];
- unsigned int intraOnly;
- unsigned int resetFrameContext;
- unsigned int frameParallelDecoding;
- unsigned int refreshFrameFlags;
- unsigned char refFrameSignBias[4];
- unsigned int frameContextIdx;
- unsigned int resolutionChange;
- unsigned int allow_high_precision_mv;
- unsigned int mcomp_filter_type;
- unsigned int allow_comp_inter_inter;
- unsigned int comp_fixed_ref;
- unsigned int comp_var_ref[2];
- unsigned int loopFilterLevel;
- unsigned int loopFilterSharpness;
- unsigned int log2_tile_columns;
- unsigned int log2_tile_rows;
- unsigned int mbRefLfDelta[4];
- unsigned int mbModeLfDelta[2];
- int segmentMapTemporalUpdate;
- unsigned char segmentFeatureEnable[8][4];
- unsigned char mb_segment_tree_probs[7];
- unsigned char segment_pred_probs[3];
- unsigned char reserved2[2];
- short segmentFeatureData[8][4];
- unsigned int scaledWidth;
- unsigned int scaledHeight;
- unsigned int scalingActive;
- unsigned int segmentEnabled;
- unsigned int prevIsKeyFrame;
- unsigned int PrevShowFrame;
- unsigned int modeRefLfEnabled;
- int qpYAc;
- int qpYDc;
- int qpChDc;
- int qpChAc;
- unsigned int lossless;
- unsigned int segmentMapUpdate;
- unsigned int segmentFeatureMode;
- unsigned int refreshEntropyProbs;
- unsigned int transform_mode;
- int probsDecoded;
- unsigned int comp_pred_mode;
- unsigned int probRefreshDetected;
- unsigned int frameTagSize;
- unsigned int offsetToDctParts;
-} CUVIDVP9PICPARAMS;
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// Picture Parameters for Decoding 
-//
-
-typedef struct _CUVIDPICPARAMS
-{
- int PicWidthInMbs; // Coded Frame Size
- int FrameHeightInMbs; // Coded Frame Height
- int CurrPicIdx; // Output index of the current picture
- int field_pic_flag; // 0=frame picture, 1=field picture
- int bottom_field_flag; // 0=top field, 1=bottom field (ignored if field_pic_flag=0)
- int second_field; // Second field of a complementary field pair
- // Bitstream data
- unsigned int nBitstreamDataLen; // Number of bytes in bitstream data buffer
- const unsigned char *pBitstreamData; // Ptr to bitstream data for this picture (slice-layer)
- unsigned int nNumSlices; // Number of slices in this picture
- const unsigned int *pSliceDataOffsets; // nNumSlices entries, contains offset of each slice within the bitstream data buffer
- int ref_pic_flag; // This picture is a reference picture
- int intra_pic_flag; // This picture is entirely intra coded
- unsigned int Reserved[30]; // Reserved for future use
- // Codec-specific data
- union {
- CUVIDMPEG2PICPARAMS mpeg2; // Also used for MPEG-1
- CUVIDH264PICPARAMS h264;
- CUVIDVC1PICPARAMS vc1;
- CUVIDMPEG4PICPARAMS mpeg4;
- CUVIDJPEGPICPARAMS jpeg;
- CUVIDHEVCPICPARAMS hevc;
- CUVIDVP9PICPARAMS vp9;
- unsigned int CodecReserved[1024];
- } CodecSpecific;
-} CUVIDPICPARAMS;
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// Post-processing
-//
-
-typedef struct _CUVIDPROCPARAMS
-{
- int progressive_frame; // Input is progressive (deinterlace_mode will be ignored)
- int second_field; // Output the second field (ignored if deinterlace mode is Weave)
- int top_field_first; // Input frame is top field first (1st field is top, 2nd field is bottom)
- int unpaired_field; // Input only contains one field (2nd field is invalid)
- // The fields below are used for raw YUV input
- unsigned int reserved_flags; // Reserved for future use (set to zero)
- unsigned int reserved_zero; // Reserved (set to zero)
- unsigned long long raw_input_dptr; // Input CUdeviceptr for raw YUV extensions
- unsigned int raw_input_pitch; // pitch in bytes of raw YUV input (should be aligned appropriately)
- unsigned int raw_input_format; // Reserved for future use (set to zero)
- unsigned long long raw_output_dptr; // Reserved for future use (set to zero)
- unsigned int raw_output_pitch; // Reserved for future use (set to zero)
- unsigned int Reserved[48];
- void *Reserved3[3];
-} CUVIDPROCPARAMS;
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// In order to maximize decode latencies, there should be always at least 2 pictures in the decode
-// queue at any time, in order to make sure that all decode engines are always busy.
-//
-// Overall data flow:
-// - cuvidCreateDecoder(...)
-// For each picture:
-// - cuvidDecodePicture(N)
-// - cuvidMapVideoFrame(N-4)
-// - do some processing in cuda
-// - cuvidUnmapVideoFrame(N-4)
-// - cuvidDecodePicture(N+1)
-// - cuvidMapVideoFrame(N-3)
-// ...
-// - cuvidDestroyDecoder(...)
-//
-// NOTE:
-// - In the current version, the cuda context MUST be created from a D3D device, using cuD3D9CtxCreate function.
-// For multi-threaded operation, the D3D device must also be created with the D3DCREATE_MULTITHREADED flag.
-// - There is a limit to how many pictures can be mapped simultaneously (ulNumOutputSurfaces)
-// - cuVidDecodePicture may block the calling thread if there are too many pictures pending 
-// in the decode queue
-//
-////////////////////////////////////////////////////////////////////////////////////////////////
-
-// Create/Destroy the decoder object
-extern CUresult CUDAAPI cuvidCreateDecoder(CUvideodecoder *phDecoder, CUVIDDECODECREATEINFO *pdci);
-extern CUresult CUDAAPI cuvidDestroyDecoder(CUvideodecoder hDecoder);
-
-// Decode a single picture (field or frame)
-extern CUresult CUDAAPI cuvidDecodePicture(CUvideodecoder hDecoder, CUVIDPICPARAMS *pPicParams);
-
-#if !defined(__CUVID_DEVPTR64) || defined(__CUVID_INTERNAL)
-// Post-process and map a video frame for use in cuda
-extern CUresult CUDAAPI cuvidMapVideoFrame(CUvideodecoder hDecoder, int nPicIdx,
- unsigned int *pDevPtr, unsigned int *pPitch,
- CUVIDPROCPARAMS *pVPP);
-// Unmap a previously mapped video frame
-extern CUresult CUDAAPI cuvidUnmapVideoFrame(CUvideodecoder hDecoder, unsigned int DevPtr);
-#endif
-
-#if defined(__x86_64) || defined(AMD64) || defined(_M_AMD64)
-extern CUresult CUDAAPI cuvidMapVideoFrame64(CUvideodecoder hDecoder, int nPicIdx, unsigned long long *pDevPtr,
- unsigned int *pPitch, CUVIDPROCPARAMS *pVPP);
-extern CUresult CUDAAPI cuvidUnmapVideoFrame64(CUvideodecoder hDecoder, unsigned long long DevPtr);
-#if defined(__CUVID_DEVPTR64) && !defined(__CUVID_INTERNAL)
-#define cuvidMapVideoFrame cuvidMapVideoFrame64
-#define cuvidUnmapVideoFrame cuvidUnmapVideoFrame64
-#endif
-#endif
-
-// Get the pointer to the d3d9 surface that is the decode RT
-extern CUresult CUDAAPI cuvidGetVideoFrameSurface(CUvideodecoder hDecoder, int nPicIdx, void **pSrcSurface);
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// Context-locking: to facilitate multi-threaded implementations, the following 4 functions
-// provide a simple mutex-style host synchronization. If a non-NULL context is specified
-// in CUVIDDECODECREATEINFO, the codec library will acquire the mutex associated with the given 
-// context before making any cuda calls.
-// A multi-threaded application could create a lock associated with a context handle so that
-// multiple threads can safely share the same cuda context:
-// - use cuCtxPopCurrent immediately after context creation in order to create a 'floating' context
-// that can be passed to cuvidCtxLockCreate.
-// - When using a floating context, all cuda calls should only be made within a cuvidCtxLock/cuvidCtxUnlock section.
-//
-// NOTE: This is a safer alternative to cuCtxPushCurrent and cuCtxPopCurrent, and is not related to video
-// decoder in any way (implemented as a critical section associated with cuCtx{Push|Pop}Current calls).
-
-extern CUresult CUDAAPI cuvidCtxLockCreate(CUvideoctxlock *pLock, CUcontext ctx);
-extern CUresult CUDAAPI cuvidCtxLockDestroy(CUvideoctxlock lck);
-extern CUresult CUDAAPI cuvidCtxLock(CUvideoctxlock lck, unsigned int reserved_flags);
-extern CUresult CUDAAPI cuvidCtxUnlock(CUvideoctxlock lck, unsigned int reserved_flags);
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-
-#if defined(__cplusplus)
-}
-
-// Auto-lock helper for C++ applications
-class CCtxAutoLock
-{
-private:
- CUvideoctxlock m_ctx;
-public:
- CCtxAutoLock(CUvideoctxlock ctx):m_ctx(ctx) { cuvidCtxLock(m_ctx,0); }
- ~CCtxAutoLock() { cuvidCtxUnlock(m_ctx,0); }
-};
-
-#endif /* __cplusplus */
-
-#endif // __CUDA_VIDEO_H__
-

QtAV-1.11.0.tar.gz/src/cuda/dllapi/nvcuvid.h Deleted

@@ -1,234 +0,0 @@
-/*
- * Copyright 1993-2008 NVIDIA Corporation.  All rights reserved.
- *
- * NOTICE TO USER:   
- *
- * This source code is subject to NVIDIA ownership rights under U.S. and 
- * international Copyright laws.  Users and possessors of this source code 
- * are hereby granted a nonexclusive, royalty-free license to use this code 
- * in individual and commercial software.
- *
- * NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE 
- * CODE FOR ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR 
- * IMPLIED WARRANTY OF ANY KIND.  NVIDIA DISCLAIMS ALL WARRANTIES WITH 
- * REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF 
- * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
- * IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL, 
- * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS 
- * OF USE, DATA OR PROFITS,  WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE 
- * OR OTHER TORTIOUS ACTION,  ARISING OUT OF OR IN CONNECTION WITH THE USE 
- * OR PERFORMANCE OF THIS SOURCE CODE.  
- *
- * U.S. Government End Users.   This source code is a "commercial item" as 
- * that term is defined at  48 C.F.R. 2.101 (OCT 1995), consisting  of 
- * "commercial computer  software"  and "commercial computer software 
- * documentation" as such terms are  used in 48 C.F.R. 12.212 (SEPT 1995) 
- * and is provided to the U.S. Government only as a commercial end item.  
- * Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through 
- * 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the 
- * source code with only those rights set forth herein. 
- *
- * Any use of this source code in individual and commercial software must 
- * include, in the user documentation and internal comments to the code,
- * the above Disclaimer and U.S. Government End Users Notice.
- */
-
-#if !defined(__NVCUVID_H__)
-#define __NVCUVID_H__
-
-#include "cuviddec.h"
-
-#if defined(__cplusplus)
-extern "C" {
-#endif /* __cplusplus */
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// High-level helper APIs for video sources
-//
-
-typedef void *CUvideosource;
-typedef void *CUvideoparser;
-typedef long long CUvideotimestamp;
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// video data structures
-//
-
-// Video Source State
-typedef enum {
-    cudaVideoState_Error   = -1,    // Error state (invalid source)
-    cudaVideoState_Stopped = 0,     // Source is stopped (or reached end-of-stream)
-    cudaVideoState_Started = 1      // Source is running and delivering data
-} cudaVideoState;
-
-// Audio compression
-typedef enum {
-    cudaAudioCodec_MPEG1=0,         // MPEG-1 Audio
-    cudaAudioCodec_MPEG2,           // MPEG-2 Audio
-    cudaAudioCodec_MP3,             // MPEG-1 Layer III Audio
-    cudaAudioCodec_AC3,             // Dolby Digital (AC3) Audio
-    cudaAudioCodec_LPCM             // PCM Audio
-} cudaAudioCodec;
-
-
-// Video format
-typedef struct
-{
-    cudaVideoCodec codec;           // Compression format
-    struct {
-        unsigned int numerator;     // frame rate numerator   (0 = unspecified or variable frame rate)
-        unsigned int denominator;   // frame rate denominator (0 = unspecified or variable frame rate)
-    } frame_rate;                   // frame rate = numerator / denominator (for example: 30000/1001)
-    unsigned char progressive_sequence; // 0=interlaced, 1=progressive
-    unsigned char bit_depth_luma_minus8;
-    unsigned char bit_depth_chroma_minus8;
-    unsigned char reserved1;
-    unsigned int coded_width;       // coded frame width
-    unsigned int coded_height;      // coded frame height 
-    struct {                        // area of the frame that should be displayed
-        int left;                   // typical example:
-        int top;                    //   coded_width = 1920, coded_height = 1088
-        int right;                  //   display_area = { 0,0,1920,1080 }
-        int bottom;
-    } display_area;
-    cudaVideoChromaFormat chroma_format;    // Chroma format
-    unsigned int bitrate;           // video bitrate (bps, 0=unknown)
-    struct {                        // Display Aspect Ratio = x:y (4:3, 16:9, etc)
-        int x;
-        int y;
-    } display_aspect_ratio;
-    struct {
-        unsigned char video_format          : 3;
-        unsigned char video_full_range_flag : 1;
-        unsigned char reserved_zero_bits    : 4;
-        unsigned char color_primaries;
-        unsigned char transfer_characteristics;
-        unsigned char matrix_coefficients;
-    } video_signal_description;
-    unsigned int seqhdr_data_length;          // Additional bytes following (CUVIDEOFORMATEX)
-} CUVIDEOFORMAT;
-
-// Video format including raw sequence header information
-typedef struct
-{
-    CUVIDEOFORMAT format;
-    unsigned char raw_seqhdr_data[1024];
-} CUVIDEOFORMATEX;
-
-
-// Audio Format
-typedef struct
-{
-    cudaAudioCodec codec;       // Compression format
-    unsigned int channels;      // number of audio channels
-    unsigned int samplespersec; // sampling frequency
-    unsigned int bitrate;       // For uncompressed, can also be used to determine bits per sample
-    unsigned int reserved1;
-    unsigned int reserved2;
-} CUAUDIOFORMAT;
-
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// video source
-//
-
-// Data packet
-typedef enum {
-    CUVID_PKT_ENDOFSTREAM   = 0x01,   // Set when this is the last packet for this stream
-    CUVID_PKT_TIMESTAMP     = 0x02,   // Timestamp is valid
-    CUVID_PKT_DISCONTINUITY = 0x04    // Set when a discontinuity has to be signalled
-} CUvideopacketflags;
-
-typedef struct _CUVIDSOURCEDATAPACKET
-{
-    unsigned long flags;            // Combination of CUVID_PKT_XXX flags
-    unsigned long payload_size;     // number of bytes in the payload (may be zero if EOS flag is set)
-    const unsigned char *payload;   // Pointer to packet payload data (may be NULL if EOS flag is set)
-    CUvideotimestamp timestamp;     // Presentation timestamp (10MHz clock), only valid if CUVID_PKT_TIMESTAMP flag is set
-} CUVIDSOURCEDATAPACKET;
-
-// Callback for packet delivery
-typedef int (CUDAAPI *PFNVIDSOURCECALLBACK)(void *, CUVIDSOURCEDATAPACKET *);
-
-typedef struct _CUVIDSOURCEPARAMS
-{
-    unsigned int ulClockRate;   // Timestamp units in Hz (0=default=10000000Hz)
-    unsigned int uReserved1[7]; // Reserved for future use - set to zero
-    void *pUserData;    // Parameter passed in to the data handlers
-    PFNVIDSOURCECALLBACK pfnVideoDataHandler;   // Called to deliver audio packets
-    PFNVIDSOURCECALLBACK pfnAudioDataHandler;   // Called to deliver video packets
-    void *pvReserved2[8];   // Reserved for future use - set to NULL
-} CUVIDSOURCEPARAMS;
-
-typedef enum {
-    CUVID_FMT_EXTFORMATINFO = 0x100     // Return extended format structure (CUVIDEOFORMATEX)
-} CUvideosourceformat_flags;
-
-#if !defined(__APPLE__)
-// Video file source
-CUresult CUDAAPI cuvidCreateVideoSource(CUvideosource *pObj, const char *pszFileName, CUVIDSOURCEPARAMS *pParams);
-CUresult CUDAAPI cuvidCreateVideoSourceW(CUvideosource *pObj, const wchar_t *pwszFileName, CUVIDSOURCEPARAMS *pParams);
-CUresult CUDAAPI cuvidDestroyVideoSource(CUvideosource obj);
-CUresult CUDAAPI cuvidSetVideoSourceState(CUvideosource obj, cudaVideoState state);
-cudaVideoState CUDAAPI cuvidGetVideoSourceState(CUvideosource obj);
-CUresult CUDAAPI cuvidGetSourceVideoFormat(CUvideosource obj, CUVIDEOFORMAT *pvidfmt, unsigned int flags);
-CUresult CUDAAPI cuvidGetSourceAudioFormat(CUvideosource obj, CUAUDIOFORMAT *paudfmt, unsigned int flags);
-#endif
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-//
-// Video parser
-//
-
-typedef struct _CUVIDPARSERDISPINFO
-{
-    int picture_index;
-    int progressive_frame;
-    int top_field_first;
-    int repeat_first_field; // Number of additional fields (1=ivtc, 2=frame doubling, 4=frame tripling, -1=unpaired field)
-    CUvideotimestamp timestamp;
-} CUVIDPARSERDISPINFO;
-
-//
-// Parser callbacks
-// The parser will call these synchronously from within cuvidParseVideoData(), whenever a picture is ready to
-// be decoded and/or displayed.
-//
-typedef int (CUDAAPI *PFNVIDSEQUENCECALLBACK)(void *, CUVIDEOFORMAT *);
-typedef int (CUDAAPI *PFNVIDDECODECALLBACK)(void *, CUVIDPICPARAMS *);
-typedef int (CUDAAPI *PFNVIDDISPLAYCALLBACK)(void *, CUVIDPARSERDISPINFO *);
-
-typedef struct _CUVIDPARSERPARAMS
-{
-    cudaVideoCodec CodecType;       // cudaVideoCodec_XXX
-    unsigned int ulMaxNumDecodeSurfaces;    // Max # of decode surfaces (parser will cycle through these)
-    unsigned int ulClockRate;       // Timestamp units in Hz (0=default=10000000Hz)
-    unsigned int ulErrorThreshold;  // % Error threshold (0-100) for calling pfnDecodePicture (100=always call pfnDecodePicture even if picture bitstream is fully corrupted)
-    unsigned int ulMaxDisplayDelay; // Max display queue delay (improves pipelining of decode with display) - 0=no delay (recommended values: 2..4)
-    unsigned int uReserved1[5]; // Reserved for future use - set to 0
-    void *pUserData;        // User data for callbacks
-    PFNVIDSEQUENCECALLBACK pfnSequenceCallback; // Called before decoding frames and/or whenever there is a format change
-    PFNVIDDECODECALLBACK pfnDecodePicture;      // Called when a picture is ready to be decoded (decode order)
-    PFNVIDDISPLAYCALLBACK pfnDisplayPicture;    // Called whenever a picture is ready to be displayed (display order)
-    void *pvReserved2[7];           // Reserved for future use - set to NULL
-    CUVIDEOFORMATEX *pExtVideoInfo; // [Optional] sequence header data from system layer
-} CUVIDPARSERPARAMS;
-
-
-CUresult CUDAAPI cuvidCreateVideoParser(CUvideoparser *pObj, CUVIDPARSERPARAMS *pParams);
-CUresult CUDAAPI cuvidParseVideoData(CUvideoparser obj, CUVIDSOURCEDATAPACKET *pPacket);
-CUresult CUDAAPI cuvidDestroyVideoParser(CUvideoparser obj);
-
-
-////////////////////////////////////////////////////////////////////////////////////////////////
-
-#if defined(__cplusplus)
-}
-#endif /* __cplusplus */
-
-#endif // __NVCUVID_H__
-

QtAV-1.11.0.tar.gz/src/opengl/Geometry.h Deleted

@@ -1,129 +0,0 @@
-/******************************************************************************
- QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
-
-* This file is part of QtAV (from 2016)
-
- This library is free software; you can redistribute it and/or
- modify it under the terms of the GNU Lesser General Public
- License as published by the Free Software Foundation; either
- version 2.1 of the License, or (at your option) any later version.
-
- This library is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- Lesser General Public License for more details.
-
- You should have received a copy of the GNU Lesser General Public
- License along with this library; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
-******************************************************************************/
-#ifndef QTAV_GEOMETRY_H
-#define QTAV_GEOMETRY_H
-#include <QtCore/QRectF>
-#include <QtCore/QVector>
-#include <QtAV/QtAV_Global.h>
-
-// TODO: generate vertex/fragment shader code from Geometry.attributes()
-namespace QtAV {
-
-enum DataType { //equals to GL_BYTE etc.
- TypeByte = 0x1400,
- TypeUnsignedByte = 0x1401,
- TypeShort = 0x1402,
- TypeUnsignedShort = 0x1403,
- TypeInt = 0x1404,
- TypeUnsignedInt = 0x1405,
- TypeFloat = 0x1406
-};
-
-class Attribute {
- bool m_normalize;
- DataType m_type;
- int m_tupleSize, m_offset;
- QByteArray m_name;
-public:
- Attribute(DataType type = TypeFloat, int tupleSize = 0, int offset = 0, bool normalize = true);
- Attribute(const QByteArray& name, DataType type = TypeFloat, int tupleSize = 0, int offset = 0, bool normalize = true);
- QByteArray name() const {return m_name;}
- DataType type() const {return m_type;}
- int tupleSize() const {return m_tupleSize;}
- int offset() const {return m_offset;}
- bool normalize() const {return m_normalize;}
-};
-#ifndef QT_NO_DEBUG_STREAM
-Q_AV_EXPORT QDebug operator<<(QDebug debug, const Attribute &a);
-#endif
-
-/*!
- * \brief The Geometry class
- * \code
- * foreach (const Attribute& a, g->attributes()) {
- * program()->setAttributeBuffer(a.name(), a.type(), a.offset(), a.tupleSize(), g->stride());
- * }
- * \endcode
- */
-class Geometry {
-public:
- /// Strip or Triangles is preferred by ANGLE. The values are equal to opengl
- enum PrimitiveType {
- Triangles = 0x0004,
- TriangleStrip = 0x0005, //default
- TriangleFan = 0x0006, // Not recommended
- };
- Geometry(int vertexCount = 0, int indexCount = 0, DataType indexType = TypeUnsignedShort);
- virtual ~Geometry() {}
- PrimitiveType primitiveType() const {return m_primitive;}
- void setPrimitiveType(PrimitiveType value) { m_primitive = value;}
- int vertexCount() const {return m_vcount;}
- void setVertexCount(int value) {m_vcount = value;} // TODO: remove, or allocate data here
- // TODO: setStride and no virtual
- virtual int stride() const = 0;
- // TODO: add/set/remove attributes()
- virtual const QVector<Attribute>& attributes() const = 0;
- void* vertexData() { return m_vdata.data();}
- const void* vertexData() const { return m_vdata.constData();}
- void* indexData() { return m_icount > 0 ? m_idata.data() : NULL;}
- const void* indexData() const { return m_icount > 0 ? m_idata.constData() : NULL;}
- int indexCount() const { return m_icount;}
- // GL_UNSIGNED_BYTE/SHORT/INT
- DataType indexType() const {return m_itype;}
- void setIndexType(DataType value) { m_itype = value;}
- /*!
- * \brief allocate
- * Call allocate() when all parameters are set. vertexData() may change
- */
- void allocate(int nbVertex, int nbIndex = 0);
-protected:
- PrimitiveType m_primitive;
- DataType m_itype;
- int m_vcount;
- int m_icount;
- QByteArray m_vdata;
- QByteArray m_idata;
-};
-
-class TexturedGeometry : public Geometry {
-public:
- TexturedGeometry();
- /*!
- * \brief setTextureCount
- * sometimes we needs more than 1 texture coordinates, for example we have to set rectangle texture
- * coordinates for each plane.
- */
- void setTextureCount(int value);
- int textureCount() const;
- void setPoint(int index, const QPointF& p, const QPointF& tp, int texIndex = 0);
- void setGeometryPoint(int index, const QPointF& p);
- void setTexturePoint(int index, const QPointF& tp, int texIndex = 0);
- void setRect(const QRectF& r, const QRectF& tr, int texIndex = 0);
- void setGeometryRect(const QRectF& r);
- void setTextureRect(const QRectF& tr, int texIndex = 0);
- int stride() const Q_DECL_OVERRIDE { return 2*sizeof(float)*(textureCount()+1); }
- const QVector<Attribute>& attributes() const Q_DECL_OVERRIDE;
-private:
- int nb_tex;
- QVector<Attribute> a;
-};
-} //namespace QtAV
-#endif //QTAV_GEOMETRY_H

QtAV-1.11.0.tar.gz/src/opengl/GeometryRenderer.h Deleted

@@ -1,58 +0,0 @@
-/******************************************************************************
- QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
-
-* This file is part of QtAV (from 2016)
-
- This library is free software; you can redistribute it and/or
- modify it under the terms of the GNU Lesser General Public
- License as published by the Free Software Foundation; either
- version 2.1 of the License, or (at your option) any later version.
-
- This library is distributed in the hope that it will be useful,
- but WITHOUT ANY WARRANTY; without even the implied warranty of
- MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- Lesser General Public License for more details.
-
- You should have received a copy of the GNU Lesser General Public
- License along with this library; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
-******************************************************************************/
-#ifndef QTAV_GEOMETRYRENDERER_H
-#define QTAV_GEOMETRYRENDERER_H
-#include "opengl/Geometry.h"
-#include "opengl/OpenGLHelper.h"
-#define QT_VAO (QT_VERSION >= QT_VERSION_CHECK(5, 1, 0))
-#if QT_VAO
-#include <QtGui/QOpenGLVertexArrayObject>
-#endif //QT_VAO
-
-QT_BEGIN_NAMESPACE
-class QOpenGLShaderProgram;
-QT_END_NAMESPACE
-
-namespace QtAV {
-class GeometryRenderer
-{
-public:
- GeometryRenderer();
- void setShaderProgram(QOpenGLShaderProgram *sp);
- /// assume attributes are bound in the order 0, 1, 2,....
- /// null geometry: release vao/vbo
- bool updateBuffers(Geometry* g = NULL);
- void bindBuffers(Geometry* g);
- void render(Geometry* g);
- void unbindBuffers(Geometry *g);
-private:
- QOpenGLShaderProgram *program;
- // TODO: setFeatures(VAO|VBO)
- bool try_vbo; // check environment var and opengl support
- bool try_vao;
- QOpenGLBuffer vbo; //VertexBuffer
-#if QT_VAO
- QOpenGLVertexArrayObject vao;
-#endif //QT_VAO
-};
-
-} //namespace QtAV
-#endif //QTAV_GEOMETRYRENDERER_H

QtAV-1.11.0.tar.gz/.gitignore -> QtAV-1.12.0.tar.gz/.gitignore Changed

QtAV-1.11.0.tar.gz/.qmake.conf -> QtAV-1.12.0.tar.gz/.qmake.conf Changed

QtAV-1.12.0.tar.gz/CMakeLists.txt Added

@@ -0,0 +1,126 @@
+cmake_minimum_required(VERSION 2.8.11 FATAL_ERROR)
+set(QTAV_MAJOR 1)
+set(QTAV_MINOR 11)
+set(QTAV_PATCH 0)
+set(PROJECT_VERSION ${QTAV_MAJOR}.${QTAV_MINOR}.${QTAV_PATCH})
+set(SO_VERSION ${QTAV_MAJOR})
+
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+if(POLICY CMP0063) # visibility. since 3.3
+  cmake_policy(SET CMP0063 NEW)
+endif()
+set(CMAKE_CXX_VISIBILITY_PRESET hidden) #use with -fdata-sections -ffunction-sections to reduce target size
+set(CMAKE_VISIBILITY_INLINES_HIDDEN ON)
+
+
+option(BUILD_EXAMPLES "Build examples" ON)
+option(BUILD_PLAYERS "Build players" ON)
+option(BUILD_TESTS "Build tests" ON)
+option(BUILD_QT5OPENGL "Build with Qt5 OpenGL module" ON)
+
+list(APPEND CMAKE_FIND_ROOT_PATH ${QTDIR})
+
+find_package(Qt5Core REQUIRED)
+find_package(Qt5Gui REQUIRED)
+get_target_property(qmake Qt5::qmake LOCATION)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_HEADERS
+    OUTPUT_VARIABLE QT_INSTALL_HEADERS
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_LIBS
+    OUTPUT_VARIABLE QT_INSTALL_LIBS
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_BINS
+    OUTPUT_VARIABLE QT_INSTALL_BINS
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_QML
+    OUTPUT_VARIABLE QT_INSTALL_QML
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_PREFIX
+    OUTPUT_VARIABLE QT_INSTALL_PREFIX
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${QT5_CFLAGS}")
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+
+if(POLICY CMP0063) # visibility. since 3.3
+  cmake_policy(SET CMP0063 NEW)
+endif()
+set(CMAKE_CXX_VISIBILITY_PRESET hidden) #use with -fdata-sections -ffunction-sections to reduce target size
+set(CMAKE_VISIBILITY_INLINES_HIDDEN ON)
+
+# Find includes in corresponding build directories
+set(CMAKE_INCLUDE_CURRENT_DIR ON) # for .moc
+# Instruct CMake to run moc automatically when needed.
+set(CMAKE_AUTOMOC ON)
+if(NOT CMAKE_INSTALL_PREFIX_INITIALIZED_TO_DEFAULT)
+  set(QTAV_INSTALL_HEADERS ${CMAKE_INSTALL_PREFIX}/include)
+  set(QTAV_INSTALL_LIBS ${CMAKE_INSTALL_PREFIX}/lib)
+  set(QTAV_INSTALL_BINS ${CMAKE_INSTALL_PREFIX}/bin)
+  set(QTAV_INSTALL_QML ${CMAKE_INSTALL_PREFIX}/qml)
+else()
+  set(CMAKE_INSTALL_PREFIX ${QT_INSTALL_PREFIX} CACHE PATH "default install path" FORCE)
+  set(QTAV_INSTALL_HEADERS ${QT_INSTALL_HEADERS})
+  set(QTAV_INSTALL_LIBS ${QT_INSTALL_LIBS})
+  set(QTAV_INSTALL_BINS ${QT_INSTALL_BINS})
+  set(QTAV_INSTALL_QML ${QT_INSTALL_QML})
+endif()
+
+message(STATUS "Qt version: ${Qt5Core_VERSION_STRING}")
+message(STATUS "Qt prefix: ${QT_INSTALL_PREFIX}")
+message(STATUS "QtAV headers prefix: ${QTAV_INSTALL_HEADERS}")
+message(STATUS "QtAV libs prefix: ${QTAV_INSTALL_LIBS}")
+message(STATUS "QtAV bins prefix: ${QTAV_INSTALL_BINS}")
+message(STATUS "QtAV qml prefix: ${QTAV_INSTALL_QML}")
+
+set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
+set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib)
+set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib)
+
+#set(CMAKE_DEBUG_POSTFIX d)
+
+install(FILES
+  cmake/FindQtAV.cmake
+  DESTINATION ${QTAV_INSTALL_LIBS}/cmake
+)
+
+if(CMAKE_GENERATOR MATCHES "Visual Studio.*")
+  set(UCRT_INCLUDE $ENV{UniversalCRTSDKDir}Include\\$ENV{UCRTVersion}\\ucrt)
+  set(VC_ARCH $ENV{Platform})
+  if(NOT VC_ARCH)
+    set(VC_ARCH x86)
+  endif()
+  set(UCRT_LIB $ENV{UniversalCRTSDKDir}Lib\\$ENV{UCRTVersion}\\ucrt\\${VC_ARCH})
+  if(EXISTS ${UCRT_INCLUDE})
+  message("VS project. ucrt: ${UCRT_LIB}")
+    include_directories(${UCRT_INCLUDE})
+    link_libraries(${CMAKE_LIBRARY_PATH_FLAG}${UCRT_LIB})
+  endif()
+endif()
+
+add_subdirectory(src)
+find_package(Qt5Widgets)
+if(Qt5Widgets_FOUND)
+  add_subdirectory(widgets)
+endif()
+find_package(Qt5 COMPONENTS Qml Quick)
+if(Qt5Qml_FOUND AND Qt5Quick_FOUND)
+  add_subdirectory(qml)
+endif()
+
+if(BUILD_EXAMPLES OR BUILD_PLAYERS)
+  add_subdirectory(examples)
+endif()
+
+

QtAV-1.11.0.tar.gz/Changelog -> QtAV-1.12.0.tar.gz/Changelog Changed

QtAV-1.11.0.tar.gz/README.md -> QtAV-1.12.0.tar.gz/README.md Changed

QtAV-1.11.0.tar.gz/appveyor.yml -> QtAV-1.12.0.tar.gz/appveyor.yml Changed

QtAV-1.12.0.tar.gz/cmake Added

QtAV-1.12.0.tar.gz/cmake/FindQtAV.cmake Added

@@ -0,0 +1,56 @@
+# - Try to find the QtAV library
+#
+# Once done this will define
+#
+#  QTAV_FOUND        - system has libqtav
+#  QTAV_INCLUDE_DIRS - the libqtav include directory
+#  QTAV_LIBRARIES    - Link these to use libqtav
+
+find_package(Qt5 QUIET REQUIRED NO_MODULE COMPONENTS Core)
+
+get_target_property(qmake Qt5::qmake LOCATION)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_HEADERS
+    OUTPUT_VARIABLE QT_INSTALL_HEADERS
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+execute_process(
+    COMMAND ${qmake} -query QT_INSTALL_LIBS
+    OUTPUT_VARIABLE QT_INSTALL_LIBS
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+)
+
+find_path(QTAV_INCLUDE_DIR NAMES QtAV.h
+    HINTS ${QT_INSTALL_HEADERS}
+    PATH_SUFFIXES QtAV
+)
+find_library(QTAV_LIBRARY NAMES QtAV QtAV1
+    HINTS ${QT_INSTALL_LIBS}
+)
+
+find_path(QTAVWIDGETS_INCLUDE_DIR NAMES QtAVWidgets.h
+    HINTS ${QT_INSTALL_HEADERS}
+    PATH_SUFFIXES QtAVWidgets
+)
+find_library(QTAVWIDGETS_LIBRARY NAMES QtAVWidgets QtAVWidgets1
+    HINTS ${QT_INSTALL_LIBS}
+)
+
+set(QTAV_INCLUDE_DIRS ${QTAV_INCLUDE_DIR} ${QTAV_INCLUDE_DIR}/..)
+set(QTAV_LIBRARIES ${QTAV_LIBRARY})
+if(NOT QTAVWIDGETS_INCLUDE_DIR MATCHES "QTAVWIDGETS_INCLUDE_DIR-NOTFOUND")
+    set(QTAVWIDGETS_INCLUDE_DIRS ${QTAVWIDGETS_INCLUDE_DIR} ${QTAVWIDGETS_INCLUDE_DIR}/.. ${QTAV_INCLUDE_DIRS})
+endif()
+if(NOT QTAV_LIBRARIES MATCHES "QTAV_LIBRARIES-NOTFOUND")
+    set(QTAVWIDGETS_LIBRARIES ${QTAVWIDGETS_LIBRARY} ${QTAV_LIBRARY})
+endif()
+
+find_package(PackageHandleStandardArgs REQUIRED)
+find_package_handle_standard_args(QtAV REQUIRED_VARS QTAV_LIBRARIES QTAV_INCLUDE_DIRS)
+mark_as_advanced(QTAV_INCLUDE_DIRS QTAV_LIBRARIES QTAVWIDGETS_INCLUDE_DIRS QTAVWIDGETS_LIBRARIES)
+
+message("QtAV_FOUND                 = ${QTAV_FOUND}")
+message("QTAV_INCLUDE_DIRS          = ${QTAV_INCLUDE_DIRS}")
+message("QTAV_LIBRARIES             = ${QTAV_LIBRARIES}")
+message("QTAVWIDGETS_INCLUDE_DIRS   = ${QTAVWIDGETS_INCLUDE_DIRS}")
+message("QTAVWIDGETS_LIBRARIES      = ${QTAVWIDGETS_LIBRARIES}")

QtAV-1.12.0.tar.gz/cmake/QtAV.rc.in Added

@@ -0,0 +1,35 @@
+#include "winver.h"
+#include "@CMAKE_SOURCE_DIR@/src/QtAV/version.h"
+IDI_ICON1               ICON    DISCARDABLE     "@CMAKE_SOURCE_DIR@/src/QtAV.ico"
+
+VS_VERSION_INFO VERSIONINFO
+ FILEVERSION QTAV_MAJOR,QTAV_MINOR,QTAV_PATCH,0
+ PRODUCTVERSION QTAV_MAJOR,QTAV_MINOR,QTAV_PATCH,0
+#ifdef _DEBUG
+ FILEFLAGS VS_FF_DEBUG
+#else
+ FILEFLAGS 0x0L
+#endif
+ FILEFLAGSMASK 0x3fL
+ FILEOS VOS_NT_WINDOWS32
+ FILETYPE VFT_DLL
+ FILESUBTYPE 0x0L
+BEGIN
+    BLOCK "StringFileInfo"
+    BEGIN
+        BLOCK "000004b0"
+        BEGIN
+            VALUE "CompanyName", "Shanghai University->S3 Graphics->Deepin->PPTV | wbsecg1@gmail.com"
+            VALUE "FileDescription", "QtAV Multimedia framework. http://qtav.org"
+            VALUE "FileVersion", QTAV_VERSION_STR ".0"
+            VALUE "LegalCopyright", "Copyright (C) 2012-2017 WangBin, wbsecg1@gmail.com"
+            VALUE "InternalName", "@MODULE@"
+            VALUE "ProductName", "@MODULE@"
+            VALUE "ProductVersion", QTAV_VERSION_STR ".0"
+        END
+    END
+    BLOCK "VarFileInfo"
+    BEGIN
+        VALUE "Translation", 0x0, 1200
+    END
+END

QtAV-1.11.0.tar.gz/common.pri -> QtAV-1.12.0.tar.gz/common.pri Changed

QtAV-1.11.0.tar.gz/debian/changelog -> QtAV-1.12.0.tar.gz/debian/changelog Changed

QtAV-1.11.0.tar.gz/debian/control -> QtAV-1.12.0.tar.gz/debian/control Changed

QtAV-1.11.0.tar.gz/debian/ubuntu.sh -> QtAV-1.12.0.tar.gz/debian/ubuntu.sh Changed

@@ -1,4 +1,5 @@
 CHANGELOG_BAK=/tmp/qtav_changelog
+CONTROL_BAK=/tmp/qtav_control
 mkchangelog() {
 cat >debian/changelog<<EOF
 qtav ($1) $2; urgency=low
@@ -11,14 +12,21 @@
 EOF
 }
 
-DISTRIBUTIONS=(trusty vivid wily xenial)
+DISTRIBUTIONS=(trusty vivid wily xenial yakkety zesty)
 DATE=`date -d @$(git log -n1 --format="%at") +%Y%m%d`
+idx=0
 for D in ${DISTRIBUTIONS[@]}; do
- git checkout -- debian/changelog
+ git checkout -- debian/changelog debian/control
+ cp -avf debian/control $CONTROL_BAK
 cp -avf debian/changelog $CHANGELOG_BAK
- VER=1.11.0~`git log -1 --pretty=format:"git${DATE}.%h~${D}" 2> /dev/null`
+ VER=1.12.0~`git log -1 --pretty=format:"git${DATE}.%h~${D}" 2> /dev/null`
 mkchangelog $VER $D
+ if [ $idx -gt 3 ]; then
+ sed -i 's,qtdeclarative5-controls-plugin,qml-module-qtquick-controls,g' debian/control
+ fi
 debuild -S -sa
 dput -f ppa:wbsecg1/qtav ../qtav_${VER}_source.changes
 cp -avf $CHANGELOG_BAK debian/changelog
+ cp -avf $CONTROL_BAK debian/control
+ idx=$((idx+1))
 done

QtAV-1.12.0.tar.gz/examples/CMakeLists.txt Added

@@ -0,0 +1,178 @@
+find_package(Qt5Sql REQUIRED)
+if(WIN32)
+  set(EXE_TYPE WIN32)
+elseif(APPLE)
+  #set(EXE_TYPE MACOSX_BUNDLE)
+endif()
+set(COMMON_SRC
+  common/common.cpp
+  common/Config.cpp
+  common/qoptions.cpp
+)
+set(COMMON_HEADERS
+  common/common.h
+  common/Config.h
+  common/qoptions.h
+  common/ScreenSaver.h
+  common/common_export.h
+)
+if(NOT IOS)
+  list(APPEND COMMON_SRC common/ScreenSaver.cpp)
+  if(APPLE)
+    list(APPEND COMMON_LIBS "-framework CoreServices")
+  endif()
+endif()
+
+SET(COMMON_QRC common/theme/theme.qrc)
+SOURCE_GROUP("Resources" FILES ${COMMON_QRC})
+qt5_add_resources(COMMON_RES ${COMMON_QRC})
+set_source_files_properties(${COMMON_RES} PROPERTIES GENERATED ON)
+
+# add HEADERS for moc
+add_library(common STATIC ${COMMON_SRC} ${COMMON_RES} ${COMMON_HEADERS})
+target_link_libraries(common
+  LINK_PUBLIC Qt5::Core Qt5::Gui ${COMMON_LIBS}
+  LINK_PRIVATE Qt5::Sql
+)
+target_compile_definitions(common PUBLIC -DBUILD_COMMON_STATIC)
+target_include_directories(common PUBLIC ${CMAKE_CURRENT_SOURCE_DIR})
+
+set(PLAYER_SRC
+    player/main.cpp
+    player/MainWindow.cpp
+    player/ClickableMenu.cpp
+    player/StatisticsView.cpp
+    player/Slider.cpp
+    player/TVView.cpp
+    player/EventFilter.cpp
+    player/config/ConfigDialog.cpp
+    player/config/ConfigPageBase.cpp
+    player/config/CaptureConfigPage.cpp
+    player/config/VideoEQConfigPage.cpp
+    player/config/DecoderConfigPage.cpp
+    player/config/MiscPage.cpp
+    player/filters/OSD.cpp
+    player/filters/OSDFilter.cpp
+    player/playlist/PlayListModel.cpp
+    player/playlist/PlayListItem.cpp
+    player/playlist/PlayListDelegate.cpp
+    player/playlist/PlayList.cpp
+    player/config/PropertyEditor.cpp
+    player/config/AVFormatConfigPage.cpp
+    player/config/AVFilterConfigPage.cpp
+    player/config/ShaderPage.cpp
+    player/filters/AVFilterSubtitle.cpp
+)
+set(PLAYER_HEADERS
+    player/MainWindow.h
+    player/ClickableMenu.h
+    player/StatisticsView.h
+    player/Slider.h
+    player/TVView.h
+    player/EventFilter.h
+    player/config/ConfigDialog.h
+    player/config/ConfigPageBase.h
+    player/config/CaptureConfigPage.h
+    player/config/VideoEQConfigPage.h
+    player/config/DecoderConfigPage.h
+    player/config/MiscPage.h
+    player/filters/OSD.h
+    player/filters/OSDFilter.h
+    player/playlist/PlayListModel.h
+    player/playlist/PlayListItem.h
+    player/playlist/PlayListDelegate.h
+    player/playlist/PlayList.h
+    player/config/PropertyEditor.h
+    player/config/AVFormatConfigPage.h
+    player/config/AVFilterConfigPage.h
+    player/config/ShaderPage.h
+    player/filters/AVFilterSubtitle.h
+)
+
+SET(PLAYER_QRC player/res/player.qrc)
+SOURCE_GROUP("Resources" FILES ${PLAYER_QRC})
+qt5_add_resources(PLAYER_RES ${PLAYER_QRC})
+set_source_files_properties(${PLAYER_RES} PROPERTIES GENERATED ON)
+
+if(Qt5Quick_FOUND)
+  set(QMLPLAYER_QRC QMLPlayer/qmlplayer.qrc)
+  qt5_add_resources(QMLPLAYER_RES ${QMLPLAYER_QRC})
+  set_source_files_properties(${QMLPLAYER_RES} PROPERTIES GENERATED ON)
+  set(MODULE QMLPlayer)
+  if(WIN32)
+    set(RC_FILE ${CMAKE_CURRENT_BINARY_DIR}/${MODULE}.rc)
+    configure_file(${CMAKE_SOURCE_DIR}/cmake/QtAV.rc.in ${RC_FILE})
+  endif()
+  add_executable(QMLPlayer ${EXE_TYPE}
+      QMLPlayer/main.cpp
+      QMLPlayer/qtquick2applicationviewer/qtquick2applicationviewer.cpp
+      QMLPlayer/qtquick2applicationviewer/qtquick2applicationviewer.h
+      ${QMLPLAYER_RES}
+      ${RC_FILE}
+      )
+  target_include_directories(QMLPlayer PRIVATE QMLPlayer/qtquick2applicationviewer)
+  target_link_libraries(QMLPlayer Qt5::Quick common)
+  install(TARGETS QMLPlayer
+    RUNTIME DESTINATION ${QTAV_INSTALL_BINS}
+  )
+endif()
+if(Qt5Widgets_FOUND)
+  set(MODULE Player)
+  if(WIN32)
+    set(RC_FILE ${CMAKE_CURRENT_BINARY_DIR}/${MODULE}.rc)
+    configure_file(${CMAKE_SOURCE_DIR}/cmake/QtAV.rc.in ${RC_FILE})
+  endif()
+  add_executable(Player ${EXE_TYPE} ${PLAYER_SRC} ${PLAYER_HEADERS} ${PLAYER_RES} ${RC_FILE})
+  target_link_libraries(Player QtAVWidgets common)
+
+  install(TARGETS Player
+    RUNTIME DESTINATION ${QTAV_INSTALL_BINS}
+  )
+  if(BUILD_EXAMPLES)
+    SET(FILTERS_QRC filters/res.qrc)
+    SOURCE_GROUP("Resources" FILES ${FILTERS_QRC})
+    qt5_add_resources(FILTERS_RES ${FILTERS_QRC})
+    set_source_files_properties(${FILTERS_RES} PROPERTIES GENERATED ON)
+    add_executable(filters filters/main.cpp filters/SimpleFilter.cpp ${FILTERS_RES})
+    target_link_libraries(filters QtAVWidgets)
+
+    add_executable(glslfilter glslfilter/main.cpp)
+    target_link_libraries(glslfilter QtAVWidgets)
+
+    add_executable(shader shader/main.cpp)
+    target_link_libraries(shader QtAVWidgets)
+
+    add_executable(sharedoutput sharedoutput/main.cpp sharedoutput/widget.cpp)
+    target_link_libraries(sharedoutput QtAVWidgets)
+
+    add_executable(simpleplayer simpleplayer/main.cpp simpleplayer/playerwindow.cpp)
+    target_link_libraries(simpleplayer QtAVWidgets)
+
+    add_executable(videocapture videocapture/main.cpp videocapture/playerwindow.cpp)
+    target_link_libraries(videocapture QtAVWidgets)
+
+    add_executable(videographicsitem videographicsitem/main.cpp videographicsitem/videoplayer.cpp)
+    target_link_libraries(videographicsitem QtAVWidgets)
+
+    add_executable(videogroup videogroup/main.cpp videogroup/videogroup.cpp)
+    target_link_libraries(videogroup QtAVWidgets)
+
+    add_executable(videowall videowall/main.cpp videowall/VideoWall.cpp)
+    target_link_libraries(videowall QtAVWidgets)
+
+    add_executable(simpletranscode simpletranscode/main.cpp)
+    target_link_libraries(simpletranscode QtAV)
+  endif()
+endif()
+
+if(BUILD_EXAMPLES)
+  add_executable(audiopipeline audiopipeline/main.cpp)
+  target_link_libraries(audiopipeline QtAV)
+
+  add_executable(framereader framereader/main.cpp)
+  target_link_libraries(framereader QtAV)
+
+  add_executable(window window/main.cpp)
+  target_link_libraries(window QtAV)
+endif()
+

QtAV-1.11.0.tar.gz/examples/QMLPlayer/QMLPlayer.pro -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/QMLPlayer.pro Changed

QtAV-1.11.0.tar.gz/examples/QMLPlayer/QMLPlayer_sdk.pro -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/QMLPlayer_sdk.pro Changed

QtAV-1.11.0.tar.gz/examples/QMLPlayer/android/AndroidManifest.xml -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/android/AndroidManifest.xml Changed

QtAV-1.12.0.tar.gz/examples/QMLPlayer/i18n/QMLPlayer.ts Added

@@ -0,0 +1,589 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE TS>
+<TS version="2.1">
+<context>
+ <name>About</name>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="5"/>
+ <source>About</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="22"/>
+ <source>based on</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="23"/>
+ <source>QtAV is a cross platform, high performance multimedia framework</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="26"/>
+ <source>Home page</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="27"/>
+ <source>Install QtAV for Windows desktop/store, macOS, Linux and Android</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="28"/>
+ <source>Double click</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="28"/>
+ <source>show/hide control bar</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="29"/>
+ <source>Click right area</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="29"/>
+ <source>show config panel</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="30"/>
+ <location filename="../qml/QMLPlayer/About.qml" line="31"/>
+ <source>Open</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="30"/>
+ <source>a subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="30"/>
+ <source>press open button to select a subtitle, or a video + a subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="31"/>
+ <source>a URL</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="31"/>
+ <source>press and hold open button</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="34"/>
+ <source>Shortcut</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="35"/>
+ <source>Mute</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="35"/>
+ <source>Fullscreen</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="35"/>
+ <source>Up/Down</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="35"/>
+ <source>Volume</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="36"/>
+ <source>Left/Right</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="36"/>
+ <source>Swipe</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="36"/>
+ <source>Seek backward/forward</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="37"/>
+ <source>Space</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="37"/>
+ <source>Pause/Resume</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="37"/>
+ <source>Quit</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="38"/>
+ <source>Rotate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="38"/>
+ <source>Aspect ratio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/About.qml" line="42"/>
+ <source>Donate</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>AudioPage</name>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="8"/>
+ <source>Audio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="27"/>
+ <source>Channel layout</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="47"/>
+ <source>Audio track</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="70"/>
+ <source>External</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="89"/>
+ <source>Click here to select a file</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="100"/>
+ <source>Stereo</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="101"/>
+ <source>Mono</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="102"/>
+ <source>Left</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="103"/>
+ <source>Right</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/AudioPage.qml" line="128"/>
+ <source>Open an external audio track</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>ConfigPanel</name>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="33"/>
+ <source>Media info</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="34"/>
+ <source>Video codec</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="35"/>
+ <source>Effect</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="36"/>
+ <source>Subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="37"/>
+ <source>Audio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="38"/>
+ <source>Misc</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/ConfigPanel.qml" line="39"/>
+ <source>About</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>EffectPage</name>
+ <message>
+ <location filename="../qml/QMLPlayer/EffectPage.qml" line="6"/>
+ <source>Effect</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/EffectPage.qml" line="27"/>
+ <source>Brightness</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/EffectPage.qml" line="50"/>
+ <source>Contrast</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/EffectPage.qml" line="73"/>
+ <source>Hue</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/EffectPage.qml" line="96"/>
+ <source>Saturation</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/EffectPage.qml" line="116"/>
+ <source>Reset</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>MediaInfoPage</name>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="6"/>
+ <source>Media Information</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="28"/>
+ <source>Duration: </source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="34"/>
+ <source>Size: </source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="36"/>
+ <source>Title</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="38"/>
+ <source>Album</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="40"/>
+ <source>Comment</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="42"/>
+ <source>Year</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="44"/>
+ <source>Date</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="46"/>
+ <source>Author</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="48"/>
+ <source>Publisher</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="50"/>
+ <source>Genre</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="52"/>
+ <source>Track</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="54"/>
+ <source>Track count</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="57"/>
+ <source>Video</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="58"/>
+ <source>Resolution</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="59"/>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="70"/>
+ <source>Bit rate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="60"/>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="66"/>
+ <source>Codec</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="61"/>
+ <source>Pixel format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="62"/>
+ <source>Frames</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="62"/>
+ <source>Frame rate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="65"/>
+ <source>Audio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="67"/>
+ <source>Sample format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="68"/>
+ <source>Sample rate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MediaInfoPage.qml" line="69"/>
+ <source>Channels</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>MiscPage</name>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="5"/>
+ <source>Misc</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="15"/>
+ <source>Reset all</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="25"/>
+ <source>Preview</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="42"/>
+ <source>Press on the preview item to seek</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="64"/>
+ <source>Requirement</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="81"/>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="201"/>
+ <source>Restart to apply</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="162"/>
+ <source>Developer only</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/MiscPage.qml" line="201"/>
+ <source>Language</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>PlayListPanel</name>
+ <message>
+ <location filename="../qml/QMLPlayer/PlayListPanel.qml" line="58"/>
+ <source>History</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>SubtitlePage</name>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="7"/>
+ <source>Subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="27"/>
+ <source>Delay</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="27"/>
+ <source>ms</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="51"/>
+ <source>Engine</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="79"/>
+ <source>Supported formats</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="102"/>
+ <source>Bottom margin</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="115"/>
+ <source>Font</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="130"/>
+ <source>Outline</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="174"/>
+ <source>Font file</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="182"/>
+ <source>Force</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="192"/>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="223"/>
+ <source>Clear</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="215"/>
+ <source>Fonts dir</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="241"/>
+ <source>Embedded Subtitles</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="271"/>
+ <source>External Subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="284"/>
+ <source>Enabled</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="293"/>
+ <source>Auto load</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="325"/>
+ <source>Choose a font file</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/SubtitlePage.qml" line="332"/>
+ <source>Choose a fonts dir</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>VideoCodec</name>
+ <message>
+ <location filename="../qml/QMLPlayer/VideoCodec.qml" line="6"/>
+ <source>Video Codec</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/VideoCodec.qml" line="13"/>
+ <source>Takes effect on the next play</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/VideoCodec.qml" line="75"/>
+ <source>hardware decoding</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/VideoCodec.qml" line="75"/>
+ <source>software decoding</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/VideoCodec.qml" line="80"/>
+ <source>Zero Copy support</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/VideoCodec.qml" line="88"/>
+ <source>Zero copy</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>main</name>
+ <message>
+ <location filename="../qml/QMLPlayer/main.qml" line="196"/>
+ <source>Subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../qml/QMLPlayer/main.qml" line="571"/>
+ <source>Open a URL</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+</TS>

QtAV-1.11.0.tar.gz/examples/QMLPlayer/ios/Info.plist -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/ios/Info.plist Changed

QtAV-1.11.0.tar.gz/examples/QMLPlayer/qml/QMLPlayer/main.qml -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/qml/QMLPlayer/main.qml Changed

QtAV-1.11.0.tar.gz/examples/QMLPlayer/winrt/WinPhone8.Package.appxmanifest -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/winrt/WinPhone8.Package.appxmanifest Changed

QtAV-1.11.0.tar.gz/examples/QMLPlayer/winrt/WinRT10.Package.appxmanifest -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/winrt/WinRT10.Package.appxmanifest Changed

QtAV-1.11.0.tar.gz/examples/QMLPlayer/winrt/WinRT8.Package.appxmanifest -> QtAV-1.12.0.tar.gz/examples/QMLPlayer/winrt/WinRT8.Package.appxmanifest Changed

QtAV-1.11.0.tar.gz/examples/audiopipeline/main.cpp -> QtAV-1.12.0.tar.gz/examples/audiopipeline/main.cpp Changed

QtAV-1.11.0.tar.gz/examples/common/common.cpp -> QtAV-1.12.0.tar.gz/examples/common/common.cpp Changed

QtAV-1.11.0.tar.gz/examples/common/libcommon.pri -> QtAV-1.12.0.tar.gz/examples/common/libcommon.pri Changed

QtAV-1.11.0.tar.gz/examples/filters/main.cpp -> QtAV-1.12.0.tar.gz/examples/filters/main.cpp Changed

QtAV-1.11.0.tar.gz/examples/player/MainWindow.cpp -> QtAV-1.12.0.tar.gz/examples/player/MainWindow.cpp Changed

@@ -48,6 +48,8 @@
 #include <QToolTip>
 #include <QKeyEvent>
 #include <QWheelEvent>
+#include <QStyleFactory>
+
 #include "ClickableMenu.h"
 #include "Slider.h"
 #include "StatisticsView.h"
@@ -110,6 +112,10 @@
 , m_preview(0)
 , m_shader(NULL)
 {
+ #if defined(Q_OS_MACX) && QT_VERSION >= QT_VERSION_CHECK(5, 0, 0)
+ QApplication::setStyle(QStyleFactory::create("Fusion"));
+ #endif
+
 setWindowIcon(QIcon(QString::fromLatin1(":/QtAV.svg")));
 mpOSD = new OSDFilter(this);
 mpSubtitle = new SubtitleFilter(this);
@@ -164,6 +170,7 @@
 onCaptureConfigChanged();
 onAVFilterVideoConfigChanged();
 onAVFilterAudioConfigChanged();
+ connect(&Config::instance(), SIGNAL(forceFrameRateChanged()), SLOT(setFrameRate()));
 connect(&Config::instance(), SIGNAL(captureDirChanged(QString)), SLOT(onCaptureConfigChanged()));
 connect(&Config::instance(), SIGNAL(captureFormatChanged(QString)), SLOT(onCaptureConfigChanged()));
 connect(&Config::instance(), SIGNAL(captureQualityChanged(int)), SLOT(onCaptureConfigChanged()));
@@ -567,7 +574,9 @@
 qWarning("close audio failed");
 return;
 }
- ao->audioFormat().setChannelLayout(cl);
+ AudioFormat af(ao->audioFormat());
+ af.setChannelLayout(cl);
+ ao->setAudioFormat(af);
 if (!ao->open()) {
 qWarning("open audio failed");
 return;
@@ -696,6 +705,7 @@
 mpOSD->installTo(mpRenderer);
 mpSubtitle->installTo(mpRenderer);
 onUserShaderChanged();
+#define GL_ASS 0
 #if GL_ASS
 GLSLFilter* glsl = new GLSLFilter(this);
 glsl->setOutputSize(QSize(4096, 2160));
@@ -860,7 +870,7 @@
 void MainWindow::onStopPlay()
 {
 mpPlayer->setPriority(idsFromNames(Config::instance().decoderPriorityNames()));
- if (mpPlayer->currentRepeat() < mpPlayer->repeat())
+ if (mpPlayer->currentRepeat() >= 0 && mpPlayer->currentRepeat() < mpPlayer->repeat())
 return;
 // use shortcut to replay in EventFilter, the options will not be set, so set here
 mpPlayer->setFrameRate(Config::instance().forceFrameRate());
@@ -892,6 +902,13 @@
 mpSpeed->setText(QString::fromLatin1("%1").arg(speed, 4, 'f', 2, QLatin1Char('0')));
 }
 
+void MainWindow::setFrameRate()
+{
+ if (!mpPlayer)
+ return;
+ mpPlayer->setFrameRate(Config::instance().forceFrameRate());
+}
+
 void MainWindow::seek(int value)
 {
 mpPlayer->setSeekType(AccurateSeek);

QtAV-1.11.0.tar.gz/examples/player/MainWindow.h -> QtAV-1.12.0.tar.gz/examples/player/MainWindow.h Changed

QtAV-1.12.0.tar.gz/examples/player/ios Added

QtAV-1.12.0.tar.gz/examples/player/ios/Info.plist Added

@@ -0,0 +1,231 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>CFBundleIconFile</key>
+	<string>@ICON@</string>
+	<key>CFBundlePackageType</key>
+	<string>APPL</string>
+	<key>CFBundleGetInfoString</key>
+ <string>Created by Wang Bin</string>
+	<key>CFBundleSignature</key>
+ <string>????</string>
+	<key>CFBundleExecutable</key>
+ <string>Player</string>
+	<key>CFBundleIdentifier</key>
+ <string>org.qtav.player</string>
+	<key>CFBundleDisplayName</key>
+ <string>QtAV Player</string>
+	<key>CFBundleName</key>
+ <string>QtAV Player</string>
+	<key>CFBundleShortVersionString</key>
+ <string>1.12</string>
+	<key>CFBundleVersion</key>
+ <string>1.12.0</string>
+	<key>LSRequiresIPhoneOS</key>
+	<true/>
+	<key>UIFileSharingEnabled</key>
+	<true/>
+	<key>UILaunchStoryboardName</key>
+	<string>LaunchScreen</string>
+	<key>UISupportedInterfaceOrientations</key>
+	<array>
+		<string>UIInterfaceOrientationPortrait</string>
+		<string>UIInterfaceOrientationPortraitUpsideDown</string>
+		<string>UIInterfaceOrientationLandscapeLeft</string>
+		<string>UIInterfaceOrientationLandscapeRight</string>
+	</array>
+	<key>NOTE</key>
+	<string>This file was generated by Qt/QMake.</string>
+	<key>CFBundleDocumentTypes</key>
+	<array>
+		<dict>
+			<key>CFBundleTypeExtensions</key>
+			<array>
+				<string>AAC</string>
+				<string>AC3</string>
+				<string>AIFF</string>
+				<string>M4A</string>
+				<string>MKA</string>
+				<string>MP3</string>
+				<string>OGG</string>
+				<string>PCM</string>
+				<string>VAW</string>
+				<string>WAV</string>
+				<string>WAW</string>
+				<string>WMA</string>
+				<string>aac</string>
+				<string>ac3</string>
+				<string>aiff</string>
+				<string>m4a</string>
+				<string>mka</string>
+				<string>mp3</string>
+				<string>ogg</string>
+				<string>pcm</string>
+				<string>vaw</string>
+				<string>wav</string>
+				<string>waw</string>
+				<string>wma</string>
+			</array>
+			<key>CFBundleTypeIconFile</key>
+			<string>document.icns</string>
+			<key>CFBundleTypeName</key>
+			<string>Audio file</string>
+			<key>CFBundleTypeRole</key>
+			<string>Viewer</string>
+			<key>LSTypeIsPackage</key>
+			<false/>
+			<key>NSPersistentStoreTypeKey</key>
+			<string>XML</string>
+		</dict>
+		<dict>
+			<key>CFBundleTypeExtensions</key>
+			<array>
+				<string>*</string>
+				<string>*</string>
+				<string>3GP</string>
+				<string>3IV</string>
+				<string>3gp</string>
+				<string>3iv</string>
+				<string>ASF</string>
+				<string>AVI</string>
+				<string>CPK</string>
+				<string>DAT</string>
+				<string>DIVX</string>
+				<string>DV</string>
+				<string>FLAC</string>
+				<string>FLI</string>
+				<string>FLV</string>
+				<string>H264</string>
+				<string>I263</string>
+				<string>M2TS</string>
+				<string>M4V</string>
+				<string>MKV</string>
+				<string>MOV</string>
+				<string>MP2</string>
+				<string>MP4</string>
+				<string>MPEG</string>
+				<string>MPG</string>
+				<string>MPG2</string>
+				<string>MPG4</string>
+				<string>NSV</string>
+				<string>NUT</string>
+				<string>NUV</string>
+				<string>OGG</string>
+				<string>OGM</string>
+				<string>QT</string>
+				<string>RM</string>
+				<string>RMVB</string>
+				<string>VCD</string>
+				<string>VFW</string>
+				<string>VOB</string>
+				<string>WEBM</string>
+				<string>WMV</string>
+				<string>asf</string>
+				<string>avi</string>
+				<string>cpk</string>
+				<string>dat</string>
+				<string>divx</string>
+				<string>dv</string>
+				<string>flac</string>
+				<string>fli</string>
+				<string>flv</string>
+				<string>h264</string>
+				<string>i263</string>
+				<string>m2ts</string>
+				<string>m4v</string>
+				<string>mkv</string>
+				<string>mov</string>
+				<string>mp2</string>
+				<string>mp4</string>
+				<string>mpeg</string>
+				<string>mpg</string>
+				<string>mpg2</string>
+				<string>mpg4</string>
+				<string>mts</string>
+				<string>nsv</string>
+				<string>nut</string>
+				<string>nuv</string>
+				<string>ogg</string>
+				<string>ogm</string>
+				<string>qt</string>
+				<string>rm</string>
+				<string>rmvb</string>
+				<string>vcd</string>
+				<string>vfw</string>
+				<string>vob</string>
+				<string>webm</string>
+				<string>wmv</string>
+				<string>f4v</string>
+				<string>ts</string>
+			</array>
+			<key>CFBundleTypeIconFile</key>
+			<string>document.icns</string>
+			<key>CFBundleTypeName</key>
+			<string>Movie file</string>
+			<key>CFBundleTypeRole</key>
+			<string>Viewer</string>
+			<key>LSTypeIsPackage</key>
+			<false/>
+			<key>NSPersistentStoreTypeKey</key>
+			<string>XML</string>
+		</dict>
+		<dict>
+			<key>CFBundleTypeExtensions</key>
+			<array>
+				<string>AQT</string>
+				<string>ASS</string>
+				<string>JSS</string>
+				<string>RT</string>
+				<string>SMI</string>
+				<string>SRT</string>
+				<string>SSA</string>
+				<string>SUB</string>
+				<string>TXT</string>
+				<string>UTF</string>
+				<string>aqt</string>
+				<string>ass</string>
+				<string>jss</string>
+				<string>rt</string>
+				<string>smi</string>
+				<string>srt</string>
+				<string>ssa</string>
+				<string>sub</string>
+				<string>txt</string>
+				<string>utf</string>
+			</array>
+			<key>CFBundleTypeIconFile</key>
+			<string>document.icns</string>
+			<key>CFBundleTypeName</key>
+			<string>Subtitles file</string>
+			<key>CFBundleTypeRole</key>
+			<string>Viewer</string>
+			<key>LSTypeIsPackage</key>
+			<false/>
+			<key>NSPersistentStoreTypeKey</key>
+			<string>XML</string>
+		</dict>
+	</array>
+	<key>CFBundleURLTypes</key>
+	<array>
+		<dict>
+			<key>CFBundleTypeRole</key>
+			<string>Viewer</string>
+			<key>CFBundleURLName</key>
+			<string>Streaming Protocol</string>
+			<key>CFBundleURLSchemes</key>
+			<array>
+				<string>mms</string>
+				<string>mmst</string>
+				<string>http</string>
+				<string>httpproxy</string>
+				<string>rtp</string>
+				<string>rtsp</string>
+				<string>ftp</string>
+				<string>udp</string>
+				<string>smb</string>
+			</array>
+		</dict>
+	</array>
+</dict>
+</plist>

QtAV-1.11.0.tar.gz/examples/player/player.pro -> QtAV-1.12.0.tar.gz/examples/player/player.pro Changed

QtAV-1.11.0.tar.gz/examples/player/player_sdk.pro -> QtAV-1.12.0.tar.gz/examples/player/player_sdk.pro Changed

QtAV-1.12.0.tar.gz/examples/player/res/player.ts Added

@@ -0,0 +1,1012 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE TS>
+<TS version="2.1">
+<context>
+ <name>AVFilterConfigPage</name>
+ <message>
+ <location filename="../config/AVFilterConfigPage.cpp" line="38"/>
+ <source>Video</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFilterConfigPage.cpp" line="39"/>
+ <source>Audio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFilterConfigPage.cpp" line="42"/>
+ <source>Enable</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFilterConfigPage.cpp" line="45"/>
+ <source>Registered</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFilterConfigPage.cpp" line="45"/>
+ <source>filters</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFilterConfigPage.cpp" line="50"/>
+ <source>Parameters</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>AVFormatConfigPage</name>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="38"/>
+ <source>Enable</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="38"/>
+ <source>options</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="40"/>
+ <source>Reduce buffering</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="42"/>
+ <source>Probe size</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="46"/>
+ <source>0: auto</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="48"/>
+ <source>Max analyze duration</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="51"/>
+ <source>0: auto. how many microseconds are analyzed to probe the input</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="54"/>
+ <source>Extra</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/AVFormatConfigPage.cpp" line="62"/>
+ <source>AVFormat</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>CaptureConfigPage</name>
+ <message>
+ <location filename="../config/CaptureConfigPage.cpp" line="45"/>
+ <source>Browse</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/CaptureConfigPage.cpp" line="48"/>
+ <location filename="../config/CaptureConfigPage.cpp" line="95"/>
+ <source>Save dir</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/CaptureConfigPage.cpp" line="51"/>
+ <source>Save format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/CaptureConfigPage.cpp" line="58"/>
+ <source>Quality</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/CaptureConfigPage.cpp" line="74"/>
+ <source>Capture</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>ConfigDialog</name>
+ <message>
+ <location filename="../config/ConfigDialog.cpp" line="49"/>
+ <source>Reset</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ConfigDialog.cpp" line="50"/>
+ <source>Ok</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ConfigDialog.cpp" line="51"/>
+ <source>Cancel</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ConfigDialog.cpp" line="52"/>
+ <source>Apply</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>DecoderConfigPage</name>
+ <message>
+ <location filename="../config/DecoderConfigPage.cpp" line="168"/>
+ <source>Video decoder config page</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/DecoderConfigPage.cpp" line="180"/>
+ <location filename="../config/DecoderConfigPage.cpp" line="243"/>
+ <source>Decoder</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/DecoderConfigPage.cpp" line="180"/>
+ <source>Priorities</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/DecoderConfigPage.cpp" line="180"/>
+ <source>reopen is required</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/DecoderConfigPage.cpp" line="224"/>
+ <source>Up</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/DecoderConfigPage.cpp" line="227"/>
+ <source>Down</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>EventFilter</name>
+ <message>
+ <location filename="../EventFilter.cpp" line="60"/>
+ <source>Open a video</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="69"/>
+ <source>Open an url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="69"/>
+ <source>Url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="90"/>
+ <source>Drag and drop a file to player
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="91"/>
+ <source>A: switch aspect ratio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="92"/>
+ <source>Double click to switch fullscreen</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="93"/>
+ <source>Shortcut:
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="94"/>
+ <source>Space: pause/continue
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="95"/>
+ <source>F: fullscreen on/off
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="96"/>
+ <source>T: stays on top on/off
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="97"/>
+ <source>N: show next frame. Continue the playing by pressing &apos;Space&apos;
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="98"/>
+ <source>Ctrl+O: open a file
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="99"/>
+ <source>O: OSD
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="100"/>
+ <source>P: replay
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="101"/>
+ <source>Q/ESC: quit
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="102"/>
+ <source>S: stop
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="103"/>
+ <source>R: rotate 90</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="104"/>
+ <source>M: mute on/off
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="105"/>
+ <source>C: capture video</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="106"/>
+ <source>Up/Down: volume +/-
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="107"/>
+ <source>Ctrl+Up/Down: speed +/-
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="108"/>
+ <source>-&amp;gt;/&amp;lt;-: seek forward/backward
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="109"/>
+ <location filename="../EventFilter.cpp" line="327"/>
+ <source>Help</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="323"/>
+ <source>Open</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="324"/>
+ <source>Open Url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../EventFilter.cpp" line="326"/>
+ <source>About</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>MainWindow</name>
+ <message>
+ <location filename="../MainWindow.cpp" line="162"/>
+ <source>Video renderer is </source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="162"/>
+ <location filename="../MainWindow.cpp" line="631"/>
+ <source>not availabe on your platform!</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="239"/>
+ <source>Current time</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="243"/>
+ <source>Duration</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="247"/>
+ <source>Render engine</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="252"/>
+ <source>Speed. Ctrl+Up/Down</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="263"/>
+ <location filename="../MainWindow.cpp" line="414"/>
+ <source>Open</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="270"/>
+ <source>Capture</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="294"/>
+ <source>Open Url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="298"/>
+ <source>Play list</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="308"/>
+ <source>History</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="322"/>
+ <source>About</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="323"/>
+ <location filename="../MainWindow.cpp" line="1127"/>
+ <source>Help</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="324"/>
+ <source>Donate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="325"/>
+ <source>Setup</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="330"/>
+ <source>Speed</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="341"/>
+ <source>Repeat</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="344"/>
+ <location filename="../MainWindow.cpp" line="406"/>
+ <source>Enable</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="351"/>
+ <source>infinity</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="353"/>
+ <source>Times</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="359"/>
+ <source>From</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="362"/>
+ <location filename="../MainWindow.cpp" line="371"/>
+ <source>negative value means from the end</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="368"/>
+ <source>To</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="388"/>
+ <source>Clock</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="393"/>
+ <source>Auto</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="394"/>
+ <source>Audio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="395"/>
+ <location filename="../MainWindow.cpp" line="474"/>
+ <source>Video</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="402"/>
+ <source>Take effect in next playback</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="404"/>
+ <source>Subtitle</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="410"/>
+ <source>Auto load</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="419"/>
+ <source>Engine</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="429"/>
+ <source>FFmpeg supports more subtitles but only render plain text</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="429"/>
+ <source>LibASS supports ass styles</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="434"/>
+ <source>Charset</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="440"/>
+ <source>Auto detect</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="441"/>
+ <source>System</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="447"/>
+ <source>Auto detect requires libchardet</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="449"/>
+ <source>Audio track</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="455"/>
+ <source>Channel</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="459"/>
+ <source>As input</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="460"/>
+ <source>Stereo</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="461"/>
+ <source>Mono (center)</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="462"/>
+ <source>Left</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="463"/>
+ <source>Right</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="471"/>
+ <location filename="../MainWindow.cpp" line="1229"/>
+ <source>Aspect ratio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="476"/>
+ <source>Window</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="479"/>
+ <source>Custom</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="485"/>
+ <source>Color space</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="493"/>
+ <source>Decoder</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="500"/>
+ <source>Renderer</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="596"/>
+ <source>Open an external audio track</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="654"/>
+ <source>Can not use this renderer</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="786"/>
+ <source>Open a media file</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1132"/>
+ <source>Open an url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1132"/>
+ <source>Url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1164"/>
+ <location filename="../MainWindow.cpp" line="1183"/>
+ <source>External</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1344"/>
+ <source>Player error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1357"/>
+ <source>No media</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1360"/>
+ <source>Invalid meida</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1363"/>
+ <source>Buffering...</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1366"/>
+ <source>Buffered</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1369"/>
+ <source>Loading...</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1372"/>
+ <source>Loaded</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1375"/>
+ <source>Stalled</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1478"/>
+ <source>Capture video frame</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1479"/>
+ <source>Save to</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1481"/>
+ <source>Format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../MainWindow.cpp" line="1576"/>
+ <source>Open a subtitle file</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>MiscPage</name>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="32"/>
+ <location filename="../config/MiscPage.cpp" line="38"/>
+ <source>Preview</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="38"/>
+ <source>size</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="45"/>
+ <source>Force fps</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="48"/>
+ <source>Ignore</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="51"/>
+ <source>Progress update interval</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="56"/>
+ <source>Buffer frames</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="62"/>
+ <source>Timeout</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="62"/>
+ <source>s</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="68"/>
+ <source>Abort</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="74"/>
+ <source>OpenGL type</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="80"/>
+ <source>Windows only</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="80"/>
+ <source>OpenGLES is Used by DXVA Zero Copy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="83"/>
+ <source>D3D9 has performance if ZeroCopy is disabled or for software decoders</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="83"/>
+ <source>RESTART REQUIRED</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="93"/>
+ <source>Currently only works for Qt&gt;=5.5 XCB build</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/MiscPage.cpp" line="107"/>
+ <source>Misc</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>PlayList</name>
+ <message>
+ <location filename="../playlist/PlayList.cpp" line="45"/>
+ <source>Click to select multiple</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../playlist/PlayList.cpp" line="52"/>
+ <source>Clear</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../playlist/PlayList.cpp" line="55"/>
+ <source>Remove selected items</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../playlist/PlayList.cpp" line="201"/>
+ <source>Select files</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QObject</name>
+ <message>
+ <location filename="../StatisticsView.cpp" line="31"/>
+ <source>Url</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="32"/>
+ <source>Format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="33"/>
+ <location filename="../StatisticsView.cpp" line="47"/>
+ <source>Bit rate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="34"/>
+ <location filename="../StatisticsView.cpp" line="46"/>
+ <source>Start time</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="35"/>
+ <source>Duration</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="41"/>
+ <source>Available</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="42"/>
+ <source>Codec</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="43"/>
+ <source>Decoder</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="44"/>
+ <source>Decoder detail</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="45"/>
+ <source>Total time</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="48"/>
+ <source>Frames</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="49"/>
+ <source>FPS</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="55"/>
+ <source>FPS Now</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="56"/>
+ <source>Pixel format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="57"/>
+ <source>Size</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="58"/>
+ <source>Coded size</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="59"/>
+ <source>GOP size</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="64"/>
+ <source>Sample format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="65"/>
+ <source>Sample rate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="66"/>
+ <source>Channels</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="67"/>
+ <source>Channel layout</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="68"/>
+ <source>Frame size</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="139"/>
+ <location filename="../StatisticsView.cpp" line="145"/>
+ <location filename="../StatisticsView.cpp" line="150"/>
+ <source>Metadata</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="141"/>
+ <source>Video</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="147"/>
+ <source>Audio</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="154"/>
+ <source>Ok</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>ShaderPage</name>
+ <message>
+ <location filename="../config/ShaderPage.cpp" line="32"/>
+ <source>Enable</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ShaderPage.cpp" line="34"/>
+ <source>Intermediate FBO</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ShaderPage.cpp" line="36"/>
+ <source>Fragment shader header</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ShaderPage.cpp" line="40"/>
+ <source>Additional header code</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ShaderPage.cpp" line="42"/>
+ <source>Fragment shader texel sample function</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/ShaderPage.cpp" line="58"/>
+ <source>Shader</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>StatisticsView</name>
+ <message>
+ <location filename="../StatisticsView.cpp" line="127"/>
+ <source>Media info</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="134"/>
+ <source>Key</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../StatisticsView.cpp" line="135"/>
+ <source>Value</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>TVView</name>
+ <message>
+ <location filename="../TVView.cpp" line="34"/>
+ <source>Online TV channels</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>VideoEQConfigPage</name>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="38"/>
+ <source>Engine</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="53"/>
+ <source>Brightness</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="54"/>
+ <source>Constrast</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="55"/>
+ <source>Hue</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="56"/>
+ <source>Saturation</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="72"/>
+ <source>Global</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../config/VideoEQConfigPage.cpp" line="75"/>
+ <source>Reset</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+</TS>

QtAV-1.12.0.tar.gz/examples/simpleplayer/CMakeLists.txt Added

QtAV-1.11.0.tar.gz/examples/simpletranscode/main.cpp -> QtAV-1.12.0.tar.gz/examples/simpletranscode/main.cpp Changed

@@ -18,7 +18,7 @@
 along with this program. If not, see <http://www.gnu.org/licenses/>.
 ******************************************************************************/
 
-#include <QApplication>
+#include <QCoreApplication>
 #include <QtCore/QDir>
 #include <QtAV>
 #include <QtAV/AVTranscoder.h>
@@ -28,9 +28,9 @@
 
 int main(int argc, char *argv[])
 {
- QApplication a(argc, argv);
+ QCoreApplication a(argc, argv);
 qDebug("QtAV simpletranscode");
- qDebug("./simpletranscode -i infile -o outfile [-async] [-c:v video_codec (default: libx264)] [-f format] [-an] [-ss HH:mm:ss.z]");
+ qDebug("./simpletranscode -i infile -o outfile [-async] [-c:v video_codec (default: libx264)] [-hwdev dev] [-f format] [-an] [-ss HH:mm:ss.z]");
 qDebug("-an: disable audio");
 qDebug() << "examples:\n"
 << "./simpletranscode -i test.mp4 -o /tmp/test-%05d.png -f image2 -c:v png\n"
@@ -62,6 +62,10 @@
 idx = a.arguments().indexOf(QLatin1String("-f"));
 if (idx > 0)
 fmt = a.arguments().at(idx + 1);
+ QString hwdev;
+ idx = a.arguments().indexOf(QLatin1String("-hwdev"));
+ if (idx > 0)
+ hwdev = a.arguments().at(idx + 1);
 const bool an = a.arguments().contains(QLatin1String("-an"));
 const bool async = a.arguments().contains(QLatin1String("-async"));
 qint64 ss = 0;
@@ -94,6 +98,8 @@
 VideoEncoder *venc = avt.videoEncoder();
 venc->setCodecName(cv); // "png"
 venc->setBitRate(1024*1024);
+ if (!hwdev.isEmpty())
+ venc->setProperty("hwdevice", hwdev);
 if (fmt == QLatin1String("image2"))
 venc->setPixelFormat(VideoFormat::Format_RGBA32);
 if (an) {

QtAV-1.11.0.tar.gz/examples/simpletranscode/simpletranscode.pro -> QtAV-1.12.0.tar.gz/examples/simpletranscode/simpletranscode.pro Changed

QtAV-1.12.0.tar.gz/msys2 Added

QtAV-1.12.0.tar.gz/msys2/PKGBUILD Added

@@ -0,0 +1,49 @@
+realname=qtav
+pkgname="${MINGW_PACKAGE_PREFIX}-${realname}"
+pkgver=r3368.39e6eafe
+pkgrel=1
+pkgdesc="Multimedia framework based on Qt and FFmpeg (mingw-w64)"
+arch=('any')
+license=('LGPL')
+depends=("${MINGW_PACKAGE_PREFIX}-uchardet"
+         "${MINGW_PACKAGE_PREFIX}-ffmpeg"
+         "${MINGW_PACKAGE_PREFIX}-openal"
+         "${MINGW_PACKAGE_PREFIX}-qt5")
+makedepends=('git')
+source=("${realname}::git://github.com/wang-bin/QtAV.git")
+md5sums=('SKIP')
+
+pkgver() {
+  cd "${srcdir}/${realname}"
+  printf "r%s.%s" "$(git rev-list --count HEAD)" "$(git rev-parse --short HEAD)"
+}
+
+prepare() {
+  cd "${srcdir}/${realname}"
+  git submodule update --init
+}
+
+build() {
+  cd "${srcdir}/${realname}"
+  
+  MSYS2_ARG_CONV_EXCL="-DCMAKE_INSTALL_PREFIX=" \
+  cmake \
+    -G"MSYS Makefiles" \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DCMAKE_INSTALL_PREFIX="${MINGW_PREFIX}" \
+    -DBUILD_EXAMPLES=OFF \
+    -DBUILD_PLAYERS=ON \
+    -DBUILD_TESTS=OFF \
+    ../${realname}
+
+  make
+}
+
+package() {
+  cd "${srcdir}/${realname}"
+  
+  make DESTDIR="${pkgdir}" install
+  
+  mkdir -p "${pkgdir}${MINGW_PREFIX}/share/licenses/${realname}"
+  cp lgpl-2.1.txt "${pkgdir}${MINGW_PREFIX}/share/licenses/${realname}/LICENSE"
+}

QtAV-1.12.0.tar.gz/qml/CMakeLists.txt Added

@@ -0,0 +1,84 @@
+set(MODULE QmlAV)
+set(EXTRA_DEFS -DBUILD_QMLAV_LIB)
+
+#URI = QtAV #uri used in QtAVQmlPlugin::registerTypes(uri)
+#qtAtLeast(5, 3): QMAKE_MOC_OPTIONS += -Muri=$$URI # not sure what moc does
+set(HEADERS
+ QmlAV/Export.h
+ QmlAV/MediaMetaData.h
+ QmlAV/SGVideoNode.h
+ QmlAV/QQuickItemRenderer.h
+ QmlAV/QuickFilter.h
+ QmlAV/QmlAVPlayer.h
+ QmlAV/QuickSubtitle.h
+ QmlAV/QuickSubtitleItem.h
+ QmlAV/QuickVideoPreview.h
+)
+set(SOURCES
+ plugin.cpp
+ QQuickItemRenderer.cpp
+ SGVideoNode.cpp
+ QmlAVPlayer.cpp
+ QuickFilter.cpp
+ QuickSubtitle.cpp
+ MediaMetaData.cpp
+ QuickSubtitleItem.cpp
+ QuickVideoPreview.cpp
+)
+if(NOT Qt5Qml_VERSION VERSION_LESS 5.2.0)
+ list(APPEND HEADERS QmlAV/QuickFBORenderer.h)
+ list(APPEND SOURCES QuickFBORenderer.cpp)
+endif()
+# add HEADERS for moc
+if(WIN32)
+ set(RC_FILE ${CMAKE_CURRENT_BINARY_DIR}/${MODULE}.rc)
+ configure_file(${CMAKE_SOURCE_DIR}/cmake/QtAV.rc.in ${RC_FILE})
+endif()
+add_library(${MODULE} SHARED ${SOURCES} ${RESOURCES_SOURCES} ${HEADERS} ${RC_FILE})
+target_link_libraries(${MODULE}
+ LINK_PRIVATE ${EXTRA_LIBS}
+ LINK_PUBLIC QtAV Qt5::Qml Qt5::Quick
+)
+set_target_properties(${MODULE} PROPERTIES
+ OUTPUT_NAME ${MODULE}
+ CLEAN_DIRECT_OUTPUT 1
+ #LINK_SEARCH_START_STATIC 1
+ MACOSX_RPATH ON
+ FRAMEWORK OFF
+ LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin/QtAV
+ RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin/QtAV
+)
+
+#http://stackoverflow.com/questions/19866424/cmake-and-qt5-automoc-error
+#http://doc.qt.io/qt-5/cmake-manual.html
+set(CMAKE_INCLUDE_CURRENT_DIR ON) # for .moc
+target_include_directories(${MODULE}
+ PUBLIC $<INSTALL_INTERFACE:include>
+ PUBLIC $<INSTALL_INTERFACE:include/${MODULE}>
+ PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
+ PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/${MODULE}>
+ PRIVATE ${EXTRA_INCLUDE}
+ )
+target_compile_definitions(${MODULE} PRIVATE ${EXTRA_DEFS})
+set(QML_FILES qmldir Video.qml plugins.qmltypes)
+add_custom_command(TARGET ${MODULE} POST_BUILD
+ COMMAND ${CMAKE_COMMAND} -E make_directory ${CMAKE_BINARY_DIR}/bin/QtAV
+ COMMAND ${CMAKE_COMMAND} -E copy_if_different ${QML_FILES} ${CMAKE_BINARY_DIR}/bin/QtAV
+ WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+)
+
+install(TARGETS ${MODULE}
+ EXPORT ${MODULE}-targets
+ RUNTIME DESTINATION ${QTAV_INSTALL_QML}/QtAV
+ LIBRARY DESTINATION ${QTAV_INSTALL_QML}/QtAV
+ ARCHIVE DESTINATION ${QTAV_INSTALL_QML}/QtAV
+ FRAMEWORK DESTINATION ${QTAV_INSTALL_LIBS}
+)
+install(EXPORT ${MODULE}-targets
+ DESTINATION ${QTAV_INSTALL_LIBS}/cmake/${MODULE}
+ FILE ${MODULE}-config.cmake
+)
+install(
+ FILES ${QML_FILES}
+ DESTINATION ${QTAV_INSTALL_QML}/QtAV
+)

QtAV-1.11.0.tar.gz/qml/QQuickItemRenderer.cpp -> QtAV-1.12.0.tar.gz/qml/QQuickItemRenderer.cpp Changed

QtAV-1.11.0.tar.gz/qml/QmlAV/QmlAVPlayer.h -> QtAV-1.12.0.tar.gz/qml/QmlAV/QmlAVPlayer.h Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2013)
 
@@ -74,11 +74,15 @@
 Q_PROPERTY(QStringList videoCodecs READ videoCodecs)
 Q_PROPERTY(QStringList videoCodecPriority READ videoCodecPriority WRITE setVideoCodecPriority NOTIFY videoCodecPriorityChanged)
 Q_PROPERTY(QVariantMap videoCodecOptions READ videoCodecOptions WRITE setVideoCodecOptions NOTIFY videoCodecOptionsChanged)
+ Q_PROPERTY(QVariantMap avFormatOptions READ avFormatOptions WRITE setAVFormatOptions NOTIFY avFormatOptionsChanged)
 Q_PROPERTY(bool useWallclockAsTimestamps READ useWallclockAsTimestamps WRITE setWallclockAsTimestamps NOTIFY useWallclockAsTimestampsChanged)
 Q_PROPERTY(QtAV::VideoCapture *videoCapture READ videoCapture CONSTANT)
 Q_PROPERTY(int audioTrack READ audioTrack WRITE setAudioTrack NOTIFY audioTrackChanged)
+ Q_PROPERTY(int videoTrack READ videoTrack WRITE setVideoTrack NOTIFY videoTrackChanged)
+ Q_PROPERTY(int bufferSize READ bufferSize WRITE setBufferSize NOTIFY bufferSizeChanged)
 Q_PROPERTY(QUrl externalAudio READ externalAudio WRITE setExternalAudio NOTIFY externalAudioChanged)
 Q_PROPERTY(QVariantList internalAudioTracks READ internalAudioTracks NOTIFY internalAudioTracksChanged)
+ Q_PROPERTY(QVariantList internalVideoTracks READ internalVideoTracks NOTIFY internalVideoTracksChanged)
 Q_PROPERTY(QVariantList externalAudioTracks READ externalAudioTracks NOTIFY externalAudioTracksChanged)
 Q_PROPERTY(QVariantList internalSubtitleTracks READ internalSubtitleTracks NOTIFY internalSubtitleTracksChanged)
 // internal subtitle, e.g. mkv embedded subtitles
@@ -196,6 +200,8 @@
 void setVideoCodecPriority(const QStringList& p);
 QVariantMap videoCodecOptions() const;
 void setVideoCodecOptions(const QVariantMap& value);
+ QVariantMap avFormatOptions() const;
+ void setAVFormatOptions(const QVariantMap& value);
 
 bool useWallclockAsTimestamps() const;
 void setWallclockAsTimestamps(bool use_wallclock_as_timestamps);
@@ -219,6 +225,18 @@
 void setAudioTrack(int value);
 QVariantList internalAudioTracks() const;
 /*!
+ /*!
+ * \brief videoTrack
+ * The video stream number in current media.
+ * Value can be: 0, 1, 2.... 0 means the 1st video stream in current media
+ */
+ int videoTrack() const;
+ void setVideoTrack(int value);
+ QVariantList internalVideoTracks() const;
+
+ int bufferSize() const;
+ void setBufferSize(int value);
+ /*!
 * \brief externalAudio
 * If externalAudio url is valid, player will use audioTrack of external audio as audio source.
 * Set an invalid url to disable external audio
@@ -275,16 +293,20 @@
 void bufferProgressChanged();
 void videoCodecPriorityChanged();
 void videoCodecOptionsChanged();
+ void avFormatOptionsChanged();
 void useWallclockAsTimestampsChanged();
 void channelLayoutChanged();
 void timeoutChanged();
 void abortOnTimeoutChanged();
 void audioTrackChanged();
 void internalAudioTracksChanged();
+ void videoTrackChanged();
+ void internalVideoTracksChanged();
 void externalAudioChanged();
 void externalAudioTracksChanged();
 void internalSubtitleTrackChanged();
 void internalSubtitleTracksChanged();
+ void bufferSizeChanged();
 
 void errorChanged();
 void error(Error error, const QString &errorString);
@@ -337,11 +359,13 @@
 int m_timeout;
 bool m_abort_timeout;
 int m_audio_track;
+ int m_video_track;
 QUrl m_audio;
 int m_sub_track;
 
 QScopedPointer<MediaMetaData> m_metaData;
 QVariantMap vcodec_opt;
+ QVariantMap avfmt_opt;
 
 QList<QuickAudioFilter*> m_afilters;
 QList<QuickVideoFilter*> m_vfilters;

QtAV-1.11.0.tar.gz/qml/QmlAV/QuickVideoPreview.h -> QtAV-1.12.0.tar.gz/qml/QmlAV/QuickVideoPreview.h Changed

QtAV-1.11.0.tar.gz/qml/QmlAVPlayer.cpp -> QtAV-1.12.0.tar.gz/qml/QmlAVPlayer.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2013)
 
@@ -63,6 +63,7 @@
 , m_timeout(30000)
 , m_abort_timeout(true)
 , m_audio_track(0)
+ , m_video_track(0)
 , m_sub_track(0)
 , m_ao(AudioOutput::backendsAvailable())
 {
@@ -76,6 +77,7 @@
 mpPlayer = new AVPlayer(this);
 connect(mpPlayer, SIGNAL(internalSubtitleTracksChanged(QVariantList)), SIGNAL(internalSubtitleTracksChanged()));
 connect(mpPlayer, SIGNAL(internalAudioTracksChanged(QVariantList)), SIGNAL(internalAudioTracksChanged()));
+ connect(mpPlayer, SIGNAL(internalVideoTracksChanged(QVariantList)), SIGNAL(internalVideoTracksChanged()));
 connect(mpPlayer, SIGNAL(externalAudioTracksChanged(QVariantList)), SIGNAL(externalAudioTracksChanged()));
 connect(mpPlayer, SIGNAL(durationChanged(qint64)), SIGNAL(durationChanged()));
 connect(mpPlayer, SIGNAL(mediaStatusChanged(QtAV::MediaStatus)), SLOT(_q_statusChanged()));
@@ -103,7 +105,6 @@
 {
 // TODO: set player parameters
 if (mSource.isValid() && (mAutoLoad || mAutoPlay)) {
- mpPlayer->setFile(QUrl::fromPercentEncoding(mSource.toEncoded()));
 if (mAutoLoad)
 mpPlayer->load();
 if (mAutoPlay)
@@ -137,7 +138,14 @@
 if (mSource == url)
 return;
 mSource = url;
- mpPlayer->setFile(QUrl::fromPercentEncoding(mSource.toEncoded()));
+ if (url.isLocalFile() || url.scheme().isEmpty()
+ || url.scheme().startsWith("qrc")
+ || url.scheme().startsWith("avdevice")
+ // TODO: what about custom io?
+ )
+ mpPlayer->setFile(QUrl::fromPercentEncoding(url.toEncoded()));
+ else
+ mpPlayer->setFile(url.toEncoded());
 Q_EMIT sourceChanged(); //TODO: Q_EMIT only when player loaded a new source
 
 if (mHasAudio) {
@@ -262,6 +270,29 @@
 mpPlayer->setVideoDecoderPriority(videoCodecPriority());
 }
 
+QVariantMap QmlAVPlayer::avFormatOptions() const
+{
+ return avfmt_opt;
+}
+
+void QmlAVPlayer::setAVFormatOptions(const QVariantMap &value)
+{
+ if (value == avfmt_opt)
+ return;
+ avfmt_opt = value;
+ Q_EMIT avFormatOptionsChanged();
+ if (!mpPlayer) {
+ qWarning("player not ready");
+ return;
+ }
+ QVariantHash avfopt;
+ for (QVariantMap::const_iterator cit = avfmt_opt.cbegin(); cit != avfmt_opt.cend(); ++cit) {
+ avfopt[cit.key()] = cit.value();
+ }
+ if (!avfopt.isEmpty())
+ mpPlayer->setOptionsForFormat(avfopt);
+}
+
 bool QmlAVPlayer::useWallclockAsTimestamps() const
 {
 return mUseWallclockAsTimestamps;
@@ -364,6 +395,36 @@
 mpPlayer->setAudioStream(value);
 }
 
+int QmlAVPlayer::videoTrack() const
+{
+ return m_video_track;
+}
+
+void QmlAVPlayer::setVideoTrack(int value)
+{
+ if (m_video_track == value)
+ return;
+ m_video_track = value;
+ Q_EMIT videoTrackChanged();
+ if (mpPlayer)
+ mpPlayer->setVideoStream(value);
+}
+
+int QmlAVPlayer::bufferSize() const
+{
+ return mpPlayer->bufferValue();
+}
+
+void QmlAVPlayer::setBufferSize(int value)
+{
+ if (mpPlayer->bufferValue() == value)
+ return;
+ if (mpPlayer) {
+ mpPlayer->setBufferValue(value);
+ Q_EMIT bufferSizeChanged();
+ }
+}
+
 QUrl QmlAVPlayer::externalAudio() const
 {
 return m_audio;
@@ -388,6 +449,11 @@
 return mpPlayer ? mpPlayer->internalAudioTracks() : QVariantList();
 }
 
+QVariantList QmlAVPlayer::internalVideoTracks() const
+{
+ return mpPlayer ? mpPlayer->internalVideoTracks() : QVariantList();
+}
+
 int QmlAVPlayer::internalSubtitleTrack() const
 {
 return m_sub_track;
@@ -657,6 +723,7 @@
 mpPlayer->setInterruptOnTimeout(m_abort_timeout);
 mpPlayer->setRepeat(mLoopCount - 1);
 mpPlayer->setAudioStream(m_audio_track);
+ mpPlayer->setVideoStream(m_video_track); // will check in case of error
 mpPlayer->setSubtitleStream(m_sub_track);
 if (!vcodec_opt.isEmpty()) {
 QVariantHash vcopt;
@@ -666,6 +733,15 @@
 if (!vcopt.isEmpty())
 mpPlayer->setOptionsForVideoCodec(vcopt);
 }
+ if (!avfmt_opt.isEmpty()) {
+ QVariantHash avfopt;
+ for (QVariantMap::const_iterator cit = avfmt_opt.cbegin(); cit != avfmt_opt.cend(); ++cit) {
+ avfopt[cit.key()] = cit.value();
+ }
+ if (!avfopt.isEmpty())
+ mpPlayer->setOptionsForFormat(avfopt);
+ }
+
 mpPlayer->setStartPosition(startPosition());
 if (stopPosition() == PositionMax)
 mpPlayer->setStopPosition();

QtAV-1.11.0.tar.gz/qml/QuickFBORenderer.cpp -> QtAV-1.12.0.tar.gz/qml/QuickFBORenderer.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2015)
 
@@ -31,7 +31,8 @@
 #include <QtGui/QOpenGLFramebufferObject>
 #include <QtQuick/QQuickWindow>
 // for dynamicgl. qglfunctions before qt5.3 does not have portable gl functions
-#ifdef QT_OPENGL_DYNAMIC
+// use qt gl func if possible to avoid linking to opengl directly
+#if QT_VERSION >= QT_VERSION_CHECK(5, 3, 0)
 #include <QtGui/QOpenGLFunctions>
 #define DYGL(glFunc) QOpenGLContext::currentContext()->functions()->glFunc
 #else
@@ -116,7 +117,8 @@
 
 bool QuickFBORenderer::isSupported(VideoFormat::PixelFormat pixfmt) const
 {
- if (pixfmt == VideoFormat::Format_RGB48BE)
+ if (pixfmt == VideoFormat::Format_RGB48BE
+ || pixfmt == VideoFormat::Format_Invalid)
 return false;
 if (!isOpenGL())
 return VideoFormat::isRGB(pixfmt);

QtAV-1.11.0.tar.gz/qml/QuickVideoPreview.cpp -> QtAV-1.12.0.tar.gz/qml/QuickVideoPreview.cpp Changed

QtAV-1.11.0.tar.gz/qml/SGVideoNode.cpp -> QtAV-1.12.0.tar.gz/qml/SGVideoNode.cpp Changed

QtAV-1.11.0.tar.gz/qml/Video.qml -> QtAV-1.12.0.tar.gz/qml/Video.qml Changed

@@ -84,9 +84,11 @@
     property alias subtitleText: text_sub // not for ass.
     property alias videoCapture: player.videoCapture
     property alias audioTrack: player.audioTrack
+    property alias videoTrack: player.videoTrack
     property alias externalAudio: player.externalAudio
     property alias internalAudioTracks: player.internalAudioTracks
     property alias externalAudioTracks: player.externalAudioTracks
+    property alias internalVideoTracks: player.internalVideoTracks
     /*** Properties of VideoOutput ***/
     /*!
         \qmlproperty enumeration Video::fillMode
@@ -163,6 +165,13 @@
     property alias bufferProgress:  player.bufferProgress
 
     /*!
+        \qmlproperty int Video::bufferSize
+
+        This property holds the buffer value.
+    */
+    property alias bufferSize:  player.bufferSize
+
+    /*!
         \qmlproperty int Video::duration
 
         This property holds the duration of the media in milliseconds.
@@ -344,6 +353,7 @@
         anchors.fill: video
         source: player
     }
+
     SubtitleItem {
         id: ass_sub
         rotation: -videoOut.orientation

QtAV-1.11.0.tar.gz/qml/libQmlAV.pri -> QtAV-1.12.0.tar.gz/qml/libQmlAV.pri Changed

QtAV-1.11.0.tar.gz/qml/libQmlAV.pro -> QtAV-1.12.0.tar.gz/qml/libQmlAV.pro Changed

QtAV-1.11.0.tar.gz/qml/plugins.qmltypes -> QtAV-1.12.0.tar.gz/qml/plugins.qmltypes Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/build.sh -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/build.sh Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/config/config.xml -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/config/config.xml Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.dev/meta/package.xml -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.dev/meta/package.xml Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.examples/meta/package.xml -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.examples/meta/package.xml Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.player/meta/package.xml -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.player/meta/package.xml Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.runtime/meta/package.xml -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product.runtime/meta/package.xml Changed

QtAV-1.11.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product/meta/package.xml -> QtAV-1.12.0.tar.gz/qtc_packaging/ifw/packages/com.qtav.product/meta/package.xml Changed

QtAV-1.11.0.tar.gz/src/AVCompat.cpp -> QtAV-1.12.0.tar.gz/src/AVCompat.cpp Changed

@@ -22,10 +22,6 @@
 #include "QtAV/private/AVCompat.h"
 #include "QtAV/version.h"
 
-#ifndef av_err2str
-
-#endif //av_err2str
-
 #if !FFMPEG_MODULE_CHECK(LIBAVFORMAT, 56, 4, 101)
 int avio_feof(AVIOContext *s)
 {
@@ -341,9 +337,9 @@
             goto failed_alloc;                                          \
         memcpy(data, src, size);                                        \
         if (padding)                                                    \
-            memset((uint8_t *)data + size, 0,                           \
+            memset((uint8_t*)data + size, 0,                           \
                    FF_INPUT_BUFFER_PADDING_SIZE);                       \
-        dst = data;                                                     \
+        *((void**)&dst) = data;                                                     \
     } while (0)
 
     *dst = *src;
@@ -371,9 +367,19 @@
 }
 #endif
 #if !AV_MODULE_CHECK(LIBAVCODEC, 55, 52, 0, 63, 100)
-void avcodec_free_context(AVCodecContext **avctx)
+void avcodec_free_context(AVCodecContext **pavctx)
 {
-    av_freep(avctx);
+
+    AVCodecContext *avctx = *pavctx;
+    if (!avctx)
+        return;
+    avcodec_close(avctx);
+    av_freep(&avctx->extradata);
+    av_freep(&avctx->subtitle_header);
+    av_freep(&avctx->intra_matrix);
+    av_freep(&avctx->inter_matrix);
+    av_freep(&avctx->rc_override);
+    av_freep(pavctx);
 }
 #endif

QtAV-1.11.0.tar.gz/src/AVDemuxThread.cpp -> QtAV-1.12.0.tar.gz/src/AVDemuxThread.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -53,6 +53,8 @@
 return;
 if (mDemuxThread->isEnd())
 return;
+ if (mDemuxThread->atEndOfMedia())
+ return;
 mDemuxThread->updateBufferState(); // ensure detect buffering immediately
 AVThread *thread = mDemuxThread->videoThread();
 //qDebug("try wake up video queue");
@@ -173,7 +175,7 @@
 AVThread *avt = demux_thread->videoThread();
 avt->packetQueue()->clear(); // clear here
 if (pts <= 0) {
- demux_thread->demuxer->seek(qint64(-pts*1000.0) - 1000LL);
+ demux_thread->demuxer->seek(qint64(-pts*1000.0) - 500LL);
 QVector<qreal> ts;
 qreal t = -1.0;
 while (t < -pts) {
@@ -183,9 +185,12 @@
 t = demux_thread->demuxer->packet().pts;
 ts.push_back(t);
 }
+ const qreal t0 = ts.back();
 ts.pop_back();
+ const qreal dt = t0 - ts.back();
 pts = ts.back();
- // FIXME: sometimes can not seek to the previous pts, the result pts is always current pts
+ // FIXME: sometimes can not seek to the previous pts, the result pts is always current pts, so let the target pts a little earlier
+ pts -= dt/2.0;
 }
 qDebug("step backward: %lld, %f", qint64(pts*1000.0), pts);
 demux_thread->video_thread->setDropFrameOnSeek(false);
@@ -319,6 +324,11 @@
 return end;
 }
 
+bool AVDemuxThread::atEndOfMedia() const
+{
+ return demuxer->atEnd();
+}
+
 PacketBuffer* AVDemuxThread::buffer()
 {
 return m_buffer;
@@ -460,6 +470,7 @@
 thread->clock()->setClockAuto(clock_type & 1);
 thread->clock()->setClockType(AVClock::ClockType(clock_type/2));
 clock_type = -1;
+ thread->clock()->updateExternalClock((thread->previousHistoryPts() - thread->clock()->initialValue())*1000.0);
 }
 Q_EMIT stepFinished();
 }
@@ -589,6 +600,10 @@
 msleep(100);
 continue;
 }
+ if (demuxer->mediaStatus() == StalledMedia) {
+ qDebug("stalled media. exiting demuxing thread");
+ break;
+ }
 was_end = 0;
 if (tryPause()) {
 continue; //the queue is empty and will block
@@ -701,7 +716,10 @@
 }
 thread->disconnect(this, SIGNAL(seekFinished(qint64)));
 qDebug("Demux thread stops running....");
- Q_EMIT mediaStatusChanged(QtAV::EndOfMedia);
+ if (demuxer->atEnd())
+ Q_EMIT mediaStatusChanged(QtAV::EndOfMedia);
+ else
+ Q_EMIT mediaStatusChanged(QtAV::StalledMedia);
 }
 
 bool AVDemuxThread::tryPause(unsigned long timeout)

QtAV-1.11.0.tar.gz/src/AVDemuxThread.h -> QtAV-1.12.0.tar.gz/src/AVDemuxThread.h Changed

QtAV-1.11.0.tar.gz/src/AVDemuxer.cpp -> QtAV-1.12.0.tar.gz/src/AVDemuxer.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -252,18 +252,21 @@
 || file.startsWith(QLatin1String("udp:"))
 || file.startsWith(QLatin1String("gopher:"))
 )) {
- network = true; //iformat.flags: AVFMT_NOFILE
+ network = true;
 }
 }
 bool checkSeekable() {
+ bool s = false;
 if (!format_ctx)
- return false;
+ return s;
+ // io.seekable: byte seeking
 if (input)
- return input->isSeekable();
+ s |= input->isSeekable();
 if (format_ctx->pb)
- return format_ctx->pb->seekable;
- // avio context null. not sure the correct way to detect seekable
- return format_ctx->iformat->read_seek || format_ctx->iformat->read_seek2;
+ s |= !!format_ctx->pb->seekable;
+ // format.read_seek: time seeking. For example, seeking on hls stream steps: find segment, read packet in segment and drop until desired pts got
+ s |= format_ctx->iformat->read_seek || format_ctx->iformat->read_seek2;
+ return s;
 }
 // set wanted_xx_stream. call openCodecs() to read new stream frames
 // stream < 0 is choose best
@@ -312,7 +315,7 @@
 StreamInfo astream, vstream, sstream;
 
 AVDemuxer::InterruptHandler *interrupt_hanlder;
- QMutex mutex; //TODO: remove?
+ QMutex mutex; //TODO: remove if load, read, seek is called in 1 thread
 };
 
 AVDemuxer::AVDemuxer(QObject *parent)
@@ -422,6 +425,7 @@
 d->pkt = Packet();
 // no lock required because in AVDemuxThread read and seek are in the same thread
 AVPacket packet;
+ av_init_packet(&packet);
 d->interrupt_hanlder->begin(InterruptHandler::Read);
 int ret = av_read_frame(d->format_ctx, &packet); //0: ok, <0: error/end
 d->interrupt_hanlder->end();
@@ -430,42 +434,47 @@
 //end of file. FIXME: why no d->eof if replaying by seek(0)?
 // ffplay also check pb && pb->error and exit read thread
 if (ret == AVERROR_EOF
- // AVFMT_NOFILE(e.g. network streams) stream has no pb
 || avio_feof(d->format_ctx->pb)) {
 if (!d->eof) {
- if (getInterruptStatus()) { //eof error if interrupted!
+ if (getInterruptStatus()) {
 AVError::ErrorCode ec(AVError::ReadError);
 QString msg(tr("error reading stream data"));
 handleError(ret, &ec, msg);
 }
- d->eof = true;
+ if (mediaStatus() != StalledMedia) {
+ d->eof = true;
 #if 0 // EndOfMedia when demux thread finished
- d->started = false;
- setMediaStatus(EndOfMedia);
- emit finished();
+ d->started = false;
+ setMediaStatus(EndOfMedia);
+ Q_EMIT finished();
 #endif
- qDebug("End of file. erreof=%d feof=%d", ret == AVERROR_EOF, avio_feof(d->format_ctx->pb));
+ qDebug("End of file. erreof=%d feof=%d", ret == AVERROR_EOF, avio_feof(d->format_ctx->pb));
+ }
 }
+ av_packet_unref(&packet); //important!
 return false;
 }
 if (ret == AVERROR(EAGAIN)) {
 qWarning("demuxer EAGAIN :%s", av_err2str(ret));
+ av_packet_unref(&packet); //important!
 return false;
 }
 AVError::ErrorCode ec(AVError::ReadError);
 QString msg(tr("error reading stream data"));
 handleError(ret, &ec, msg);
 qWarning("[AVDemuxer] error: %s", av_err2str(ret));
+ av_packet_unref(&packet); //important!
 return false;
 }
 d->stream = packet.stream_index;
 //check whether the 1st frame is alreay got. emit only once
 if (!d->started) {
 d->started = true;
- emit started();
+ Q_EMIT started();
 }
 if (d->stream != videoStream() && d->stream != audioStream() && d->stream != subtitleStream()) {
 //qWarning("[AVDemuxer] unknown stream index: %d", stream);
+ av_packet_unref(&packet); //important!
 return false;
 }
 // TODO: v4l2 copy
@@ -534,7 +543,7 @@
 if (!isLoaded())
 return false;
 //duration: unit is us (10^-6 s, AV_TIME_BASE)
- qint64 upos = pos*1000LL;
+ qint64 upos = pos*1000LL; // TODO: av_rescale
 if (upos > startTimeUs() + durationUs() || pos < 0LL) {
 if (pos >= 0LL && d->input && d->input->isSeekable() && d->input->isVariableSize()) {
 qDebug("Seek for variable size hack. %lld %.2f. valid range [%lld, %lld]", upos, double(upos)/double(durationUs()), startTimeUs(), startTimeUs()+durationUs());
@@ -731,7 +740,7 @@
 setMediaStatus(NoMedia);
 return false;
 }
- QMutexLocker lock(&d->mutex);
+ QMutexLocker lock(&d->mutex); // TODO: load in AVDemuxThread and remove all locks
 Q_UNUSED(lock);
 setMediaStatus(LoadingMedia);
 d->checkNetwork();
@@ -739,19 +748,19 @@
 static const QString avd_scheme(QStringLiteral("avdevice:"));
 if (d->file.startsWith(avd_scheme)) {
 QStringList parts = d->file.split(QStringLiteral(":"));
- if (parts.count() != 3) {
+ int s0 = avd_scheme.size();
+ const int s1 = d->file.indexOf(QChar(':'), s0);
+ if (s1 < 0) {
 qDebug("invalid avdevice specification");
 setMediaStatus(InvalidMedia);
 return false;
 }
- if (d->file.startsWith(avd_scheme + QStringLiteral("//"))) {
+ if (d->file.at(s0) == QChar('/') && d->file.at(s0+1) == QChar('/')) {
 // avdevice://avfoundation:device_name
- d->input_format = av_find_input_format(parts[1].mid(2).toUtf8().constData());
- } else {
- // avdevice:video4linux2:file_name
- d->input_format = av_find_input_format(parts[1].toUtf8().constData());
- }
- d->file = parts[2];
+ s0 += 2;
+ } // else avdevice:video4linux2:file_name
+ d->input_format = av_find_input_format(d->file.mid(s0, s1-s0).toUtf8().constData());
+ d->file = d->file.mid(s1+1);
 }
 #endif
 //alloc av format context
@@ -828,13 +837,7 @@
 d->seekable = d->checkSeekable();
 if (was_seekable != d->seekable)
 Q_EMIT seekableChanged();
- qDebug("avfmtctx.flag: %d", d->format_ctx->flags);
- qDebug("AVFMT_NOTIMESTAMPS: %d, AVFMT_TS_DISCONT: %d, AVFMT_NO_BYTE_SEEK:%d, custom io: %d"
- , d->format_ctx->flags&AVFMT_NOTIMESTAMPS
- , d->format_ctx->flags&AVFMT_TS_DISCONT
- , d->format_ctx->flags&AVFMT_NO_BYTE_SEEK
- , d->format_ctx->flags&AVFMT_FLAG_CUSTOM_IO
- );
+ qDebug("avfmtctx.flags: %d, iformat.flags", d->format_ctx->flags, d->format_ctx->iformat->flags);
 if (getInterruptStatus() < 0) {
 QString msg;
 qDebug("AVERROR_EXIT: %d", AVERROR_EXIT);
@@ -852,7 +855,7 @@
 /*
 if (d->seekable) {
 d->seekable = false; //
- emit seekableChanged();
+ Q_EMIT seekableChanged();
 }
 */
 d->network = false;
@@ -945,12 +948,12 @@
 // convert to s using AV_TIME_BASE then *1000?
 qint64 AVDemuxer::startTime() const
 {
- return startTimeUs()/1000LL;
+ return startTimeUs()/1000LL; //TODO: av_rescale
 }
 
 qint64 AVDemuxer::duration() const
 {
- return durationUs()/1000LL; //time base: AV_TIME_BASE
+ return durationUs()/1000LL; //time base: AV_TIME_BASE TODO: av_rescale
 }
 
 //AVFrameContext use AV_TIME_BASE as time base. AVStream use their own timebase
@@ -1143,7 +1146,7 @@
 
 d->media_status = status;
 
- emit mediaStatusChanged(d->media_status);
+ Q_EMIT mediaStatusChanged(d->media_status);
 }
 
 void AVDemuxer::Private::applyOptionsForDict()
@@ -1202,7 +1205,7 @@
 // insufficient buffering or other interruptions
 if (getInterruptStatus() < 0) {
 setMediaStatus(StalledMedia);
- emit userInterrupted();
+ Q_EMIT userInterrupted();
 err_msg += QStringLiteral(" [%1]").arg(tr("interrupted by user"));
 } else {
 // FIXME: if not interupt on timeout and ffmpeg exits, still LoadingMedia
@@ -1228,7 +1231,7 @@
 ec = AVError::NetworkError;
 }
 AVError err(ec, err_msg, averr);
- emit error(err);
+ Q_EMIT error(err);
 *errorCode = ec;
 }

QtAV-1.11.0.tar.gz/src/AVPlayer.cpp -> QtAV-1.12.0.tar.gz/src/AVPlayer.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -184,6 +184,7 @@
 {
 if (speed == d->speed)
 return;
+ setFrameRate(0); // will set clock to default
 d->speed = speed;
 //TODO: check clock type?
 if (d->ao && d->ao->isAvailable()) {
@@ -233,6 +234,9 @@
 d->force_fps = value;
 // clock set here will be reset in playInternal()
 // also we can't change user's setting of ClockType and autoClock here if force frame rate is disabled.
+ if (!isPlaying())
+ return;
+ d->applyFrameRate();
 }
 
 qreal AVPlayer::forcedFrameRate() const
@@ -576,6 +580,7 @@
 return;
 if (isPaused() == p)
 return;
+ audio()->pause(p);
 //pause thread. check pause state?
 d->read_thread->pause(p);
 if (d->athread)
@@ -661,6 +666,8 @@
 qWarning("Load failed!");
 d->audio_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::AudioStream);
 Q_EMIT internalAudioTracksChanged(d->audio_tracks);
+ d->video_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::VideoStream);
+ Q_EMIT internalVideoTracksChanged(d->video_tracks);
 d->subtitle_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::SubtitleStream);
 Q_EMIT internalSubtitleTracksChanged(d->subtitle_tracks);
 return;
@@ -670,6 +677,8 @@
 d->applySubtitleStream(d->subtitle_track, this);
 d->audio_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::AudioStream);
 Q_EMIT internalAudioTracksChanged(d->audio_tracks);
+ d->video_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::VideoStream);
+ Q_EMIT internalVideoTracksChanged(d->video_tracks);
 Q_EMIT durationChanged(duration());
 // setup parameters from loaded media
 d->media_start_pts = d->demuxer.startTime();
@@ -706,10 +715,12 @@
 d->vdec = 0;
 }
 d->demuxer.unload();
- Q_EMIT durationChanged(0LL);
+ Q_EMIT durationChanged(0LL); // for ui, slider is invalid. use stopped instead, and remove this signal here?
 // ??
 d->audio_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::AudioStream);
 Q_EMIT internalAudioTracksChanged(d->audio_tracks);
+ d->video_tracks = d->getTracksInfo(&d->demuxer, AVDemuxer::VideoStream);
+ Q_EMIT internalVideoTracksChanged(d->video_tracks);
 }
 
 void AVPlayer::setRelativeTimeMode(bool value)
@@ -896,6 +907,11 @@
 return d->audio_tracks;
 }
 
+const QVariantList &AVPlayer::internalVideoTracks() const
+{
+ return d->video_tracks;
+}
+
 bool AVPlayer::setAudioStream(const QString &file, int n)
 {
 QString path(file);
@@ -1009,17 +1025,20 @@
 return false;
 }
 d->video_track = n;
- if (!isPlaying())
- return true;
- // pause demuxer, clear queues, set demuxer stream, set decoder, set ao, resume
- bool p = isPaused();
- pause(true);
- if (!d->setupVideoThread(this)) {
- stop();
- return false;
- }
- if (!p)
- pause(false);
+ d->demuxer.setStreamIndex(AVDemuxer::VideoStream, n);
+// if (!isPlaying())
+// return true;
+// // pause demuxer, clear queues, set demuxer stream, set decoder, set ao, resume
+// bool p = isPaused();
+// //int bv = bufferValue();
+// setBufferMode(BufferTime);
+// pause(true);
+// if (!d->setupVideoThread(this)) {
+// stop();
+// return false;
+// }
+// if (!p) pause(false);
+// //QTimer::singleShot(10000, this, SLOT(setBufferValue(bv)));
 return true;
 }
 
@@ -1191,27 +1210,6 @@
 // setup clock before avthread.start() becuase avthreads use clock. after avthreads setup because of ao check
 masterClock()->reset();
 // TODO: add isVideo() or hasVideo()?
- qreal vfps = d->force_fps;
- bool force_fps = vfps > 0;
- const bool ao_null = d->ao && d->ao->backend().toLower() == QLatin1String("null");
- if (d->athread && !ao_null) { // TODO: no null ao check. null ao block internally
- force_fps = vfps > 0 && !!d->vthread;
- } else if (!force_fps) {
- force_fps = !!d->vthread;
- vfps = d->statistics.video.frame_rate > 0 ? d->statistics.video.frame_rate : 25;
- // vfps<0: try to use pts (ExternalClock). if no pts (raw codec), try the default fps(VideoClock)
- vfps = -vfps;
- }
- if (force_fps) {
- masterClock()->setClockAuto(false);
- // vfps>0: force video fps to vfps. clock must be external
- masterClock()->setClockType(vfps > 0 ? AVClock::VideoClock : AVClock::ExternalClock);
- d->vthread->setFrameRate(vfps);
- } else {
- masterClock()->setClockAuto(true);
- if (d->vthread)
- d->vthread->setFrameRate(0.0);
- }
 if (masterClock()->isClockAuto()) {
 qDebug("auto select clock: audio > external");
 if (!d->demuxer.audioCodecContext() || !d->ao || !d->ao->isOpen() || !d->athread) {
@@ -1232,12 +1230,7 @@
 qDebug("Starting video thread...");
 d->vthread->start();
 }
- if (d->start_position_norm > 0) {
- if (relativeTimeMode())
- d->demuxer.seek(qint64((d->start_position_norm + absoluteMediaStartPosition())));
- else
- d->demuxer.seek((qint64)(d->start_position_norm));
- }
+
 d->read_thread->setMediaEndAction(mediaEndAction());
 d->read_thread->start();
 
@@ -1252,22 +1245,31 @@
 QMetaObject::invokeMethod(this, "startNotifyTimer", Qt::AutoConnection);
 }
 d->state = PlayingState;
+ if (d->repeat_current < 0)
+ d->repeat_current = 0;
 } //end lock scoped here to avoid dead lock if connect started() to a slot that call unload()/play()
+ if (d->start_position_norm > 0) {
+ if (relativeTimeMode())
+ setPosition(qint64((d->start_position_norm + absoluteMediaStartPosition())));
+ else
+ setPosition((qint64)(d->start_position_norm));
+ }
 Q_EMIT stateChanged(PlayingState);
 Q_EMIT started(); //we called stop(), so must emit started()
 }
 
 void AVPlayer::stopFromDemuxerThread()
 {
- qDebug("demuxer thread emit finished.");
+ qDebug("demuxer thread emit finished. repeat: %d/%d", currentRepeat(), repeat());
 d->seeking = false;
- if (currentRepeat() >= repeat() && repeat() >= 0) {
+ if (currentRepeat() < 0 || (currentRepeat() >= repeat() && repeat() >= 0)) {
 qreal stop_pts = masterClock()->videoTime();
 if (stop_pts <= 0)
 stop_pts = masterClock()->value();
 masterClock()->reset();
- stopNotifyTimer();
+ QMetaObject::invokeMethod(this, "stopNotifyTimer");
 // vars not set by user can be reset
+ d->repeat_current = -1;
 d->start_position_norm = 0;
 d->stop_position_norm = kInvalidPosition; // already stopped. so not 0 but invalid. 0 can stop the playback in timerEvent
 d->media_end = kInvalidPosition;
@@ -1342,11 +1344,15 @@
 
 void AVPlayer::onStarted()
 {
- //TODO: check clock type?
- if (d->ao && d->ao->isAvailable()) {
- d->ao->setSpeed(d->speed);
+ if (d->speed != 1.0) {
+ //TODO: check clock type?
+ if (d->ao && d->ao->isAvailable()) {
+ d->ao->setSpeed(d->speed);
+ }
+ masterClock()->setSpeed(d->speed);
+ } else {
+ d->applyFrameRate();
 }
- masterClock()->setSpeed(d->speed);
 }
 
 void AVPlayer::updateMediaStatus(QtAV::MediaStatus status)
@@ -1408,7 +1414,7 @@
 }
 d->seeking = false;
 d->reset_state = true;
-
+ d->repeat_current = -1;
 if (!isPlaying()) {
 qDebug("Not playing~");
 if (mediaStatus() == LoadingMedia || mediaStatus() == LoadedMedia) {

QtAV-1.11.0.tar.gz/src/AVPlayerPrivate.cpp -> QtAV-1.12.0.tar.gz/src/AVPlayerPrivate.cpp Changed

@@ -76,7 +76,7 @@
 , start_position_norm(0)
 , stop_position_norm(kInvalidPosition)
 , repeat_max(0)
- , repeat_current(0)
+ , repeat_current(-1)
 , timer_id(-1)
 , audio_track(0)
 , video_track(0)
@@ -181,6 +181,39 @@
 qDebug("notify_interval: %d", qAbs(notify_interval));
 }
 
+void AVPlayer::Private::applyFrameRate()
+{
+ qreal vfps = force_fps;
+ bool force = vfps > 0;
+ const bool ao_null = ao && ao->backend().toLower() == QLatin1String("null");
+ if (athread && !ao_null) { // TODO: no null ao check. null ao block internally
+ force = vfps > 0 && !!vthread;
+ } else if (!force) {
+ force = !!vthread;
+ vfps = statistics.video.frame_rate > 0 ? statistics.video.frame_rate : 25;
+ // vfps<0: try to use pts (ExternalClock). if no pts (raw codec), try the default fps(VideoClock)
+ vfps = -vfps;
+ }
+ qreal r = speed;
+ if (force) {
+ clock->setClockAuto(false);
+ // vfps>0: force video fps to vfps. clock must be external
+ clock->setClockType(vfps > 0 ? AVClock::VideoClock : AVClock::ExternalClock);
+ vthread->setFrameRate(vfps);
+ if (statistics.video.frame_rate > 0)
+ r = qAbs(qreal(vfps))/statistics.video.frame_rate;
+ } else {
+ clock->setClockAuto(true);
+ clock->setClockType(athread && ao->isOpen() ? AVClock::AudioClock : AVClock::ExternalClock);
+ if (vthread)
+ vthread->setFrameRate(0.0);
+ ao->setSpeed(1);
+ clock->setSpeed(1);
+ }
+ ao->setSpeed(r);
+ clock->setSpeed(r);
+}
+
 void AVPlayer::Private::initStatistics()
 {
 initBaseStatistics();
@@ -339,34 +372,17 @@
 af.setSampleRate(avctx->sample_rate);
 af.setSampleFormatFFmpeg(avctx->sample_fmt);
 af.setChannelLayoutFFmpeg(avctx->channel_layout);
- qDebug() << "audio format from codec: " << af;
 if (!af.isValid()) {
 qWarning("invalid audio format. audio stream will be disabled");
 return false;
 }
- // 5, 6, 7 channels may not play
- if (avctx->channels > 2)
- af.setChannelLayout(ao->preferredChannelLayout());
 //af.setChannels(avctx->channels);
- // FIXME: workaround. planar convertion crash now!
- if (af.isPlanar()) {
- af.setSampleFormat(AudioFormat::packedSampleFormat(af.sampleFormat()));
- }
- if (!ao->isSupported(af)) {
- if (!ao->isSupported(af.sampleFormat())) {
- af.setSampleFormat(ao->preferredSampleFormat());
- }
- if (!ao->isSupported(af.channelLayout())) {
- af.setChannelLayout(ao->preferredChannelLayout());
- }
- }
 // always reopen to ensure internal buffer queue inside audio backend(openal) is clear. also make it possible to change backend when replay.
 //if (ao->audioFormat() != af) {
 //qDebug("ao audio format is changed. reopen ao");
+ ao->setAudioFormat(af); /// set before close to workaround OpenAL context lost
 ao->close();
- if (ao->audioFormat() != af)
- ao->setAudioFormat(af);
- qDebug() << "AudioOutput format: " <<ao->audioFormat();
+ qDebug() << "AudioOutput format: " << ao->audioFormat() << "; requested: " << ao->requestedFormat();
 if (!ao->open()) {
 return false;
 }

QtAV-1.11.0.tar.gz/src/AVPlayerPrivate.h -> QtAV-1.12.0.tar.gz/src/AVPlayerPrivate.h Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2014-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2014-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -40,6 +40,7 @@
 
 bool checkSourceChange();
 void updateNotifyInterval();
+ void applyFrameRate();
 void initStatistics();
 void initBaseStatistics();
 void initCommonStatistics(int s, Statistics::Common* st, AVCodecContext* avctx);
@@ -115,9 +116,11 @@
 
 int audio_track, video_track, subtitle_track;
 QVariantList subtitle_tracks;
+ QVariantList video_tracks;
 QString external_audio;
 AVDemuxer audio_demuxer;
- QVariantList audio_tracks, external_audio_tracks;
+ QVariantList external_audio_tracks;
+ QVariantList audio_tracks;
 BufferMode buffer_mode;
 qint64 buffer_value;
 //the following things are required and must be set not null

QtAV-1.11.0.tar.gz/src/AudioFormat.cpp -> QtAV-1.12.0.tar.gz/src/AudioFormat.cpp Changed

@@ -135,23 +135,16 @@
     qint64 channel_layout_ff;
 };
 
-bool AudioFormat::isPlanar(SampleFormat format)
+AudioFormat::SampleFormat AudioFormat::make(int bytesPerSample, bool isFloat, bool isUnsigned, bool isPlanar)
 {
-    return format & kPlanar;
-}
-
-AudioFormat::SampleFormat AudioFormat::packedSampleFormat(SampleFormat fmt)
-{
-    if (isPlanar(fmt))
-        return SampleFormat((int)fmt^kPlanar);
-    return fmt;
-}
-
-AudioFormat::SampleFormat AudioFormat::planarSampleFormat(SampleFormat fmt)
-{
-    if (isPlanar(fmt))
-        return fmt;
-    return SampleFormat((int)fmt|kPlanar);
+    int f = bytesPerSample;
+    if (isFloat)
+        f |= kFloat;
+    if (isUnsigned)
+        f |= kUnsigned;
+    if (isPlanar)
+        f |= kPlanar;
+    return SampleFormat(f);
 }
 
 AudioFormat::AudioFormat():
@@ -220,12 +213,12 @@
 
 bool AudioFormat::isUnsigned() const
 {
-    return d->sample_fmt & kUnsigned;
+    return IsUnsigned(d->sample_fmt);
 }
 
 bool AudioFormat::isPlanar() const
 {
-    return d->sample_fmt & kPlanar;
+    return IsPlanar(d->sample_fmt);
 }
 
 int AudioFormat::planeCount() const

QtAV-1.11.0.tar.gz/src/AudioFrame.cpp -> QtAV-1.12.0.tar.gz/src/AudioFrame.cpp Changed

@@ -76,11 +76,11 @@
 Q_D(AudioFrame);
 d->format = format;
 d->data = data;
- d->samples_per_ch = data.size() / d->format.channels() / d->format.bytesPerSample();
 if (!d->format.isValid())
 return;
 if (d->data.isEmpty())
 return;
+ d->samples_per_ch = data.size() / d->format.channels() / d->format.bytesPerSample();
 const int nb_planes(d->format.planeCount());
 const int bpl(d->data.size()/nb_planes);
 for (int i = 0; i < nb_planes; ++i) {
@@ -140,14 +140,14 @@
 if (d->samples_per_ch <= 0 || bytesPerLine(0) <= 0)
 return AudioFrame(format());
 QByteArray buf(bytesPerLine()*planeCount(), 0);
- AudioFrame f(d->format, buf);
- f.setSamplesPerChannel(samplesPerChannel());
 char *dst = buf.data(); //must before buf is shared, otherwise data will be detached.
- for (int i = 0; i < f.planeCount(); ++i) {
- const int plane_size = f.bytesPerLine(i);
- memcpy(dst, f.constBits(i), plane_size);
+ for (int i = 0; i < planeCount(); ++i) {
+ const int plane_size = bytesPerLine(i);
+ memcpy(dst, constBits(i), plane_size);
 dst += plane_size;
 }
+ AudioFrame f(d->format, buf);
+ f.setSamplesPerChannel(samplesPerChannel());
 f.setTimestamp(timestamp());
 // meta data?
 return f;

QtAV-1.12.0.tar.gz/src/CMakeLists.txt Added

@@ -0,0 +1,538 @@
+set(MODULE QtAV)
+# TODO: translations, rpath, uchardet, x11extras, android
+
+include(CheckCCompilerFlag)
+include(CheckCXXSourceCompiles)
+include(CheckIncludeFile)
+include(CheckIncludeFiles)
+include(CheckLibraryExists)
+INCLUDE(CheckTypeSize)
+
+# set qt dirs first so we can find depends in qt install dir
+include_directories(${QTDIR}/include) #TODO: remove. use external/include
+get_filename_component(QTDIR "${QTDIR}" ABSOLUTE)
+
+list(APPEND EXTRA_INCLUDE ${CMAKE_SOURCE_DIR}/external/include)
+list(APPEND EXTRA_LIBS ${CMAKE_LIBRARY_PATH_FLAG}${CMAKE_SOURCE_DIR}/external/lib)
+if(APPLE)
+ if(IOS)
+ #set_xcode_property(myioslib IPHONEOS_DEPLOYMENT_TARGET "8.0")
+ else()
+ list(APPEND EXTRA_INCLUDE /usr/local/include) #macOS only
+ list(APPEND EXTRA_LIBS -L/usr/local/lib)
+ endif()
+endif()
+if(EXISTS ${CMAKE_SOURCE_DIR}/contrib/capi/capi.h)
+ set(HAVE_CAPI 1)
+ list(APPEND EXTRA_INCLUDE ${CMAKE_SOURCE_DIR}/contrib/capi) # TODO: only files use capi.h
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_CAPI=1)
+endif()
+
+# check ffmpeg headers. assume libs exist. lib order matters if they are static
+set(AVMODULES avformat avcodec swscale avutil) # avdevice avfilter avresample swscale)
+# CMAKE_FIND_ROOT_PATH_BOTH: ensure find_file can search from given paths for cross compiling, may be set to ONLY in toolchain file
+foreach(av ${AVMODULES})
+ string(TOUPPER ${av} AV)
+ find_file(HAVE_${AV} lib${av}/${av}.h HINTS ${EXTRA_INCLUDE} PATHS ${EXTRA_INCLUDE} CMAKE_FIND_ROOT_PATH_BOTH)
+ message("HAVE_${AV}: ${HAVE_${AV}}")
+ if(NOT ${HAVE_${AV}} MATCHES HAVE_${AV}-NOTFOUND)
+ set(HAVE_${AV} 1)
+ list(APPEND EXTRA_LIBS ${av})
+ list(APPEND EXTRA_DEFS "-DQTAV_HAVE_${AV}=1")
+ else()
+ message(FATAL_ERROR "${av} is required")
+ endif()
+ #check_include_file(lib${av}/${av}.h HAVE_${AV}) # -D__STDC_CONSTANT_MACROS is required!
+endforeach()
+
+foreach(av avfilter avdevice avresample swresample)
+ string(TOUPPER ${av} AV)
+ find_file(HAVE_${AV} lib${av}/${av}.h HINTS ${EXTRA_INCLUDE} PATHS ${EXTRA_INCLUDE} CMAKE_FIND_ROOT_PATH_BOTH)
+ message("HAVE_${AV}: ${HAVE_${AV}}")
+ if(NOT ${HAVE_${AV}} MATCHES HAVE_${AV}-NOTFOUND)
+ set(HAVE_${AV} 1)
+ list(APPEND EXTRA_LIBS ${av})
+ list(APPEND EXTRA_DEFS "-DQTAV_HAVE_${AV}=1")
+ list(APPEND AVMODULES ${av})
+ endif()
+endforeach()
+
+if (NOT HAVE_SWRESAMPLE)
+ if (NOT HAVE_AVRESAMPLE)
+ message(FATAL_ERROR "swresample or avresample is required")
+ endif()
+endif()
+
+list(APPEND EXTRA_DEFS -DBUILD_QTAV_LIB -D__STDC_CONSTANT_MACROS)
+
+check_include_file(ass/ass.h HAVE_ASS_H)
+if(HAVE_ASS_H)
+ if(HAVE_CAPI) # dynamic load
+ if(IOS OR ANDROID OR WindowsPhone OR WindowsStore)
+ else()
+ set(HAVE_ASS 1)
+ endif()
+ endif()
+ if(NOT HAVE_ASS) # link to ass
+ check_library_exists(ass ass_library_init "" HAVE_ASS)
+ if(HAVE_ASS)
+ set(DYNAMIC_ASS 0)
+ list(APPEND EXTRA_DEFS -DCAPI_LINK_ASS)
+ list(APPEND EXTRA_LIBS ass)
+ endif()
+ endif()
+endif()
+if(HAVE_ASS)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_LIBASS=1)
+ list(APPEND SOURCES
+ capi/ass_api.cpp
+ subtitle/SubtitleProcessorLibASS.cpp
+ )
+endif()
+
+set(DYNAMIC_OPENAL ${HAVE_CAPI})
+if(APPLE)
+ set(HAVE_OPENAL 1)
+ if(NOT DYNAMIC_OPENAL)
+ list(APPEND EXTRA_LIBS "-framework OpenAL")
+ endif()
+ list(APPEND EXTRA_DEFS -DHEADER_OPENAL_PREFIX)
+else()
+ set(OLD_REQUIRED_INCLUDES ${CMAKE_REQUIRED_INCLUDES})
+ set(CMAKE_REQUIRED_INCLUDES ${EXTRA_INCLUDE})
+ check_include_files(AL/al.h HAVE_AL_H)
+ set(CMAKE_REQUIRED_INCLUDES ${OLD_REQUIRED_INCLUDES})
+ if(HAVE_AL_H)
+ if(HAVE_CAPI) #TODO: option(LINK_OPENAL...)
+ set(HAVE_OPENAL 1)
+ # DYNAMIC_OPENAL is set by user
+ else()
+ if(WIN32)
+ check_library_exists(OpenAL alGetError "" HAVE_OPENAL)
+ else()
+ check_library_exists(openal alGetError "" HAVE_OPENAL)
+ if(NOT HAVE_OPENAL)
+ check_library_exists(OpenAL alGetError "" HAVE_OPENAL) # blackberry
+ if(HAVE_OPENAL)
+ list(APPEND EXTRA_LIBS OpenAL)
+ endif()
+ else()
+ list(APPEND EXTRA_LIBS openal)
+ endif()
+ endif()
+ if(HAVE_OPENAL)
+ set(DYNAMIC_OPENAL 0)
+ endif()
+ endif()
+ endif()
+endif()
+if(HAVE_OPENAL AND NOT DYNAMIC_OPENAL)
+ list(APPEND EXTRA_DEFS -DCAPI_LINK_OPENAL)
+endif()
+if(HAVE_OPENAL)
+ list(APPEND SOURCES
+ capi/openal_api.cpp
+ output/audio/AudioOutputOpenAL.cpp
+ )
+endif()
+
+if (APPLE)
+ set(CMAKE_CXX_SYSTEM_FRAMEWORK_SEARCH_FLAG "-F ") # original is "-iframework", lots of build errors
+ set(CMAKE_C_SYSTEM_FRAMEWORK_SEARCH_FLAG "-F ")
+ set(OLD_REQUIRED_LIBRARIES ${CMAKE_REQUIRED_LIBRARIES})
+ set(CMAKE_REQUIRED_LIBRARIES ${CMAKE_REQUIRED_LIBRARIES} avcodec)
+ check_c_source_compiles(
+ "#include <libavcodec/videotoolbox.h>
+ int main() {
+ av_videotoolbox_alloc_context();
+ return 0;
+ }" HAVE_VIDEOTOOLBOX)
+ set(CMAKE_REQUIRED_LIBRARIES ${OLD_REQUIRED_LIBRARIES})
+
+ if (HAVE_VIDEOTOOLBOX)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_VIDEOTOOLBOX=1)
+ list(APPEND EXTRA_LIBS "-framework CoreMedia" "-framework VideoToolbox" "-framework CoreVideo")
+ list(APPEND SOURCES 
+ codec/video/VideoDecoderVideoToolbox.cpp
+ codec/video/SurfaceInteropCV.cpp
+ )
+ if (IOS)
+ list(APPEND SOURCES 
+ codec/video/SurfaceInteropCVOpenGLES.mm
+ )
+ else()
+ list(APPEND SOURCES 
+ codec/video/SurfaceInteropIOSurface.cpp
+ )
+ endif()
+ endif()
+
+ list(APPEND SOURCES output/audio/AudioOutputAudioToolbox.cpp)
+ list(APPEND EXTRA_LIBS "-framework CoreFoundation" "-framework AudioToolbox" "-framework OpenGL")
+endif()
+
+set(DEP_H OPENAL VIDEOTOOLBOX)
+foreach (D ${DEP_H})
+ if (${D})
+ ADD_DEFINITIONS(-DQTAV_HAVE_${D}=1)
+ endif()
+endforeach()
+
+if (HAVE_AVRESAMPLE)
+ list(APPEND SOURCES AudioResamplerLibav.cpp)
+endif()
+if (HAVE_SWRESAMPLE)
+ list(APPEND SOURCES AudioResamplerFF.cpp)
+endif()
+
+set(HAVE_EGL 0)
+set(DYNAMIC_GL 0)
+set(OPENGL 0) #desktop opengl only
+set(OPENGLES 0) #glesv2 only
+set(HAVE_OPENGL 1) # qt with opengl enabled. 1 of DYNAMIC_GL, OPENGL and OPENGLES is true
+#get_target_property(QtGui_location Qt5::Gui LOCATION) #dll path
+
+if(Qt5Gui_OPENGL_IMPLEMENTATION STREQUAL GL) # windows always set to GL
+ if(EXISTS ${QT_INSTALL_HEADERS}/QtANGLE)
+ set(DYNAMIC_GL 1) # assume Qt5Gui_OPENGL_IMPLEMENTATION is not GL if build with ANGLE only
+ if(NOT DEFINED Qt5Gui_EGL_INCLUDE_DIRS)
+ set(Qt5Gui_EGL_INCLUDE_DIRS ${QT_INSTALL_HEADERS}/QtANGLE)
+ endif()
+ else()
+ set(OPENGL 1)
+ endif()
+ if(DEFINED Qt5Gui_EGL_LIBRARIES) # x11?
+ set(HAVE_EGL 1)
+ endif()
+else()
+ set(OPENGLES 1)
+endif()
+if(OPENGLES OR DYNAMIC_GL)
+ set(HAVE_EGL 1)
+endif()
+if(NOT OPENGL AND NOT OPENGLES AND NOT DYNAMIC_GL)
+ set(HAVE_OPENGL 0)
+endif()
+if(HAVE_OPENGL)
+ if(WIN32 AND NOT DYNAMIC_GL AND NOT OPENGLES) # msys2
+ find_package(OpenGL REQUIRED)
+ list(APPEND EXTRA_LIBS ${OPENGL_gl_LIBRARY})
+ endif()
+endif()
+
+file(GLOB SDK_HEADERS QtAV/*.h)
+list(APPEND SDK_HEADERS QtAV/QtAV)
+file(GLOB SDK_PRIVATE_HEADERS QtAV/private/*.h)
+
+list(APPEND SOURCES
+ AVCompat.cpp
+ QtAV_Global.cpp
+ subtitle/CharsetDetector.cpp
+ subtitle/PlainText.cpp
+ subtitle/PlayerSubtitle.cpp
+ subtitle/Subtitle.cpp
+ subtitle/SubtitleProcessor.cpp
+ subtitle/SubtitleProcessorFFmpeg.cpp
+ subtitle/SubImage.cpp
+ utils/GPUMemCopy.cpp
+ utils/Logger.cpp
+ AudioThread.cpp
+ utils/internal.cpp
+ AVThread.cpp
+ AudioFormat.cpp
+ AudioFrame.cpp
+ AudioResampler.cpp
+ AudioResamplerTemplate.cpp
+ codec/audio/AudioDecoder.cpp
+ codec/audio/AudioDecoderFFmpeg.cpp
+ codec/audio/AudioEncoder.cpp
+ codec/audio/AudioEncoderFFmpeg.cpp
+ codec/AVDecoder.cpp
+ codec/AVEncoder.cpp
+ AVMuxer.cpp
+ AVDemuxer.cpp
+ AVDemuxThread.cpp
+ ColorTransform.cpp
+ Frame.cpp
+ FrameReader.cpp
+ filter/Filter.cpp
+ filter/FilterContext.cpp
+ filter/FilterManager.cpp
+ filter/LibAVFilter.cpp
+ filter/SubtitleFilter.cpp
+ filter/EncodeFilter.cpp
+ ImageConverter.cpp
+ ImageConverterFF.cpp
+ Packet.cpp
+ PacketBuffer.cpp
+ AVError.cpp
+ AVPlayer.cpp
+ AVPlayerPrivate.cpp
+ AVTranscoder.cpp
+ AVClock.cpp
+ VideoCapture.cpp
+ VideoFormat.cpp
+ VideoFrame.cpp
+ io/MediaIO.cpp
+ io/QIODeviceIO.cpp
+ output/audio/AudioOutput.cpp
+ output/audio/AudioOutputBackend.cpp
+ output/audio/AudioOutputNull.cpp
+ output/video/VideoRenderer.cpp
+ output/video/VideoOutput.cpp
+ output/video/QPainterRenderer.cpp
+ output/AVOutput.cpp
+ output/OutputSet.cpp
+ Statistics.cpp
+ codec/video/VideoDecoder.cpp
+ codec/video/VideoDecoderFFmpegBase.cpp
+ codec/video/VideoDecoderFFmpeg.cpp
+ codec/video/VideoDecoderFFmpegHW.cpp
+ codec/video/VideoEncoder.cpp
+ codec/video/VideoEncoderFFmpeg.cpp
+ VideoThread.cpp
+ VideoFrameExtractor.cpp
+ )
+
+if(HAVE_OPENGL)
+ aux_source_directory(opengl SRC_OPENGL) 
+ list(APPEND SOURCES ${SRC_OPENGL})
+ list(APPEND SOURCES
+ filter/GLSLFilter.cpp
+ output/video/OpenGLRendererBase.cpp
+ )
+ if(NOT Qt5Gui_VERSION VERSION_LESS 5.4.0)
+ list(APPEND SDK_HEADERS QtAV/OpenGLWindowRenderer.h)
+ list(APPEND SOURCES output/video/OpenGLWindowRenderer.cpp)
+ endif()
+endif()
+
+if(HAVE_EGL)
+ list(APPEND SOURCES capi/egl_api.cpp)
+ # TODO: X11Extras
+ if(DEFINED Qt5Gui_EGL_INCLUDE_DIRS) # ANGLE
+ list(APPEND EXTRA_INCLUDE ${Qt5Gui_EGL_INCLUDE_DIRS})
+ #list(APPEND EXTRA_DEFS -DQTAV_HAVE_QT_EGL=1)
+ if(HAVE_CAPI AND NOT IOS)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_EGL_CAPI=1)
+ if(WindowsPhone OR WindowsStore)
+ list(APPEND EXTRA_DEFS -DCAPI_LINK_EGL)
+ endif()
+ endif()
+ endif()
+endif()
+if(WIN32 OR WindowsStore OR WindowsPhone)
+ check_include_files(XAudio2.h HAVE_XAUDIO2_H)
+ if(NOT HAVE_XAUDIO2_H)
+ list(APPEND EXTRA_INCLUDE ${CMAKE_SOURCE_DIR}/contrib/dxsdk)
+ endif()
+ message("Qt5Gui_EGL_INCLUDE_DIRS: ${Qt5Gui_EGL_INCLUDE_DIRS}")
+ list(APPEND HEADERS
+ output/audio/xaudio2_compat.h
+ codec/video/VideoDecoderD3D.h
+ )
+ list(APPEND SOURCES
+ utils/DirectXHelper.cpp
+ output/audio/AudioOutputXAudio2.cpp
+ codec/video/VideoDecoderD3D.cpp
+ )
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_XAUDIO2=1)
+ set(OLD_REQUIRED_LIBRARIES ${CMAKE_REQUIRED_LIBRARIES})
+ set(CMAKE_REQUIRED_LIBRARIES ${CMAKE_REQUIRED_LIBRARIES} avcodec) # TODO: lib dir
+ set(OLD_REQUIRED_INCLUDES ${CMAKE_REQUIRED_INCLUDES})
+ set(CMAKE_REQUIRED_INCLUDES ${EXTRA_INCLUDE} ${CMAKE_CURRENT_SOURCE_DIR})
+ check_cxx_source_compiles("
+ #include \"directx/dxcompat.h\"
+ #include <d3d11.h>
+ extern \"C\" {
+ #include <libavcodec/d3d11va.h>
+ }
+ #include <wrl/client.h> //ComPtr is used in QtAV
+ int main() {
+ av_d3d11va_alloc_context();
+ D3D11_VIDEO_PROCESSOR_STREAM s; //used by vp
+ return 0;
+ }
+ " HAVE_D3D11)
+ set(CMAKE_REQUIRED_INCLUDES ${OLD_REQUIRED_INCLUDES})
+ set(CMAKE_REQUIRED_LIBRARIES ${OLD_REQUIRED_LIBRARIES})
+ if(HAVE_D3D11)
+ # https://crascit.com/2015/03/28/enabling-cxx11-in-cmake/ (global and specified target)
+ set(CMAKE_CXX_STANDARD 11)
+ set(CMAKE_CXX_STANDARD_REQUIRED ON)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_D3D11VA=1)
+ list(APPEND SOURCES
+ codec/video/VideoDecoderD3D11.cpp
+ directx/SurfaceInteropD3D11.cpp
+ directx/D3D11VP.cpp
+ )
+ if(HAVE_EGL)
+ list(APPEND SOURCES directx/SurfaceInteropD3D11EGL.cpp)
+ endif()
+ if(HAVE_OPENGL AND NOT OPENGLES) # dynamic gl or desktop
+ list(APPEND SOURCES directx/SurfaceInteropD3D11GL.cpp)
+ endif()
+ endif()
+ if(WindowsStore OR WindowsPhone)
+ list(APPEND SOURCES io/WinRTIO.cpp)
+ list(APPEND EXTRA_LIBS
+ xaudio2 #only for xbox or >=win8
+ shcore
+ )
+ if(HAVE_D3D11)
+ list(APPEND EXTRA_LIBS d3d11)
+ endif()
+ else()
+ list(APPEND EXTRA_LIBS ole32 user32) #ole32: CoInitializeEx for vs2008, but can not find the symbol at runtime
+ list(APPEND SOURCES
+ output/audio/AudioOutputDSound.cpp
+ directx/SurfaceInteropD3D9.cpp
+ codec/video/VideoDecoderDXVA.cpp
+ )
+ if(HAVE_EGL)
+ list(APPEND SOURCES directx/SurfaceInteropD3D9EGL.cpp)
+ endif()
+ if(OPENGL OR DYNAMIC_GL)
+ list(APPEND SOURCES directx/SurfaceInteropD3D9GL.cpp)
+ endif()
+ list(APPEND EXTRA_DEFS
+ -DQTAV_HAVE_DSOUND=1
+ -DQTAV_HAVE_DXVA=1
+ )
+ endif()
+endif()
+check_library_exists(portaudio Pa_Initialize "" HAVE_PORTAUDIO)
+if(HAVE_PORTAUDIO)
+ list(APPEND SOURCES output/audio/AudioOutputPortAudio.cpp)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_PORTAUDIO=1)
+ list(APPEND EXTRA_LIBS portaudio)
+endif()
+check_library_exists(pulse pa_threaded_mainloop_new "" HAVE_PULSE)
+if(HAVE_PULSE)
+ list(APPEND SOURCES output/audio/AudioOutputPulse.cpp)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_PULSEAUDIO=1)
+ list(APPEND EXTRA_LIBS pulse)
+endif()
+check_library_exists(OpenSLES slCreateEngine "" HAVE_OPENSL)
+if(HAVE_OPENSL)
+ list(APPEND SOURCES output/audio/AudioOutputOpenSL.cpp)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_OPENSL=1)
+ list(APPEND EXTRA_LIBS OpenSLES)
+endif()
+check_library_exists(va vaInitialize "" HAVE_VAAPI)
+if(HAVE_VAAPI)
+ list(APPEND SOURCES
+ vaapi/vaapi_helper.cpp
+ vaapi/SurfaceInteropVAAPI.cpp
+ codec/video/VideoDecoderVAAPI.cpp
+ )
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_VAAPI=1)
+ list(APPEND EXTRA_LIBS va X11)
+endif()
+
+if(NOT APPLE)
+ list(APPEND EXTRA_DEFS -DQTAV_HAVE_CUDA=1)
+ list(APPEND EXTRA_INCLUDE ${CMAKE_CURRENT_SOURCE_DIR}/cuda)
+ list(APPEND SOURCES
+ cuda/cuda_api.cpp
+ codec/video/SurfaceInteropCUDA.cpp
+ codec/video/VideoDecoderCUDA.cpp
+ )
+endif()
+
+list(APPEND HEADERS ${SDK_HEADERS} ${SDK_PRIVATE_HEADERS}
+ AVPlayerPrivate.h
+ AVDemuxThread.h
+ AVThread.h
+ AVThread_p.h
+ AudioThread.h
+ PacketBuffer.h
+ VideoThread.h
+ ImageConverter.h
+ ImageConverter_p.h
+ codec/video/VideoDecoderFFmpegBase.h
+ codec/video/VideoDecoderFFmpegHW.h
+ codec/video/VideoDecoderFFmpegHW_p.h
+ filter/FilterManager.h
+ subtitle/CharsetDetector.h
+ subtitle/PlainText.h
+ utils/BlockingQueue.h
+ utils/GPUMemCopy.h
+ utils/Logger.h
+ utils/SharedPtr.h
+ utils/ring.h
+ utils/internal.h
+ output/OutputSet.h
+ ColorTransform.h
+ )
+
+# TODO: rc template
+SET(RESOURCES ${MODULE}.qrc shaders/shaders.qrc)
+SOURCE_GROUP("Resources" FILES ${RESOURCES})
+QT5_ADD_RESOURCES(RESOURCES_SOURCES ${RESOURCES})
+set_source_files_properties(${RESOURCES_SOURCES} PROPERTIES GENERATED ON)
+if(WIN32)
+ set(RC_FILE ${CMAKE_CURRENT_BINARY_DIR}/${MODULE}.rc)
+ configure_file(${CMAKE_SOURCE_DIR}/cmake/QtAV.rc.in ${RC_FILE})
+endif()
+# add HEADERS for moc
+add_library(${MODULE} SHARED ${SOURCES} ${RESOURCES_SOURCES} ${HEADERS} ${RC_FILE})
+
+list(REMOVE_DUPLICATES EXTRA_LIBS)
+# qt5_use_modules(since 2.8.9) is deprecated since cmake 2.8.11
+target_link_libraries(${MODULE} 
+ LINK_PRIVATE ${EXTRA_LIBS}
+ LINK_PUBLIC Qt5::Core Qt5::Gui # will add include dirs, macros etc.
+)
+set_target_properties(${MODULE} PROPERTIES
+ MACOSX_RPATH ON
+ FRAMEWORK ON
+ # MACOSX_FRAMEWORK_INFO_PLIST qtav-Info.plist
+ #PUBLIC_HEADER ${SDK_HEADERS}
+ #PRIVATE_HEADER ${SDK_PRIVATE_HEADERS}
+ XCODE_ATTRIBUTE_INSTALL_PATH "@rpath"
+
+ VERSION ${PROJECT_VERSION}
+ SOVERSION ${SO_VERSION}
+ OUTPUT_NAME ${MODULE}
+ CLEAN_DIRECT_OUTPUT 1
+ #LINK_SEARCH_START_STATIC 1
+ LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib
+)
+
+#http://stackoverflow.com/questions/19866424/cmake-and-qt5-automoc-error
+#http://doc.qt.io/qt-5/cmake-manual.html
+set(CMAKE_INCLUDE_CURRENT_DIR ON) # for .moc
+target_include_directories(${MODULE}
+ PUBLIC $<INSTALL_INTERFACE:include>
+ PUBLIC $<INSTALL_INTERFACE:include/${MODULE}>
+ PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
+ PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/${MODULE}>
+ PRIVATE ${EXTRA_INCLUDE}
+ )
+target_compile_definitions(${MODULE} PRIVATE ${EXTRA_DEFS})
+
+install(FILES
+ ${SDK_HEADERS}
+ DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}
+)
+install(FILES
+ ${SDK_PRIVATE_HEADERS}
+ DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}/private
+)
+install(TARGETS ${MODULE}
+ EXPORT ${MODULE}-targets
+ #PUBLIC_HEADER DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE} # list is too long
+ #PRIVATE_HEADER DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}/private
+ RUNTIME DESTINATION ${QTAV_INSTALL_BINS}
+ LIBRARY DESTINATION ${QTAV_INSTALL_LIBS}
+ ARCHIVE DESTINATION ${QTAV_INSTALL_LIBS}
+ FRAMEWORK DESTINATION ${QTAV_INSTALL_LIBS}
+)
+
+# FIXME: why QTAV_INCLUDE_DIRS is empty?
+install(EXPORT ${MODULE}-targets
+ DESTINATION ${QTAV_INSTALL_LIBS}/cmake/${MODULE}
+ FILE ${MODULE}-config.cmake
+)
+

QtAV-1.11.0.tar.gz/src/ColorTransform.cpp -> QtAV-1.12.0.tar.gz/src/ColorTransform.cpp Changed

@@ -24,6 +24,17 @@
 
 namespace QtAV {
 
+// http://www.brucelindbloom.com/index.html?Eqn_RGB_XYZ_Matrix.html
+static const QMatrix4x4 kXYZ2sRGB(3.2404542f,  -1.5371385f, -0.4985314f, 0.0f,
+                                  -0.9692660f,  1.8760108f,  0.0415560f, 0.0f,
+                                   0.0556434f, -0.2040259f,  1.0572252f, 0.0f,
+                                 0.0f, 0.0f, 0.0f, 1.0f);
+// http://www.cs.utah.edu/~halzahaw/CS7650/Project2/project2_index.html no gamma correction
+static const QMatrix4x4 kXYZ_RGB(2.5623f,  -1.1661f, -0.3962f, 0.0f,
+                                 -1.0215f,  1.9778f, 0.0437f,  0.0f,
+                                  0.0752f, -0.2562f, 1.1810f,  0.0f,
+                                 0.0f, 0.0f, 0.0f, 1.0f);
+
 static const QMatrix4x4 kGBR2RGB = QMatrix4x4(0, 0, 1, 0,
                                               1, 0, 0, 0,
                                               0, 1, 0, 0,
@@ -211,6 +222,9 @@
         // M *= rgb_range_translate*rgb_range_scale
         // TODO: transform to output color space other than RGB
         switch (cs_out) {
+        case ColorSpace_XYZ:
+            M = kXYZ2sRGB.inverted() * M;
+            break;
         case ColorSpace_RGB:
             M *= ColorRangeRGB(ColorRange_Full, range_out);
             break;
@@ -224,6 +238,9 @@
         }
 
         switch (cs_in) {
+        case ColorSpace_XYZ:
+            M *= kXYZ2sRGB;
+            break;
         case ColorSpace_RGB:
             break;
         case ColorSpace_GBR:
@@ -233,7 +250,8 @@
             M *= YUV2RGB(cs_in)*ColorRangeYUV(range_in, ColorRange_Full);
             break;
         }
-        if (bpc_scale != 1.0) {
+        if (bpc_scale != 1.0 && cs_in != ColorSpace_XYZ) { // why no range correction for xyz?
+            //qDebug("bpc scale: %f", bpc_scale);
             M *= QMatrix4x4(bpc_scale, 0, 0, 0,
                             0, bpc_scale, 0, 0,
                             0, 0, bpc_scale, 0,

QtAV-1.11.0.tar.gz/src/QtAV.rc -> QtAV-1.12.0.tar.gz/src/QtAV.rc Changed

QtAV-1.11.0.tar.gz/src/QtAV/AVClock.h -> QtAV-1.12.0.tar.gz/src/QtAV/AVClock.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/AVDemuxer.h -> QtAV-1.12.0.tar.gz/src/QtAV/AVDemuxer.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/AVPlayer.h -> QtAV-1.12.0.tar.gz/src/QtAV/AVPlayer.h Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -179,6 +179,10 @@
 qint64 position() const; //unit: ms
 //0: play once. N: play N+1 times. <0: infinity
 int repeat() const; //or repeatMax()?
+ /*!
+ * \brief currentRepeat
+ * \return -1 if not playback is stopped, otherwise (Playback times - 1)
+ */
 int currentRepeat() const;
 /*!
 * \brief setExternalAudio
@@ -201,9 +205,10 @@
 */
 const QVariantList& externalAudioTracks() const;
 const QVariantList& internalAudioTracks() const;
+ const QVariantList& internalVideoTracks() const;
 /*!
 * \brief setAudioStream
- * set an external audio file and stream number as audio track
+ * set an external audio file and stream number as audio track. It will be reset if setFile()/setIODevice()/setInput() is called
 * \param file external audio file. set empty to use internal audio tracks
 * \param n audio stream number n=0, 1, .... n<0: disable audio thread
 * \return false if fail
@@ -222,7 +227,7 @@
 * Set audio stream number in current media or external audio file
 */
 bool setAudioStream(int n);
- //TODO: n<0, no video thread
+ //TODO: n<0, no video thread. It will be reset if setFile()/setIODevice()/setInput() is called
 bool setVideoStream(int n);
 /*!
 * \brief internalAudioTracks
@@ -278,7 +283,8 @@
 */
 AudioOutput* audio();
 /*!
- * \brief setSpeed set playback speed.
+ * \brief setSpeed
+ * Set playback speed.
 * \param speed speed > 0. 1.0: normal speed
 * TODO: playbackRate
 */
@@ -303,10 +309,8 @@
 /*!
 * \brief setFrameRate
 * Force the (video) frame rate to a given value.
- * Call it before playback start.
- * If frame rate is set to a valid value(>0), the clock type will be set to
- * User configuration of AVClock::ClockType and autoClock will be ignored.
- * \param value <=0: ignore the value. normal playback ClockType and AVCloc
+ * AVClock::ClockType and autoClock will be changed internally.
+ * \param value <=0: use previous playback speed.
 * >0: force to a given (video) frame rate
 */
 void setFrameRate(qreal value);
@@ -337,7 +341,7 @@
 /*!
 * \brief setVideoDecoderPriority
 * also can set in opt.priority
- * \param names the video decoder name list in priority order. Name can be "FFmpeg", "CUDA", "DXVA", "D3D11", "VAAPI", "VDA", "VideoToolbox", case insensitive
+ * \param names the video decoder name list in priority order. Name can be "FFmpeg", "CUDA", "DXVA", "D3D11", "VAAPI", "VDA", "VideoToolbox", "MediaCodec", "MMAL", "QSV", "CrystalHD", case insensitive
 */
 void setVideoDecoderPriority(const QStringList& names);
 QStringList videoDecoderPriority() const;
@@ -388,7 +392,7 @@
 MediaEndAction mediaEndAction() const;
 void setMediaEndAction(MediaEndAction value);
 
-public slots:
+public Q_SLOTS:
 /*!
 * \brief load
 * Load the current media set by setFile(); Can be used to reload a media and call play() later. If already loaded, does nothing and return true.
@@ -563,6 +567,11 @@
 * Emitted when media is loaded. \sa internalAudioTracks
 */
 void internalAudioTracksChanged(const QVariantList& tracks);
+ /*!
+ * \brief internalVideoTracksChanged
+ * Emitted when media is loaded. \sa internalVideoTracks
+ */
+ void internalVideoTracksChanged(const QVariantList& tracks);
 void externalAudioTracksChanged(const QVariantList& tracks);
 void internalSubtitleTracksChanged(const QVariantList& tracks);
 /*!

QtAV-1.11.0.tar.gz/src/QtAV/AudioFormat.h -> QtAV-1.12.0.tar.gz/src/QtAV/AudioFormat.h Changed

@@ -69,15 +69,19 @@
 ChannelLayout_Unsupported //ok. now it's not complete
 };
 //typedef qint64 ChannelLayout; //currently use latest FFmpeg's
+ // TODO: constexpr
+ friend int RawSampleSize(SampleFormat fmt) { return fmt & ((1<<(kSize+1)) - 1); }
+ friend bool IsFloat(SampleFormat fmt) { return !!(fmt & kFloat);}
+ friend bool IsPlanar(SampleFormat format) { return !!(format & kPlanar);}
+ friend bool IsUnsigned(SampleFormat format) {return !!(format & kUnsigned);}
+ friend SampleFormat ToPlanar(SampleFormat fmt) { return IsPlanar(fmt) ? fmt : SampleFormat((int)fmt|kPlanar);}
+ friend SampleFormat ToPacked(SampleFormat fmt) { return IsPlanar(fmt) ? SampleFormat((int)fmt^kPlanar) : fmt;}
 
 static ChannelLayout channelLayoutFromFFmpeg(qint64 clff);
 static qint64 channelLayoutToFFmpeg(ChannelLayout cl);
 static SampleFormat sampleFormatFromFFmpeg(int fffmt);
 static int sampleFormatToFFmpeg(SampleFormat fmt);
- static bool isPlanar(SampleFormat format);
- static SampleFormat planarSampleFormat(SampleFormat fmt);
- static SampleFormat packedSampleFormat(SampleFormat fmt);
-
+ static SampleFormat make(int bytesPerSample, bool isFloat, bool isUnsigned, bool isPlanar);
 AudioFormat();
 AudioFormat(const AudioFormat &other);
 ~AudioFormat();

QtAV-1.11.0.tar.gz/src/QtAV/AudioOutput.h -> QtAV-1.12.0.tar.gz/src/QtAV/AudioOutput.h Changed

@@ -55,13 +55,15 @@
 public:
 /*!
 * \brief DeviceFeature Feature enum
- * features supported by the audio playback api (we call device or backend here)
+ * Features supported by the audio playback api (we call device or backend here)
+ * If a feature is not supported, e.g. SetVolume, then a software implementation is used.
 */
 enum DeviceFeature {
 NoFeature = 0,
- SetVolume = 1, /// NOT IMPLEMENTED. Use backend volume control api rather than software scale. Ignore if backend does not support.
- SetMute = 1 << 1, /// NOT IMPLEMENTED
+ SetVolume = 1, /// Use backend volume control api rather than software scale. Ignore if backend does not support.
+ SetMute = 1 << 1,
 SetSampleRate = 1 << 2, /// NOT IMPLEMENTED
+ SetSpeed = 1 << 3, /// NOT IMPLEMENTED
 };
 Q_DECLARE_FLAGS(DeviceFeatures, DeviceFeature)
 /*!
@@ -75,7 +77,7 @@
 * Audio format set to preferred sample format and channel layout
 */
 AudioOutput(QObject *parent = 0);
- virtual ~AudioOutput();
+ ~AudioOutput();
 /*!
 * \brief setBackends
 * set the given backends. Old backend instance and backend() is updated soon if backendsChanged.
@@ -108,22 +110,33 @@
 * for async playback backend, or until the data is completely played for blocking playback backend.
 * \param data Audio data to play
 * \param pts Timestamp for this data. Useful if need A/V sync. Ignore it if only play audio
- * \return true if play successfully
+ * \return false if currently isPaused(), no backend is available or backend failed to play
 */
 bool play(const QByteArray& data, qreal pts = 0.0);
- /// TODO: requestAudioFormat(): check support after open, use the nearest format if not supported. Or use suitableFormat(AudioFormat requestedFmt) if requestedFmt is not supported.
- void setAudioFormat(const AudioFormat& format);
- AudioFormat& audioFormat();
+ /*!
+ * \brief pause
+ * Pause audio rendering. play() will fail.
+ */
+ void pause(bool value);
+ bool isPaused() const;
+ /*!
+ * \brief setAudioFormat
+ * Set/Request to use the given \l format. If it's not supported, an preferred format will be used.
+ * \param format requested format
+ * \return actual format to use. Invalid format if backend is not available
+ * NOTE: Check format support may fail for some backends (OpenAL) if it's closed.
+ */
+ AudioFormat setAudioFormat(const AudioFormat& format);
+ const AudioFormat& requestedFormat() const;
+ /*!
+ * \brief audioFormat
+ * \return actual format for requested format
+ */
 const AudioFormat& audioFormat() const;
-
- void setSampleRate(int rate); //deprecated
- int sampleRate() const; //deprecated
- void setChannels(int channels); //deprecated
- int channels() const; //deprecated
 /*!
 * \brief setVolume
 * Set volume level.
- * If SetVolume feature is not set or not supported, software implemention will be used.
+ * If SetVolume feature is not set or not supported, software implementation will be used.
 * Call this after open(), because it will call backend api if SetVolume feature is enabled
 * \param volume linear. 1.0: original volume.
 */
@@ -131,7 +144,7 @@
 qreal volume() const;
 /*!
 * \brief setMute
- * If SetMute feature is not set or not supported, software implemention will be used.
+ * If SetMute feature is not set or not supported, software implementation will be used.
 * Call this after open(), because it will call backend api if SetMute feature is enabled
 */
 void setMute(bool value = true);
@@ -152,21 +165,9 @@
 * check \a isSupported(format.sampleFormat()) and \a isSupported(format.channelLayout())
 * \param format
 * \return true if \a format is supported. default is true
+ * NOTE: may fail for some backends if it's closed, for example OpenAL
 */
 bool isSupported(const AudioFormat& format) const;
- bool isSupported(AudioFormat::SampleFormat sampleFormat) const;
- bool isSupported(AudioFormat::ChannelLayout channelLayout) const;
- /*!
- * \brief preferredSampleFormat
- * \return the preferred sample format. default is signed16 packed
- * If the specified format is not supported, resample to preffered format
- */
- AudioFormat::SampleFormat preferredSampleFormat() const;
- /*!
- * \brief preferredChannelLayout
- * \return the preferred channel layout. default is stereo
- */
- AudioFormat::ChannelLayout preferredChannelLayout() const;
 /*!
 * \brief bufferSamples
 * Number of samples that audio output accept in 1 buffer. Feed the audio output this size of data every time.
@@ -215,7 +216,7 @@
 * \brief waitForNextBuffer
 * wait until you can feed more data
 */
- virtual bool waitForNextBuffer();
+ bool waitForNextBuffer();
 private Q_SLOTS:
 void reportVolume(qreal value);
 void reportMute(bool value);

QtAV-1.11.0.tar.gz/src/QtAV/Filter.h -> QtAV-1.12.0.tar.gz/src/QtAV/Filter.h Changed

QtAV-1.12.0.tar.gz/src/QtAV/Geometry.h Added

@@ -0,0 +1,168 @@
+/******************************************************************************
+ QtAV: Multimedia framework based on Qt and FFmpeg
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
+
+* This file is part of QtAV (from 2016)
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+******************************************************************************/
+#ifndef QTAV_GEOMETRY_H
+#define QTAV_GEOMETRY_H
+#include <QtCore/QRectF>
+#include <QtCore/QVector>
+#include <QtAV/QtAV_Global.h>
+
+// TODO: generate vertex/fragment shader code from Geometry.attributes()
+namespace QtAV {
+
+enum DataType { //equals to GL_BYTE etc.
+ TypeS8 = 0x1400, //S8
+ TypeU8 = 0x1401, //U8
+ TypeS16 = 0x1402, //S16
+ TypeU16 = 0x1403, //U16
+ TypeS32 = 0x1404, //S32
+ TypeU32 = 0x1405, //U32
+ TypeF32 = 0x1406 //F32
+};
+
+class Q_AV_EXPORT Attribute {
+ bool m_normalize;
+ DataType m_type;
+ int m_tupleSize, m_offset;
+ QByteArray m_name;
+public:
+ Attribute(DataType type = TypeF32, int tupleSize = 0, int offset = 0, bool normalize = false);
+ Attribute(const QByteArray& name, DataType type = TypeF32, int tupleSize = 0, int offset = 0, bool normalize = false);
+ QByteArray name() const {return m_name;}
+ DataType type() const {return m_type;}
+ int tupleSize() const {return m_tupleSize;}
+ int offset() const {return m_offset;}
+ bool normalize() const {return m_normalize;}
+ bool operator==(const Attribute& other) const {
+ return tupleSize() == other.tupleSize()
+ && offset() == other.offset()
+ && type() == other.type()
+ && normalize() == other.normalize();
+ }
+};
+#ifndef QT_NO_DEBUG_STREAM
+Q_AV_EXPORT QDebug operator<<(QDebug debug, const Attribute &a);
+#endif
+
+/*!
+ * \brief The Geometry class
+ * \code
+ * foreach (const Attribute& a, g->attributes()) {
+ * program()->setAttributeBuffer(a.name(), a.type(), a.offset(), a.tupleSize(), g->stride());
+ * }
+ * \endcode
+ */
+class Q_AV_EXPORT Geometry {
+public:
+ /// Strip or Triangles is preferred by ANGLE. The values are equal to opengl
+ enum Primitive {
+ Triangles = 0x0004,
+ TriangleStrip = 0x0005, //default
+ TriangleFan = 0x0006, // Not recommended
+ };
+ Geometry(int vertexCount = 0, int indexCount = 0, DataType indexType = TypeU16);
+ virtual ~Geometry() {}
+ Primitive primitive() const {return m_primitive;}
+ void setPrimitive(Primitive value) { m_primitive = value;}
+ int vertexCount() const {return m_vcount;}
+ void setVertexCount(int value) {m_vcount = value;} // TODO: remove, or allocate data here
+ // TODO: setStride and no virtual
+ virtual int stride() const = 0;
+ // TODO: add/set/remove attributes()
+ virtual const QVector<Attribute>& attributes() const = 0;
+ void* vertexData() { return m_vdata.data();}
+ const void* vertexData() const { return m_vdata.constData();}
+ const void* constVertexData() const { return m_vdata.constData();}
+ void dumpVertexData();
+ void* indexData() { return m_icount > 0 ? m_idata.data() : NULL;}
+ const void* indexData() const { return m_icount > 0 ? m_idata.constData() : NULL;}
+ const void* constIndexData() const { return m_icount > 0 ? m_idata.constData() : NULL;}
+ int indexCount() const { return m_icount;}
+ int indexDataSize() const;
+ // GL_UNSIGNED_BYTE/SHORT/INT
+ DataType indexType() const {return m_itype;}
+ void setIndexType(DataType value) { m_itype = value;}
+ void setIndexValue(int index, int value);
+ void setIndexValue(int index, int v1, int v2, int v3); // a triangle
+ void dumpIndexData();
+ /*!
+ * \brief allocate
+ * Call allocate() when all parameters are set. vertexData() may change
+ */
+ void allocate(int nbVertex, int nbIndex = 0);
+ /*!
+ * \brief compare
+ * Compare each attribute and stride that used in glVertexAttribPointer
+ * \return true if equal
+ */
+ bool compare(const Geometry *other) const;
+protected:
+ Primitive m_primitive;
+ DataType m_itype;
+ int m_vcount;
+ int m_icount;
+ QByteArray m_vdata;
+ QByteArray m_idata;
+};
+
+class Q_AV_EXPORT TexturedGeometry : public Geometry {
+public:
+ TexturedGeometry();
+ /*!
+ * \brief setTextureCount
+ * sometimes we needs more than 1 texture coordinates, for example we have to set rectangle texture
+ * coordinates for each plane.
+ */
+ void setTextureCount(int value);
+ int textureCount() const;
+
+ void setRect(const QRectF& r, const QRectF& tr, int texIndex = 0);
+ void setGeometryRect(const QRectF& r);
+ void setTextureRect(const QRectF& tr, int texIndex = 0);
+ int stride() const Q_DECL_OVERRIDE { return 2*sizeof(float)*(textureCount()+1); }
+ const QVector<Attribute>& attributes() const Q_DECL_OVERRIDE;
+ virtual void create();
+private:
+ void setPoint(int index, const QPointF& p, const QPointF& tp, int texIndex = 0);
+ void setGeometryPoint(int index, const QPointF& p);
+ void setTexturePoint(int index, const QPointF& tp, int texIndex = 0);
+protected:
+ int nb_tex;
+ QRectF geo_rect;
+ QVector<QRectF> texRect;
+ QVector<Attribute> a;
+};
+
+class Q_AV_EXPORT Sphere : public TexturedGeometry {
+public:
+ Sphere();
+ void setResolution(int w, int h); // >= 2x2
+ void setRadius(float value);
+ float radius() const;
+ void create() Q_DECL_OVERRIDE;
+ int stride() const Q_DECL_OVERRIDE { return 3*sizeof(float)+2*sizeof(float)*textureCount(); }
+protected:
+ using Geometry::setPrimitive;
+private:
+ int ru, rv;
+ float r;
+};
+} //namespace QtAV
+#endif //QTAV_GEOMETRY_H

QtAV-1.12.0.tar.gz/src/QtAV/GeometryRenderer.h Added

@@ -0,0 +1,88 @@
+/******************************************************************************
+ QtAV: Multimedia framework based on Qt and FFmpeg
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
+
+* This file is part of QtAV (from 2016)
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+******************************************************************************/
+#ifndef QTAV_GEOMETRYRENDERER_H
+#define QTAV_GEOMETRYRENDERER_H
+#include <QtAV/Geometry.h>
+#define QT_VAO (QT_VERSION >= QT_VERSION_CHECK(5, 1, 0))
+#if QT_VAO
+#include <QtGui/QOpenGLVertexArrayObject>
+#endif //QT_VAO
+# if QT_VERSION >= QT_VERSION_CHECK(5, 0, 0)
+#include <QtGui/QOpenGLBuffer>
+#else
+#include <QtOpenGL/QGLBuffer>
+typedef QGLBuffer QOpenGLBuffer;
+#endif
+QT_BEGIN_NAMESPACE
+class QOpenGLShaderProgram;
+QT_END_NAMESPACE
+
+namespace QtAV {
+/*!
+ * \brief The GeometryRenderer class
+ * TODO: support multiple geometry with same primitive (glPrimitiveRestartIndex, glDrawArraysInstanced, glDrawArraysInstanced, glMultiDrawArrays...)
+ */
+class Q_AV_EXPORT GeometryRenderer
+{
+public:
+ // rendering features. Use all possible features as the default.
+ static const int kVBO = 0x01;
+ static const int kIBO = 0x02;
+ static const int kVAO = 0x04;
+ static const int kMapBuffer = 1<<16;
+ // TODO: VAB, VBUM etc.
+ GeometryRenderer();
+ virtual ~GeometryRenderer() {}
+ // call updateBuffer internally in bindBuffer if feature is changed
+ void setFeature(int f, bool on);
+ void setFeatures(int value);
+ int features() const;
+ int actualFeatures() const;
+ bool testFeatures(int value) const;
+ /*!
+ * \brief updateGeometry
+ * Update geometry buffer. Rebind VBO, IBO to VAO if geometry attributes is changed.
+ * Assume attributes are bound in the order 0, 1, 2,....
+ * Make sure the old geometry is not destroyed before this call because it will be used to compare with the new \l geo
+ * \param geo null: release vao/vbo
+ */
+ void updateGeometry(Geometry* geo = NULL);
+ virtual void render();
+protected:
+ void bindBuffers();
+ void unbindBuffers();
+private:
+ Geometry *g;
+ int features_;
+ int vbo_size, ibo_size; // QOpenGLBuffer.size() may get error 0x501
+ QOpenGLBuffer vbo; //VertexBuffer
+#if QT_VAO
+ QOpenGLVertexArrayObject vao;
+#endif //QT_VAO
+ QOpenGLBuffer ibo;
+
+ // geometry characteristic
+ int stride;
+ QVector<Attribute> attrib;
+};
+
+} //namespace QtAV
+#endif //QTAV_GEOMETRYRENDERER_H

QtAV-1.11.0.tar.gz/src/QtAV/MediaIO.h -> QtAV-1.12.0.tar.gz/src/QtAV/MediaIO.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/OpenGLVideo.h -> QtAV-1.12.0.tar.gz/src/QtAV/OpenGLVideo.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/OpenGLWindowRenderer.h -> QtAV-1.12.0.tar.gz/src/QtAV/OpenGLWindowRenderer.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/QtAV.h -> QtAV-1.12.0.tar.gz/src/QtAV/QtAV.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/QtAV_Global.h -> QtAV-1.12.0.tar.gz/src/QtAV/QtAV_Global.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/Subtitle.h -> QtAV-1.12.0.tar.gz/src/QtAV/Subtitle.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/SubtitleFilter.h -> QtAV-1.12.0.tar.gz/src/QtAV/SubtitleFilter.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/VideoCapture.h -> QtAV-1.12.0.tar.gz/src/QtAV/VideoCapture.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/VideoDecoder.h -> QtAV-1.12.0.tar.gz/src/QtAV/VideoDecoder.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/VideoEncoder.h -> QtAV-1.12.0.tar.gz/src/QtAV/VideoEncoder.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/VideoFormat.h -> QtAV-1.12.0.tar.gz/src/QtAV/VideoFormat.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/VideoFrame.h -> QtAV-1.12.0.tar.gz/src/QtAV/VideoFrame.h Changed

@@ -28,6 +28,7 @@
 /// TODO: fromAVFrame(const AVFrame* f);
 namespace QtAV {
 
+/// metadata: pallete for pal8
 class VideoFramePrivate;
 class Q_AV_EXPORT VideoFrame : public Frame
 {
@@ -75,8 +76,11 @@
     //int width(int plane = 0) const?
     int width() const;
     int height() const;
-    // plane width without padded bytes.
-    int effectivePlaneWidth(int plane) const;
+    /*!
+     * \brief effectiveBytesPerLine
+     * The plane bytes contains valid image data without padded data for alignment reason
+     */
+    int effectiveBytesPerLine(int plane) const;
     // plane width with padded bytes for alignment.
     int planeWidth(int plane) const;
     int planeHeight(int plane) const;
@@ -89,11 +93,6 @@
     ColorRange colorRange() const;
     void setColorRange(ColorRange value);
     /*!
-     * \brief effectiveBytesPerLine
-     * The plane bytes contains valid image data without padded data for alignment reason
-     */
-    int effectiveBytesPerLine(int plane) const;
-    /*!
      * \brief toImage
      * Return a QImage of current video frame, with given format, image size and region of interest.
      * If VideoFrame is constructed from an QImage, the target format, size and roi are the same, then no data copy.

QtAV-1.11.0.tar.gz/src/QtAV/VideoShader.h -> QtAV-1.12.0.tar.gz/src/QtAV/VideoShader.h Changed

@@ -185,7 +185,6 @@
     void setCurrentFrame(const VideoFrame& frame);
     VideoFormat currentFormat() const;
     VideoShader* createShader() const;
-    void initializeShader(VideoShader* shader) const;
     virtual qint32 type() const;
     static QString typeName(qint32 value);
 
@@ -193,7 +192,7 @@
     void unbind();
     int compare(const VideoMaterial* other) const;
 
-    bool hasAlpha() const;
+    int textureTarget() const;
     /*!
      * \brief isDirty
      * \return true if material type changed, or other properties changed, e.g. 8bit=>10bit (the same material type) and eq
@@ -252,7 +251,7 @@
      */
     QRectF normalizedROI(const QRectF& roi) const;
     /*!
-     * \brief mapToFrame
+     * \brief mapToTexture
      * map a point p or a rect r to video texture in a given plane and scaled to valid width.
      * p or r is in video frame's rect coordinates, no matter which plane is
      * \param normalize -1: auto(do not normalize for rectangle texture). 0: no. 1: yes
@@ -270,9 +269,6 @@
     qreal saturation() const;
     void setSaturation(qreal value);
 protected:
-    // TODO: roi
-    // whether to update texture is set internal
-    void bindPlane(int p, bool updateTexture = true);
     VideoMaterial(VideoMaterialPrivate &d);
     DPTR_DECLARE(VideoMaterial)
 };

QtAV-1.11.0.tar.gz/src/QtAV/private/AVCompat.h -> QtAV-1.12.0.tar.gz/src/QtAV/private/AVCompat.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/private/AudioOutputBackend.h -> QtAV-1.12.0.tar.gz/src/QtAV/private/AudioOutputBackend.h Changed

@@ -53,19 +53,10 @@
 virtual bool flush() { return false;}
 virtual bool clear() { return false;}
 virtual bool isSupported(const AudioFormat& format) const { return isSupported(format.sampleFormat()) && isSupported(format.channelLayout());}
- virtual bool isSupported(AudioFormat::SampleFormat) const { return true;}
- virtual bool isSupported(AudioFormat::ChannelLayout) const { return true;}
- /*!
- * \brief preferredSampleFormat
- * \return the preferred sample format. default is signed16 packed
- * If the specified format is not supported, resample to preffered format
- */
- virtual AudioFormat::SampleFormat preferredSampleFormat() const { return AudioFormat::SampleFormat_Signed16;}
- /*!
- * \brief preferredChannelLayout
- * \return the preferred channel layout. default is stereo
- */
- virtual AudioFormat::ChannelLayout preferredChannelLayout() const { return AudioFormat::ChannelLayout_Stereo;}
+ // FIXME: workaround. planar convertion crash now!
+ virtual bool isSupported(AudioFormat::SampleFormat f) const { return !IsPlanar(f);}
+ // 5, 6, 7 channels may not play
+ virtual bool isSupported(AudioFormat::ChannelLayout cl) const { return int(cl) < int(AudioFormat::ChannelLayout_Unsupported);}
 /*!
 * \brief The BufferControl enum
 * Used to adapt to different audio playback backend. Usually you don't need this in application level development.
@@ -84,6 +75,7 @@
 virtual BufferControl bufferControl() const = 0;
 // called by callback with Callback control
 virtual void onCallback();
+ virtual void acquireNextBuffer() {}
 //default return -1. means not the control
 virtual int getPlayedCount() {return -1;} //PlayedCount
 /*!

QtAV-1.11.0.tar.gz/src/QtAV/private/MediaIO_p.h -> QtAV-1.12.0.tar.gz/src/QtAV/private/MediaIO_p.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/private/OpenGLRendererBase_p.h -> QtAV-1.12.0.tar.gz/src/QtAV/private/OpenGLRendererBase_p.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/private/VideoShader_p.h -> QtAV-1.12.0.tar.gz/src/QtAV/private/VideoShader_p.h Changed

@@ -119,12 +119,10 @@
 v_texel_size.reserve(4);
 textures.reserve(4);
 texture_size.reserve(4);
- texture_upload_size.reserve(4);
 effective_tex_width.reserve(4);
 internal_format.reserve(4);
 data_format.reserve(4);
 data_type.reserve(4);
- texture_coords.reserve(4);
 static bool enable_pbo = qgetenv("QTAV_PBO").toInt() > 0;
 if (try_pbo)
 try_pbo = enable_pbo;
@@ -135,6 +133,7 @@
 bool initPBO(int plane, int size);
 bool initTexture(GLuint tex, GLint internal_format, GLenum format, GLenum dataType, int width, int height);
 bool updateTextureParameters(const VideoFormat& fmt);
+ void uploadPlane(int p, bool updateTexture = true);
 bool ensureResources();
 bool ensureTextures();
 void setupQuality();
@@ -158,14 +157,6 @@
 QVector<GLuint> textures; //texture ids. size is plane count
 QHash<GLuint, bool> owns_texture;
 QVector<QSize> texture_size;
- /*
- * actually if render a full frame, only plane 0 is enough. other planes are the same as texture size.
- * because linesize[0]>=linesize[1]
- * uploade size is required when
- * 1. y/u is not an integer because of alignment. then padding size of y < padding size of u, and effective size y/u != texture size y/u
- * 2. odd size. enlarge y
- */
- QVector<QSize> texture_upload_size;
 
 QVector<int> effective_tex_width; //without additional width for alignment
 qreal effective_tex_width_ratio;
@@ -174,7 +165,6 @@
 QVector<GLenum> data_format;
 QVector<GLenum> data_type;
 
- QVector<GLfloat> texture_coords;
 bool dirty;
 ColorTransform colorTransform;
 bool try_pbo;

QtAV-1.11.0.tar.gz/src/QtAV/private/singleton.h -> QtAV-1.12.0.tar.gz/src/QtAV/private/singleton.h Changed

QtAV-1.11.0.tar.gz/src/QtAV/version.h -> QtAV-1.12.0.tar.gz/src/QtAV/version.h Changed

QtAV-1.11.0.tar.gz/src/QtAV_Global.cpp -> QtAV-1.12.0.tar.gz/src/QtAV_Global.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -189,14 +189,14 @@
 QString aboutQtAV_HTML()
 {
 static QString about = QString::fromLatin1("<img src='qrc:/QtAV.svg'><h3>QtAV " QTAV_VERSION_STR_LONG "</h3>\n"
- "%1%2%3"
+ "%1%2%3 "
 "Copyright (C) 2012-2016 Wang Bin (aka. Lucas Wang) <a href='mailto:wbsecg1@gmail.com'>wbsecg1@gmail.com</a>\n"
 "%4: <a href='http://qtav.org/donate.html'>http://qtav.org/donate.html</a>\n"
 "%5: <a href='https://github.com/wang-bin/QtAV'>https://github.com/wang-bin/QtAV</a>\n"
 "%6: <a href='http://qtav.org'>http://qtav.org</a>"
 ).arg(QObject::tr("Multimedia framework base on Qt and FFmpeg.\n"))
 .arg(QObject::tr("Distributed under the terms of LGPLv2.1 or later.\n"))
- .arg(QObject::tr("Shanghai University->S3 Graphics->Deepin, Shanghai, China"))
+ .arg(QObject::tr("Shanghai University->S3 Graphics->Deepin->PPTV, Shanghai, China"))
 .arg(QObject::tr("Donate"))
 .arg(QObject::tr("Source"))
 .arg(QObject::tr("Home page"));

QtAV-1.11.0.tar.gz/src/VideoFormat.cpp -> QtAV-1.12.0.tar.gz/src/VideoFormat.cpp Changed

QtAV-1.11.0.tar.gz/src/VideoFrame.cpp -> QtAV-1.12.0.tar.gz/src/VideoFrame.cpp Changed

@@ -284,11 +284,6 @@
 return d_func()->height;
 }
 
-int VideoFrame::effectivePlaneWidth(int plane) const
-{
- return planeWidth(plane)*effectiveBytesPerLine(plane)/bytesPerLine(plane);
-}
-
 int VideoFrame::planeWidth(int plane) const
 {
 Q_D(const VideoFrame);
@@ -520,12 +515,18 @@
 m_cvt->setInSize(frame.width(), frame.height());
 m_cvt->setOutSize(frame.width(), frame.height());
 m_cvt->setInRange(frame.colorRange());
- QVector<const uchar*> pitch(format.planeCount());
- QVector<int> stride(format.planeCount());
+ const int pal = format.hasPalette();
+ QVector<const uchar*> pitch(format.planeCount() + pal);
+ QVector<int> stride(format.planeCount() + pal);
 for (int i = 0; i < format.planeCount(); ++i) {
 pitch[i] = frame.constBits(i);
 stride[i] = frame.bytesPerLine(i);
 }
+ const QByteArray paldata(frame.metaData(QStringLiteral("pallete")).toByteArray());
+ if (pal > 0) {
+ pitch[1] = (const uchar*)paldata.constData();
+ stride[1] = paldata.size();
+ }
 if (!m_cvt->convert(pitch.constData(), stride.constData())) {
 return VideoFrame();
 }

QtAV-1.11.0.tar.gz/src/VideoThread.cpp -> QtAV-1.12.0.tar.gz/src/VideoThread.cpp Changed

@@ -218,7 +218,12 @@
 if (vo && (!vo->isSupported(frame.pixelFormat())
 || (vo->isPreferredPixelFormatForced() && vo->preferredPixelFormat() != frame.pixelFormat())
 )) {
- VideoFrame outFrame(d.conv.convert(frame, vo->preferredPixelFormat()));
+ VideoFormat fmt(frame.format());
+ if (fmt.hasPalette() || fmt.isRGB())
+ fmt = VideoFormat::Format_RGB32;
+ else
+ fmt = vo->preferredPixelFormat();
+ VideoFrame outFrame(d.conv.convert(frame, fmt));
 if (!outFrame.isValid()) {
 d.outputSet->unlock();
 return false;
@@ -272,7 +277,7 @@
 const char* pkt_data = NULL; // workaround for libav9 decode fail but error code >= 0
 qint64 last_deliver_time = 0;
 int sync_id = 0;
- while (true) {
+ while (!d.stop) {
 processNextTask();
 //TODO: why put it at the end of loop then stepForward() not work?
 //processNextTask tryPause(timeout) and and continue outter loop
@@ -310,8 +315,6 @@
 wait_key_frame = false;
 qDebug("video thread gets an eof packet.");
 } else {
- if (d.stop) // user stop
- break;
 //qDebug() << pkt.position << " pts:" <<pkt.pts;
 //Compare to the clock
 if (!pkt.isValid()) {
@@ -321,7 +324,8 @@
 d.dec->flush(); //d.dec instead of dec because d.dec maybe changed in processNextTask() but dec is not
 d.render_pts0 = pkt.pts;
 sync_id = pkt.position;
- qDebug("video seek: %.3f, id: %d", d.render_pts0, sync_id);
+ if (pkt.pts >= 0)
+ qDebug("video seek: %.3f, id: %d", d.render_pts0, sync_id);
 d.pts_history = ring<qreal>(d.pts_history.capacity());
 v_a = 0;
 continue;
@@ -333,7 +337,7 @@
 nb_no_pts = 0;
 }
 if (nb_no_pts > 5) {
- qDebug("the stream may have no pts. force fps to: %f", d.force_fps < 0 ? -d.force_fps : 24);
+ qDebug("the stream may have no pts. force fps to: %f/%f", d.force_fps < 0 ? -d.force_fps : 24, d.force_fps);
 d.clock->setClockAuto(false);
 d.clock->setClockType(AVClock::VideoClock);
 if (d.force_fps < 0)
@@ -613,6 +617,14 @@
 //qDebug("v_a:%.4f, v_a_: %.4f", v_a, v_a_);
 }
 }
+#if 0
+ if (d.stop) {// user stop
+ // decode eof?
+ qDebug("decoding eof...");
+
+ while (d.dec && d.dec->decode(Packet::createEOF())) {d.dec->flush();}
+ }
+#endif
 d.packets.clear();
 qDebug("Video thread stops running...");
 }

QtAV-1.11.0.tar.gz/src/capi/ass_api.cpp -> QtAV-1.12.0.tar.gz/src/capi/ass_api.cpp Changed

QtAV-1.11.0.tar.gz/src/capi/ass_api.h -> QtAV-1.12.0.tar.gz/src/capi/ass_api.h Changed

QtAV-1.11.0.tar.gz/src/capi/egl_api.cpp -> QtAV-1.12.0.tar.gz/src/capi/egl_api.cpp Changed

QtAV-1.11.0.tar.gz/src/capi/egl_api.h -> QtAV-1.12.0.tar.gz/src/capi/egl_api.h Changed

QtAV-1.11.0.tar.gz/src/capi/openal_api.cpp -> QtAV-1.12.0.tar.gz/src/capi/openal_api.cpp Changed

QtAV-1.11.0.tar.gz/src/codec/AVDecoder.cpp -> QtAV-1.12.0.tar.gz/src/codec/AVDecoder.cpp Changed

@@ -27,20 +27,21 @@
 
 namespace QtAV {
 
-static AVCodec* get_codec(const QString &name, AVCodecID cid)
+static AVCodec* get_codec(const QString &name, const QString& hwa, AVCodecID cid)
 {
-    AVCodec *codec = 0;
-    if (!name.isEmpty()) {
-        codec = avcodec_find_decoder_by_name(name.toUtf8().constData());
-        if (!codec) {
-            const AVCodecDescriptor* cd = avcodec_descriptor_get_by_name(name.toUtf8().constData());
-            if (cd)
-                codec = avcodec_find_decoder(cd->id);
-        }
-    } else {
-        codec = avcodec_find_decoder(cid);
+    QString fullname(name);
+    if (name.isEmpty()) {
+        if (hwa.isEmpty())
+            return avcodec_find_decoder(cid);
+        fullname = QString("%1_%2").arg(avcodec_get_name(cid)).arg(hwa);
     }
-    return codec;
+    AVCodec *codec = avcodec_find_decoder_by_name(fullname.toUtf8().constData());
+    if (codec)
+        return codec;
+    const AVCodecDescriptor* cd = avcodec_descriptor_get_by_name(fullname.toUtf8().constData());
+    if (cd)
+        return avcodec_find_decoder(cd->id);
+    return NULL;
 }
 
 AVDecoder::AVDecoder(AVDecoderPrivate &d)
@@ -51,7 +52,7 @@
 
 AVDecoder::~AVDecoder()
 {
-    setCodecContext(0);
+    setCodecContext(0); // FIXME:  will call virtual
 }
 
 QString AVDecoder::name() const
@@ -72,11 +73,14 @@
         qWarning("FFmpeg codec context not ready");
         return false;
     }
-    AVCodec* codec = get_codec(codecName(), d.codec_ctx->codec_id);
-    if (!codec)  { // TODO: can be null for none-ffmpeg based decoders
+    const QString hwa = property("hwaccel").toString();
+    AVCodec* codec = get_codec(codecName(), hwa, d.codec_ctx->codec_id);
+    if (!codec) { // TODO: can be null for none-ffmpeg based decoders
         QString es(tr("No codec could be found for '%1'"));
         if (d.codec_name.isEmpty()) {
             es = es.arg(QLatin1String(avcodec_get_name(d.codec_ctx->codec_id)));
+            if (!hwa.isEmpty())
+                es.append('_').append(hwa);
         } else {
             es = es.arg(d.codec_name);
         }
@@ -107,6 +111,8 @@
     d.applyOptionsForDict();
     av_opt_set_int(d.codec_ctx, "refcounted_frames", d.enableFrameRef(), 0); // why dict may have no effect?
     // TODO: only open for ff decoders
+    //av_dict_set(&d.dict, "lowres", "1", 0);
+    // dict is used for a specified AVCodec options (priv_class), av_opt_set_xxx(avctx) is only for avctx
     AV_ENSURE_OK(avcodec_open2(d.codec_ctx, codec, d.options.isEmpty() ? NULL : &d.dict), false);
     d.is_open = true;
     static const char* thread_name[] = { "Single", "Frame", "Slice"};
@@ -122,6 +128,7 @@
     DPTR_D(AVDecoder);
     d.is_open = false;
     // hwa extra finalize can be here
+    flush();
     d.close();
     // TODO: reset config?
     if (d.codec_ctx) {
@@ -259,7 +266,7 @@
         // av_opt_set_defaults(codec_ctx); //can't set default values! result maybe unexpected
         return;
     }
-    // TODO: use QVariantMap only
+
     if (!options.contains(QStringLiteral("avcodec")))
         return;
     // workaround for VideoDecoderFFmpeg. now it does not call av_opt_set_xxx, so set here in dict

QtAV-1.11.0.tar.gz/src/codec/audio/AudioDecoderFFmpeg.cpp -> QtAV-1.12.0.tar.gz/src/codec/audio/AudioDecoderFFmpeg.cpp Changed

QtAV-1.11.0.tar.gz/src/codec/video/VideoDecoder.cpp -> QtAV-1.12.0.tar.gz/src/codec/video/VideoDecoder.cpp Changed

QtAV-1.11.0.tar.gz/src/codec/video/VideoDecoderCUDA.cpp -> QtAV-1.12.0.tar.gz/src/codec/video/VideoDecoderCUDA.cpp Changed

@@ -33,7 +33,6 @@
 * TODO: VC1, HEVC bsf
 */
 #define COPY_ON_DECODE 1
-#define FILTER_ANNEXB_CUVID 0
 /*
 * avc1, ccv1 => h264 + sps, pps, nal. use filter or lavcudiv
 * http://blog.csdn.net/gavinr/article/details/7183499
@@ -165,7 +164,7 @@
 can_load = dllapi::testLoad("nvcuvid");
 #endif //QTAV_HAVE(DLLAPI_CUDA)
 available = false;
- bitstream_filter_ctx = 0;
+ bsf = 0;
 cuctx = 0;
 cudev = 0;
 dec = 0;
@@ -184,8 +183,8 @@
 interop_res = cuda::InteropResourcePtr();
 }
 ~VideoDecoderCUDAPrivate() {
- if (bitstream_filter_ctx)
- av_bitstream_filter_close(bitstream_filter_ctx);
+ if (bsf)
+ av_bitstream_filter_close(bsf);
 if (!can_load)
 return;
 if (!isLoaded()) //cuda_api
@@ -321,7 +320,7 @@
 int nb_dec_surface;
 QString description;
 
- AVBitStreamFilterContext *bitstream_filter_ctx; //TODO: rename bsf_ctx
+ AVBitStreamFilterContext *bsf; //TODO: rename bsf_ctx
 
 VideoDecoderCUDA::CopyMode copy_mode;
 cuda::InteropResourcePtr interop_res; //may be still used in video frames when decoder is destroyed
@@ -389,10 +388,10 @@
 uint8_t *outBuf = 0;
 int outBufSize = 0;
 int filtered = 0;
- if (d.bitstream_filter_ctx) {
+ if (d.bsf) {
 // h264_mp4toannexb_filter does not use last parameter 'keyFrame', so just set 0
 //return: 0: not changed, no outBuf allocated. >0: ok. <0: fail
- filtered = av_bitstream_filter_filter(d.bitstream_filter_ctx, d.codec_ctx, NULL, &outBuf, &outBufSize
+ filtered = av_bitstream_filter_filter(d.bsf, d.codec_ctx, NULL, &outBuf, &outBufSize
 , (const uint8_t*)packet.data.constData(), packet.data.size()
 , 0);//d.is_keyframe);
 //qDebug("%s @%d filtered=%d outBuf=%p, outBufSize=%d", __FUNCTION__, __LINE__, filtered, outBuf, outBufSize);
@@ -662,27 +661,24 @@
 //parser_params.pExtVideoInfo
 
 qDebug("~~~~~~~~~~~~~~~~extradata: %p %d", codec_ctx->extradata, codec_ctx->extradata_size);
- /*!
- * NOTE: DO NOT call h264_extradata_to_annexb here if use av_bitstream_filter_filter
- * because av_bitstream_filter_filter will call h264_extradata_to_annexb and marks H264BSFContext has parsed
- * h264_extradata_to_annexb will not mark it
- * LAVFilter's
- */
-#if FILTER_ANNEXB_CUVID
 memset(&extra_parser_info, 0, sizeof(CUVIDEOFORMATEX));
 // nalu
- // TODO: check mpeg, avc1, ccv1? (lavf)
- if (codec_ctx->extradata && codec_ctx->extradata_size >= 6) {
- int ret = h264_extradata_to_annexb(codec_ctx, FF_INPUT_BUFFER_PADDING_SIZE);
- if (ret >= 0) {
- qDebug("%s @%d ret %d, size %d", __FUNCTION__, __LINE__, ret, codec_ctx->extradata_size);
- memcpy(extra_parser_info.raw_seqhdr_data, codec_ctx->extradata, codec_ctx->extradata_size);
+ extra_parser_info.format.seqhdr_data_length = 0;
+ if (codec_ctx->codec_id != QTAV_CODEC_ID(H264) && codec_ctx->codec_id != QTAV_CODEC_ID(HEVC)) {
+ if (codec_ctx->extradata_size > 0) {
 extra_parser_info.format.seqhdr_data_length = codec_ctx->extradata_size;
+ memcpy(extra_parser_info.raw_seqhdr_data, codec_ctx->extradata, FFMIN(sizeof(extra_parser_info.raw_seqhdr_data), codec_ctx->extradata_size));
 }
 }
 parser_params.pExtVideoInfo = &extra_parser_info;
-#endif
+
 CUDA_ENSURE(cuvidCreateVideoParser(&parser, &parser_params), false);
+ CUVIDSOURCEDATAPACKET seq_pkt;
+ seq_pkt.payload = extra_parser_info.raw_seqhdr_data;
+ seq_pkt.payload_size = extra_parser_info.format.seqhdr_data_length;
+ if (seq_pkt.payload_size > 0) {
+ CUDA_ENSURE(cuvidParseVideoData(parser, &seq_pkt), false);
+ }
 //lavfilter: cuStreamCreate
 force_sequence_update = true;
 //DecodeSequenceData()
@@ -783,14 +779,17 @@
 void VideoDecoderCUDAPrivate::setBSF(AVCodecID codec)
 {
 if (codec == QTAV_CODEC_ID(H264)) {
- if (!bitstream_filter_ctx) {
- bitstream_filter_ctx = av_bitstream_filter_init("h264_mp4toannexb");
- Q_ASSERT(bitstream_filter_ctx && "av_bitstream_filter_init error");
- }
+ if (!bsf)
+ bsf = av_bitstream_filter_init("h264_mp4toannexb");
+ Q_ASSERT(bsf && "h264_mp4toannexb bsf not found");
+ } else if (codec == QTAV_CODEC_ID(HEVC)) {
+ if (!bsf)
+ bsf = av_bitstream_filter_init("hevc_mp4toannexb");
+ Q_ASSERT(bsf && "hevc_mp4toannexb bsf not found");
 } else {
- if (bitstream_filter_ctx) {
- av_bitstream_filter_close(bitstream_filter_ctx);
- bitstream_filter_ctx = 0;
+ if (bsf) {
+ av_bitstream_filter_close(bsf);
+ bsf = 0;
 }
 }
 }

QtAV-1.11.0.tar.gz/src/codec/video/VideoDecoderFFmpeg.cpp -> QtAV-1.12.0.tar.gz/src/codec/video/VideoDecoderFFmpeg.cpp Changed

@@ -18,7 +18,6 @@
     License along with this library; if not, write to the Free Software
     Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 ******************************************************************************/
-
 #include "VideoDecoderFFmpegBase.h"
 #include "QtAV/private/AVCompat.h"
 #include "QtAV/private/factory.h"
@@ -39,6 +38,7 @@
     Q_OBJECT
     DPTR_DECLARE_PRIVATE(VideoDecoderFFmpeg)
     Q_PROPERTY(QString codecName READ codecName WRITE setCodecName NOTIFY codecNameChanged)
+    Q_PROPERTY(QString hwaccel READ hwaccel WRITE setHwaccel NOTIFY hwaccelChanged)
     Q_PROPERTY(DiscardType skip_loop_filter READ skipLoopFilter WRITE setSkipLoopFilter)
     Q_PROPERTY(DiscardType skip_idct READ skipIDCT WRITE setSkipIDCT)
     // Force a strict standard compliance when encoding (accepted values: -2 to 2)
@@ -111,6 +111,34 @@
     };
     Q_DECLARE_FLAGS(BugFlags, BugFlag)
 
+    static VideoDecoder* createMMAL() {
+        VideoDecoderFFmpeg *vd = new VideoDecoderFFmpeg();
+        vd->setProperty("hwaccel", "mmal");
+        return vd;
+    }
+    static VideoDecoder* createQSV() {
+        VideoDecoderFFmpeg *vd = new VideoDecoderFFmpeg();
+        vd->setProperty("hwaccel", "qsv");
+        return vd;
+    }
+    static VideoDecoder* createCrystalHD() {
+        VideoDecoderFFmpeg *vd = new VideoDecoderFFmpeg();
+        vd->setProperty("hwaccel", "crystalhd");
+        return vd;
+    }
+
+    static void registerHWA() {
+#if defined(Q_OS_WIN32) || (defined(Q_OS_LINUX) && !defined(Q_PROCESSOR_ARM) && !defined(QT_ARCH_ARM))
+        VideoDecoder::Register(VideoDecoderId_QSV, createQSV, "QSV");
+#endif
+#ifdef Q_OS_LINUX
+#if defined(Q_PROCESSOR_ARM)/*qt5*/ || defined(QT_ARCH_ARM) /*qt4*/
+        VideoDecoder::Register(VideoDecoderId_MMAL, createMMAL, "MMAL");
+#else
+        VideoDecoder::Register(VideoDecoderId_CrystalHD, createCrystalHD, "CrystalHD");
+#endif
+#endif
+    }
     VideoDecoderFFmpeg();
     VideoDecoderId id() const Q_DECL_OVERRIDE Q_DECL_FINAL;
     QString description() const Q_DECL_OVERRIDE Q_DECL_FINAL {
@@ -138,13 +166,28 @@
     MotionVectorVisFlags motionVectorVisFlags() const;
     void setBugFlags(BugFlags value);
     BugFlags bugFlags() const;
+    void setHwaccel(const QString& value);
+    QString hwaccel() const;
 Q_SIGNALS:
     void codecNameChanged() Q_DECL_OVERRIDE;
+    void hwaccelChanged();
 };
 
 extern VideoDecoderId VideoDecoderId_FFmpeg;
 FACTORY_REGISTER(VideoDecoder, FFmpeg, "FFmpeg")
 
+void RegisterFFmpegHWA_Man() {
+    VideoDecoderFFmpeg::registerHWA();
+}
+
+namespace {
+    static const struct factory_register_FFmpegHWA {
+        inline factory_register_FFmpegHWA() {
+            VideoDecoderFFmpeg::registerHWA();
+        }
+    } sInit_FFmpegHWA;
+}
+
 class VideoDecoderFFmpegPrivate Q_DECL_FINAL: public VideoDecoderFFmpegBasePrivate
 {
 public:
@@ -209,6 +252,7 @@
     int threads;
     int debug_mv;
     int bug;
+    QString hwa;
 };
 
 VideoDecoderFFmpeg::VideoDecoderFFmpeg():
@@ -229,6 +273,13 @@
 
 VideoDecoderId VideoDecoderFFmpeg::id() const
 {
+    DPTR_D(const VideoDecoderFFmpeg);
+    if (d.hwa == QLatin1String("mmal"))
+        return VideoDecoderId_MMAL;
+    if (d.hwa == QLatin1String("qsv"))
+        return VideoDecoderId_QSV;
+    if (d.hwa == QLatin1String("crystalhd"))
+        return VideoDecoderId_CrystalHD;
     return VideoDecoderId_FFmpeg;
 }
 
@@ -246,6 +297,9 @@
     frame.setTimestamp((double)d.frame->pkt_pts/1000.0);
     frame.setMetaData(QStringLiteral("avbuf"), QVariant::fromValue(AVFrameBuffersRef(new AVFrameBuffers(d.frame))));
     d.updateColorDetails(&frame);
+    if (frame.format().hasPalette()) {
+        frame.setMetaData(QStringLiteral("pallete"), QByteArray((const char*)d.frame->data[1], 256*4));
+    }
     return frame;
 }
 
@@ -353,6 +407,20 @@
     return (BugFlags)d_func().bug;
 }
 
+void VideoDecoderFFmpeg::setHwaccel(const QString &value)
+{
+    DPTR_D(VideoDecoderFFmpeg);
+    if (d.hwa == value)
+        return;
+    d.hwa = value.toLower();
+    Q_EMIT hwaccelChanged();
+}
+
+QString VideoDecoderFFmpeg::hwaccel() const
+{
+    return d_func().hwa;
+}
+
 //namespace {
 void i18n() {
     QObject::tr("codecName");

QtAV-1.11.0.tar.gz/src/codec/video/VideoDecoderFFmpegBase.cpp -> QtAV-1.12.0.tar.gz/src/codec/video/VideoDecoderFFmpegBase.cpp Changed

QtAV-1.11.0.tar.gz/src/codec/video/VideoDecoderVDA.cpp -> QtAV-1.12.0.tar.gz/src/codec/video/VideoDecoderVDA.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2014)
 
@@ -37,6 +37,12 @@
 #include <VideoDecodeAcceleration/VDADecoder.h>
 #include "utils/Logger.h"
 
+// av_vda_default_init2: 2015-05-13 - cc48409 / e7c5e17 - lavc 56.39.100 / 56.23.0
+// I(wang bin) found the nv12 is the best format on mac. Then mpv developers confirmed it and pigoz added it to ffmpeg
+#if AV_MODULE_CHECK(LIBAVCODEC, 56, 23, 0, 39, 100)
+#define AV_VDA_NEW
+#endif
+
 #ifdef MAC_OS_X_VERSION_MIN_REQUIRED
 #if MAC_OS_X_VERSION_MIN_REQUIRED >= 1070 //MAC_OS_X_VERSION_10_7
 #define OSX_TARGET_MIN_LION
@@ -46,6 +52,7 @@
 #define kCFCoreFoundationVersionNumber10_7 635.00
 #endif
 
+// hwaccel 1.2: av_vda_xxx
 namespace QtAV {
 namespace cv {
 VideoFormat::PixelFormat format_from_cv(int cv);
@@ -90,7 +97,9 @@
 out_fmt = VideoDecoderVDA::UYVY;
 copy_mode = VideoDecoderFFmpegHW::ZeroCopy;
 description = QStringLiteral("VDA");
+#ifndef AV_VDA_NEW
 memset(&hw_ctx, 0, sizeof(hw_ctx));
+#endif
 }
 ~VideoDecoderVDAPrivate() {qDebug("~VideoDecoderVDAPrivate");}
 bool open() Q_DECL_OVERRIDE;
@@ -99,10 +108,18 @@
 void* setup(AVCodecContext *avctx) Q_DECL_OVERRIDE;
 bool getBuffer(void **opaque, uint8_t **data) Q_DECL_OVERRIDE;
 void releaseBuffer(void *opaque, uint8_t *data) Q_DECL_OVERRIDE;
- AVPixelFormat vaPixelFormat() const Q_DECL_OVERRIDE { return QTAV_PIX_FMT_C(VDA_VLD);}
+ AVPixelFormat vaPixelFormat() const Q_DECL_OVERRIDE {
+#ifdef AV_VDA_NEW
+ return AV_PIX_FMT_VDA;
+#else
+ return QTAV_PIX_FMT_C(VDA_VLD);
+#endif
+ }
 
 VideoDecoderVDA::PixelFormat out_fmt;
+#ifndef AV_VDA_NEW
 struct vda_context hw_ctx;
+#endif
 };
 
 typedef struct {
@@ -175,7 +192,9 @@
 CVPixelBufferRef cvbuf; // keep ref until video frame is destroyed
 public:
 SurfaceInteropCVBuffer(CVPixelBufferRef cv, bool gl) : glinterop(gl), cvbuf(cv) {
- //CVPixelBufferRetain(cvbuf);
+#ifdef AV_VDA_NEW
+ CVPixelBufferRetain(cvbuf);
+#endif
 }
 ~SurfaceInteropCVBuffer() {
 CVPixelBufferRelease(cvbuf);
@@ -348,11 +367,17 @@
 
 void* VideoDecoderVDAPrivate::setup(AVCodecContext *avctx)
 {
+ releaseUSWC();
+#ifdef AV_VDA_NEW
+ av_vda_default_free(avctx);
+ AVVDAContext* hw_ctx = av_vda_alloc_context();
+ hw_ctx->cv_pix_fmt_type = out_fmt;
+ int status = av_vda_default_init2(avctx, hw_ctx);
+#else
 const int w = codedWidth(avctx);
 const int h = codedHeight(avctx);
 if (hw_ctx.decoder) {
 ff_vda_destroy_decoder(&hw_ctx);
- releaseUSWC();
 } else {
 memset(&hw_ctx, 0, sizeof(hw_ctx));
 hw_ctx.format = 'avc1'; //fourcc
@@ -365,13 +390,18 @@
 height = avctx->height;
 /* create the decoder */
 int status = ff_vda_create_decoder(&hw_ctx, codec_ctx->extradata, codec_ctx->extradata_size);
+#endif
 if (status) {
- qWarning("Failed to create decoder (%i): %s", status, vda_err_str(status));
+ qWarning("Failed to init VDA decoder (%#x %s): %s", status, av_err2str(status), vda_err_str(status));
 return NULL;
 }
- initUSWC(hw_ctx.width);
+ initUSWC(codedWidth(avctx));
 qDebug() << "VDA decoder created. format: " << cv::format_from_cv(out_fmt);
+#ifdef AV_VDA_NEW
+ return hw_ctx;
+#else
 return &hw_ctx;
+#endif
 }
 
 bool VideoDecoderVDAPrivate::getBuffer(void **opaque, uint8_t **data)
@@ -385,13 +415,6 @@
 {
 Q_UNUSED(opaque);
 Q_UNUSED(data)
-#if 0
- // released in getBuffer?
- CVPixelBufferRef cv_buffer = (CVPixelBufferRef)data;
- if (!cv_buffer)
- return;
- CVPixelBufferRelease(cv_buffer);
-#endif
 }
 
 bool VideoDecoderVDAPrivate::open()
@@ -415,20 +438,20 @@
 default:
 break;
 }
-#if 0
- if (!codec_ctx->extradata || codec_ctx->extradata_size < 7) {
- qWarning("VDA requires extradata.");
- return false;
- }
-#endif
- return setup(codec_ctx);
+ return true;
+ //return setup(codec_ctx); // must be in get_format() in hwa 1.2
 }
 
 void VideoDecoderVDAPrivate::close()
 {
 restore(); //IMPORTANT. can not call restore in dtor because ctx is 0 there
 qDebug("destroying VDA decoder");
+#ifdef AV_VDA_NEW
+ if (codec_ctx)
+ av_vda_default_free(codec_ctx);
+#else
 ff_vda_destroy_decoder(&hw_ctx);
+#endif
 releaseUSWC();
 }

QtAV-1.11.0.tar.gz/src/codec/video/VideoEncoderFFmpeg.cpp -> QtAV-1.12.0.tar.gz/src/codec/video/VideoEncoderFFmpeg.cpp Changed

@@ -27,6 +27,13 @@
 #include "QtAV/version.h"
 #include "utils/Logger.h"
 
+#if AV_MODULE_CHECK(LIBAVUTIL, 55, 13, 0, 27, 100)
+#define HAVE_AVHWCTX
+extern "C" {
+#include <libavutil/hwcontext.h>
+}
+#endif
+
 /*!
 * options (properties) are from libavcodec/options_table.h
 * enum name here must convert to lower case to fit the names in avcodec. done in AVEncoder.setOptions()
@@ -35,14 +42,42 @@
 
 namespace QtAV {
 
+#ifdef HAVE_AVHWCTX
+struct {
+ AVHWDeviceType type;
+ const char* name;
+} hwdevs[] = {
+{AV_HWDEVICE_TYPE_VDPAU, "vdpau"},
+{AV_HWDEVICE_TYPE_CUDA, "cuda"},
+{AV_HWDEVICE_TYPE_VAAPI, "vaapi"},
+{AV_HWDEVICE_TYPE_DXVA2, "dxva2"},
+};
+
+AVHWDeviceType fromHWAName(const char* name)
+{
+ for (size_t i = 0; i < sizeof(hwdevs)/sizeof(hwdevs[0]); ++i) {
+ if (qstrcmp(name, hwdevs[i].name) == 0)
+ return hwdevs[i].type;
+ }
+ return AVHWDeviceType(-1);
+}
+#endif // HAVE_AVHWCTX
+
 class VideoEncoderFFmpegPrivate;
-class VideoEncoderFFmpeg Q_DECL_FINAL: public VideoEncoder
+class VideoEncoderFFmpeg : public VideoEncoder
 {
+ Q_OBJECT
 DPTR_DECLARE_PRIVATE(VideoEncoderFFmpeg)
+ Q_PROPERTY(QString hwdevice READ hwDevice WRITE setHWDevice NOTIFY hwDeviceChanged)
 public:
 VideoEncoderFFmpeg();
 VideoEncoderId id() const Q_DECL_OVERRIDE;
 bool encode(const VideoFrame &frame = VideoFrame()) Q_DECL_OVERRIDE;
+
+ void setHWDevice(const QString& name);
+ QString hwDevice() const;
+Q_SIGNALS:
+ void hwDeviceChanged();
 };
 
 static const VideoEncoderId VideoEncoderId_FFmpeg = mkid::id32base36_6<'F', 'F', 'm', 'p', 'e', 'g'>::value;
@@ -64,6 +99,14 @@
 
 qint64 nb_encoded;
 QByteArray buffer;
+ QString hwdev;
+#ifdef HAVE_AVHWCTX
+ AVBufferRef *hw_device_ctx;
+
+ AVBufferRef *hwframes_ref;
+ AVHWFramesContext *hwframes;
+ QVector<AVPixelFormat> sw_fmts;
+#endif
 };
 
 bool VideoEncoderFFmpegPrivate::open()
@@ -94,38 +137,111 @@
 avctx->width = width; // coded_width works, why?
 avctx->height = height;
 // reset format_used to user defined format. important to update default format if format is invalid
- format_used = format.pixelFormat();
- if (format.pixelFormat() == VideoFormat::Format_Invalid) {
- if (codec->pix_fmts) {
- qDebug("use first supported pixel format: %d", codec->pix_fmts[0]);
- format_used = VideoFormat::pixelFormatFromFFmpeg((int)codec->pix_fmts[0]);
+ format_used = VideoFormat::Format_Invalid;
+ AVPixelFormat fffmt = (AVPixelFormat)format.pixelFormatFFmpeg();
+ if (codec->pix_fmts && format.isValid()) {
+ for (int i = 0; codec->pix_fmts[i] != AVPixelFormat(-1); ++i) {
+ if (fffmt == codec->pix_fmts[i]) {
+ format_used = format.pixelFormat();
+ break;
+ }
+ }
+ }
+ //avctx->sample_aspect_ratio =
+ AVPixelFormat hwfmt = AVPixelFormat(-1);
+ if (av_pix_fmt_desc_get(codec->pix_fmts[0])->flags & AV_PIX_FMT_FLAG_HWACCEL)
+ hwfmt = codec->pix_fmts[0];
+ bool use_hwctx = false;
+ if (hwfmt != AVPixelFormat(-1)) {
+#ifdef HAVE_AVHWCTX
+ const AVHWDeviceType dt = fromHWAName(codec_name.section(QChar('_'), -1).toUtf8().constData());
+ if (dt != AVHWDeviceType(-1)) {
+ use_hwctx = true;
+ avctx->pix_fmt = hwfmt;
+ hw_device_ctx = NULL;
+ AV_ENSURE(av_hwdevice_ctx_create(&hw_device_ctx, dt, hwdev.toLatin1().constData(), NULL, 0), false);
+ avctx->hw_frames_ctx = av_hwframe_ctx_alloc(hw_device_ctx);
+ if (!avctx->hw_frames_ctx) {
+ qWarning("Failed to create hw frame context for '%s'", codec_name.toLatin1().constData());
+ return false;
+ }
+ // get sw formats
+ const void *hwcfg = NULL;
+ AVHWFramesConstraints *constraints = av_hwdevice_get_hwframe_constraints(hw_device_ctx, hwcfg);
+ const AVPixelFormat* in_fmts = constraints->valid_sw_formats;
+ AVPixelFormat sw_fmt = AVPixelFormat(-1);
+ if (in_fmts) {
+ sw_fmt = in_fmts[0];
+ while (*in_fmts != AVPixelFormat(-1)) {
+ if (*in_fmts == fffmt)
+ sw_fmt = *in_fmts;
+ sw_fmts.append(*in_fmts);
+ ++in_fmts;
+ }
+ } else {
+ sw_fmt = QTAV_PIX_FMT_C(YUV420P);
+ }
+ av_hwframe_constraints_free(&constraints);
+ format_used = VideoFormat::pixelFormatFromFFmpeg(sw_fmt);
+ // encoder surface pool parameters
+ AVHWFramesContext* hwfs = (AVHWFramesContext*)avctx->hw_frames_ctx->data;
+ hwfs->format = hwfmt; // must the same as avctx->pix_fmt
+ hwfs->sw_format = sw_fmt; // if it's not set, vaapi will choose the last valid_sw_formats, but that's wrong for vaGetImage/DeriveImage. nvenc always need sw_format
+ // hw upload parameters. encoder's hwframes is just for parameter checking, will never be intialized, so we allocate an individual one.
+ hwframes_ref = av_hwframe_ctx_alloc(hw_device_ctx);
+ if (!hwframes_ref) {
+ qWarning("Failed to create hw frame context for uploading '%s'", codec_name.toLatin1().constData());
+ } else {
+ hwframes = (AVHWFramesContext*)hwframes_ref->data;
+ hwframes->format = hwfmt;
+ }
+ }
+#endif //HAVE_AVHWCTX
+ }
+
+ if (!use_hwctx) { // no hw device (videotoolbox, wrong device name etc.), or old ffmpeg
+ // TODO: check frame is hw frame
+ if (hwfmt == AVPixelFormat(-1)) { // sw enc
+ if (format_used == VideoFormat::Format_Invalid) {// requested format is not supported by sw enc
+ if (codec->pix_fmts) { //pix_fmts[0] is always a sw format here
+ qDebug("use first supported pixel format '%d' for sw encoder", codec->pix_fmts[0]);
+ format_used = VideoFormat::pixelFormatFromFFmpeg((int)codec->pix_fmts[0]);
+ }
+ }
 } else {
- qWarning("pixel format and supported pixel format are not set. use yuv420p");
+ if (format_used == VideoFormat::Format_Invalid) { // requested format is not supported by hw enc
+ qDebug("use first supported sw pixel format '%d' for hw encoder", codec->pix_fmts[1]);
+ if (codec->pix_fmts && codec->pix_fmts[1] != AVPixelFormat(-1))
+ format_used = VideoFormat::pixelFormatFromFFmpeg(codec->pix_fmts[1]);
+ }
+ }
+ if (format_used == VideoFormat::Format_Invalid) {
+ qWarning("fallback to yuv420p");
 format_used = VideoFormat::Format_YUV420P;
 }
+ avctx->pix_fmt = (AVPixelFormat)VideoFormat::pixelFormatToFFmpeg(format_used);
 }
- //avctx->sample_aspect_ratio =
- avctx->pix_fmt = (AVPixelFormat)VideoFormat::pixelFormatToFFmpeg(format_used);
 if (frame_rate > 0)
 avctx->time_base = av_d2q(1.0/frame_rate, frame_rate*1001.0+2);
 else
 avctx->time_base = av_d2q(1.0/VideoEncoder::defaultFrameRate(), VideoEncoder::defaultFrameRate()*1001.0+2);
 qDebug("size: %dx%d tbc: %f=%d/%d", width, height, av_q2d(avctx->time_base), avctx->time_base.num, avctx->time_base.den);
 avctx->bit_rate = bit_rate;
-#if 1
 //AVDictionary *dict = 0;
 if(avctx->codec_id == QTAV_CODEC_ID(H264)) {
 avctx->gop_size = 10;
 //avctx->max_b_frames = 3;//h264
- av_dict_set(&dict, "preset", "fast", 0);
- av_dict_set(&dict, "tune", "zerolatency", 0);
- av_dict_set(&dict, "profile", "main", 0);
+ av_dict_set(&dict, "preset", "fast", 0); //x264
+ av_dict_set(&dict, "tune", "zerolatency", 0); //x264
+ //av_dict_set(&dict, "profile", "main", 0); // conflict with vaapi (int values)
 }
 if(avctx->codec_id == AV_CODEC_ID_HEVC){
 av_dict_set(&dict, "preset", "ultrafast", 0);
 av_dict_set(&dict, "tune", "zero-latency", 0);
 }
-#endif
+ if (avctx->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
+ av_dict_set(&dict, "strict", "-2", 0); // mpeg2 arbitrary fps
+ }
 applyOptionsForContext();
 AV_ENSURE_OK(avcodec_open2(avctx, codec, &dict), false);
 // from mpv ao_lavc
@@ -151,13 +267,36 @@
 return VideoEncoderId_FFmpeg;
 }
 
+void VideoEncoderFFmpeg::setHWDevice(const QString &name)
+{
+ DPTR_D(VideoEncoderFFmpeg);
+ if (d.hwdev == name)
+ return;
+ d.hwdev = name;
+ Q_EMIT hwDeviceChanged();
+}
+
+QString VideoEncoderFFmpeg::hwDevice() const
+{
+ return d_func().hwdev;
+}
+
+struct ScopedAVFrameDeleter
+{
+ static inline void cleanup(void *pointer) {
+ av_frame_free((AVFrame**)&pointer);
+ }
+};
+
 bool VideoEncoderFFmpeg::encode(const VideoFrame &frame)
 {
 DPTR_D(VideoEncoderFFmpeg);
- AVFrame *f = NULL;
+ QScopedPointer<AVFrame, ScopedAVFrameDeleter> f;
+ // hwupload
+ AVPixelFormat pixfmt = AVPixelFormat(frame.pixelFormatFFmpeg());
 if (frame.isValid()) {
- f = av_frame_alloc();
- f->format = frame.format().pixelFormatFFmpeg();
+ f.reset(av_frame_alloc());
+ f->format = pixfmt;
 f->width = frame.width();
 f->height = frame.height();
 // f->quality = d.avctx->global_quality;
@@ -171,6 +310,7 @@
 default:
 break;
 }
+
 // pts is set in muxer
 const int nb_planes = frame.planeCount();
 for (int i = 0; i < nb_planes; ++i) {
@@ -183,14 +323,55 @@
 if (d.avctx->height <= 0) {
 d.avctx->height = frame.width();
 }
+#ifdef HAVE_AVHWCTX
+ if (d.avctx->hw_frames_ctx) {
+ // TODO: try to map to SourceSurface
+ // checl valid sw_formats
+ if (!d.hwframes_ref) {
+ qWarning("no hw frame context for uploading");
+ return false;
+ }
+ if (pixfmt != d.hwframes->sw_format) {
+ // reinit or got an unsupported format. assume parameters will not change, so it's the 1st init
+ // check constraints
+ bool init_frames_ctx = d.hwframes->sw_format == AVPixelFormat(-1);
+ if (d.sw_fmts.contains(pixfmt)) { // format changed
+ init_frames_ctx = true;
+ } else { // convert to supported sw format
+ pixfmt = d.sw_fmts[0];
+ f->format = pixfmt;
+ VideoFrame converted = frame.to(VideoFormat::pixelFormatFromFFmpeg(pixfmt));
+ for (int i = 0; i < converted.planeCount(); ++i) {
+ f->linesize[i] = converted.bytesPerLine(i);
+ f->data[i] = (uint8_t*)frame.constBits(i);
+ }
+ }
+ if (init_frames_ctx) {
+ d.hwframes->sw_format = pixfmt;
+ d.hwframes->width = frame.width();
+ d.hwframes->height = frame.height();
+ AV_ENSURE(av_hwframe_ctx_init(d.hwframes_ref), false);
+ }
+ }
+ // upload
+ QScopedPointer<AVFrame, ScopedAVFrameDeleter> hwf( av_frame_alloc());
+ AV_ENSURE(av_hwframe_get_buffer(d.hwframes_ref, hwf.data(), 0), false);
+ //hwf->format = d.hwframes->format; // not necessary
+ //hwf->width = f->width;
+ //hwf->height = f->height;
+ AV_ENSURE(av_hwframe_transfer_data(hwf.data(), f.data(), 0), false);
+ AV_ENSURE(av_frame_copy_props(hwf.data(), f.data()), false);
+ av_frame_unref(f.data());
+ av_frame_move_ref(f.data(), hwf.data());
+ }
+#endif //HAVE_AVHWCTX
 }
 AVPacket pkt;
 av_init_packet(&pkt);
 pkt.data = (uint8_t*)d.buffer.constData();
 pkt.size = d.buffer.size();
 int got_packet = 0;
- int ret = avcodec_encode_video2(d.avctx, &pkt, f, &got_packet);
- av_frame_free(&f);
+ int ret = avcodec_encode_video2(d.avctx, &pkt, f.data(), &got_packet);
 if (ret < 0) {
 qWarning("error avcodec_encode_video2: %s" ,av_err2str(ret));
 return false; //false
@@ -209,3 +390,4 @@
 }
 
 } //namespace QtAV
+#include "VideoEncoderFFmpeg.moc"

QtAV-1.11.0.tar.gz/src/cuda/cuda_api.cpp -> QtAV-1.12.0.tar.gz/src/cuda/cuda_api.cpp Changed

QtAV-1.11.0.tar.gz/src/cuda/dllapi/nv_inc.h -> QtAV-1.12.0.tar.gz/src/cuda/dllapi/nv_inc.h Changed

QtAV-1.12.0.tar.gz/src/cuda/dynlink_cuda.h Added

@@ -0,0 +1,502 @@
+/*
+ * This copyright notice applies to this header file only:
+ *
+ * Copyright (c) 2016
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the software, and to permit persons to whom the
+ * software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef __cuda_cuda_h__
+#define __cuda_cuda_h__
+
+#include <stddef.h>
+
+#define CUDA_VERSION 7050
+
+#if defined(_WIN32) || defined(__CYGWIN__)
+#define CUDAAPI __stdcall
+#else
+#define CUDAAPI
+#endif
+
+typedef int CUdevice;
+typedef struct CUarray_st *CUarray; /**< CUDA array */
+typedef struct CUctx_st *CUcontext; /**< CUDA context */
+#if defined(__x86_64) || defined(AMD64) || defined(_M_AMD64)
+typedef unsigned long long CUdeviceptr;
+#else
+typedef unsigned int CUdeviceptr;
+#endif
+typedef struct CUstream_st *CUstream; /**< CUDA stream */
+typedef struct CUgraphicsResource_st *CUgraphicsResource; /**< CUDA graphics interop resource */
+
+/**
+ * Context creation flags
+ */
+typedef enum CUctx_flags_enum
+{
+ CU_CTX_SCHED_AUTO = 0x00, /**< Automatic scheduling */
+ CU_CTX_SCHED_SPIN = 0x01, /**< Set spin as default scheduling */
+ CU_CTX_SCHED_YIELD = 0x02, /**< Set yield as default scheduling */
+ CU_CTX_SCHED_BLOCKING_SYNC = 0x04, /**< Set blocking synchronization as default scheduling */
+ CU_CTX_BLOCKING_SYNC = 0x04, /**< Set blocking synchronization as default scheduling \deprecated */
+ CU_CTX_MAP_HOST = 0x08, /**< Support mapped pinned allocations */
+ CU_CTX_LMEM_RESIZE_TO_MAX = 0x10, /**< Keep local memory allocation after launch */
+#if __CUDA_API_VERSION < 4000
+ CU_CTX_SCHED_MASK = 0x03,
+ CU_CTX_FLAGS_MASK = 0x1f
+#else
+ CU_CTX_SCHED_MASK = 0x07,
+ CU_CTX_PRIMARY = 0x20, /**< Initialize and return the primary context */
+ CU_CTX_FLAGS_MASK = 0x3f
+#endif
+} CUctx_flags;
+
+/**
+ * Stream creation flags
+ */
+typedef enum CUstream_flags_enum {
+ CU_STREAM_DEFAULT = 0x0, /**< Default stream flag */
+ CU_STREAM_NON_BLOCKING = 0x1 /**< Stream does not synchronize with stream 0 (the NULL stream) */
+} CUstream_flags;
+
+/**
+ * Device properties
+ */
+typedef enum CUdevice_attribute_enum
+{
+ CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK = 1, /**< Maximum number of threads per block */
+ CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_X = 2, /**< Maximum block dimension X */
+ CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Y = 3, /**< Maximum block dimension Y */
+ CU_DEVICE_ATTRIBUTE_MAX_BLOCK_DIM_Z = 4, /**< Maximum block dimension Z */
+ CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X = 5, /**< Maximum grid dimension X */
+ CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Y = 6, /**< Maximum grid dimension Y */
+ CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_Z = 7, /**< Maximum grid dimension Z */
+ CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK = 8, /**< Maximum shared memory available per block in bytes */
+ CU_DEVICE_ATTRIBUTE_SHARED_MEMORY_PER_BLOCK = 8, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAX_SHARED_MEMORY_PER_BLOCK */
+ CU_DEVICE_ATTRIBUTE_TOTAL_CONSTANT_MEMORY = 9, /**< Memory available on device for __constant__ variables in a CUDA C kernel in bytes */
+ CU_DEVICE_ATTRIBUTE_WARP_SIZE = 10, /**< Warp size in threads */
+ CU_DEVICE_ATTRIBUTE_MAX_PITCH = 11, /**< Maximum pitch in bytes allowed by memory copies */
+ CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK = 12, /**< Maximum number of 32-bit registers available per block */
+ CU_DEVICE_ATTRIBUTE_REGISTERS_PER_BLOCK = 12, /**< Deprecated, use CU_DEVICE_ATTRIBUTE_MAX_REGISTERS_PER_BLOCK */
+ CU_DEVICE_ATTRIBUTE_CLOCK_RATE = 13, /**< Peak clock frequency in kilohertz */
+ CU_DEVICE_ATTRIBUTE_TEXTURE_ALIGNMENT = 14, /**< Alignment requirement for textures */
+ CU_DEVICE_ATTRIBUTE_GPU_OVERLAP = 15, /**< Device can possibly copy memory and execute a kernel concurrently */
+ CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT = 16, /**< Number of multiprocessors on device */
+ CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT = 17, /**< Specifies whether there is a run time limit on kernels */
+ CU_DEVICE_ATTRIBUTE_INTEGRATED = 18, /**< Device is integrated with host memory */
+ CU_DEVICE_ATTRIBUTE_CAN_MAP_HOST_MEMORY = 19, /**< Device can map host memory into CUDA address space */
+ CU_DEVICE_ATTRIBUTE_COMPUTE_MODE = 20, /**< Compute mode (See ::CUcomputemode for details) */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_WIDTH = 21, /**< Maximum 1D texture width */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_WIDTH = 22, /**< Maximum 2D texture width */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_HEIGHT = 23, /**< Maximum 2D texture height */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_WIDTH = 24, /**< Maximum 3D texture width */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_HEIGHT = 25, /**< Maximum 3D texture height */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE3D_DEPTH = 26, /**< Maximum 3D texture depth */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_WIDTH = 27, /**< Maximum texture array width */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_HEIGHT = 28, /**< Maximum texture array height */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE2D_ARRAY_NUMSLICES = 29, /**< Maximum slices in a texture array */
+ CU_DEVICE_ATTRIBUTE_SURFACE_ALIGNMENT = 30, /**< Alignment requirement for surfaces */
+ CU_DEVICE_ATTRIBUTE_CONCURRENT_KERNELS = 31, /**< Device can possibly execute multiple kernels concurrently */
+ CU_DEVICE_ATTRIBUTE_ECC_ENABLED = 32, /**< Device has ECC support enabled */
+ CU_DEVICE_ATTRIBUTE_PCI_BUS_ID = 33, /**< PCI bus ID of the device */
+ CU_DEVICE_ATTRIBUTE_PCI_DEVICE_ID = 34, /**< PCI device ID of the device */
+ CU_DEVICE_ATTRIBUTE_TCC_DRIVER = 35 /**< Device is using TCC driver model */
+#if __CUDA_API_VERSION >= 4000
+ , CU_DEVICE_ATTRIBUTE_MEMORY_CLOCK_RATE = 36, /**< Peak memory clock frequency in kilohertz */
+ CU_DEVICE_ATTRIBUTE_GLOBAL_MEMORY_BUS_WIDTH = 37, /**< Global memory bus width in bits */
+ CU_DEVICE_ATTRIBUTE_L2_CACHE_SIZE = 38, /**< Size of L2 cache in bytes */
+ CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR = 39, /**< Maximum resident threads per multiprocessor */
+ CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT = 40, /**< Number of asynchronous engines */
+ CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING = 41, /**< Device uses shares a unified address space with the host */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_WIDTH = 42, /**< Maximum 1D layered texture width */
+ CU_DEVICE_ATTRIBUTE_MAXIMUM_TEXTURE1D_LAYERED_LAYERS = 43 /**< Maximum layers in a 1D layered texture */
+#endif
+} CUdevice_attribute;
+
+
+/**
+ * Error codes
+ */
+typedef enum cudaError_enum
+{
+ /**
+ * The API call returned with no errors. In the case of query calls, this
+ * can also mean that the operation being queried is complete (see
+ * ::cuEventQuery() and ::cuStreamQuery()).
+ */
+ CUDA_SUCCESS = 0,
+
+ /**
+ * This indicates that one or more of the parameters passed to the API call
+ * is not within an acceptable range of values.
+ */
+ CUDA_ERROR_INVALID_VALUE = 1,
+
+ /**
+ * The API call failed because it was unable to allocate enough memory to
+ * perform the requested operation.
+ */
+ CUDA_ERROR_OUT_OF_MEMORY = 2,
+
+ /**
+ * This indicates that the CUDA driver has not been initialized with
+ * ::cuInit() or that initialization has failed.
+ */
+ CUDA_ERROR_NOT_INITIALIZED = 3,
+
+ /**
+ * This indicates that the CUDA driver is in the process of shutting down.
+ */
+ CUDA_ERROR_DEINITIALIZED = 4,
+
+ /**
+ * This indicates profiling APIs are called while application is running
+ * in visual profiler mode.
+ */
+ CUDA_ERROR_PROFILER_DISABLED = 5,
+ /**
+ * This indicates profiling has not been initialized for this context.
+ * Call cuProfilerInitialize() to resolve this.
+ */
+ CUDA_ERROR_PROFILER_NOT_INITIALIZED = 6,
+ /**
+ * This indicates profiler has already been started and probably
+ * cuProfilerStart() is incorrectly called.
+ */
+ CUDA_ERROR_PROFILER_ALREADY_STARTED = 7,
+ /**
+ * This indicates profiler has already been stopped and probably
+ * cuProfilerStop() is incorrectly called.
+ */
+ CUDA_ERROR_PROFILER_ALREADY_STOPPED = 8,
+ /**
+ * This indicates that no CUDA-capable devices were detected by the installed
+ * CUDA driver.
+ */
+ CUDA_ERROR_NO_DEVICE = 100,
+
+ /**
+ * This indicates that the device ordinal supplied by the user does not
+ * correspond to a valid CUDA device.
+ */
+ CUDA_ERROR_INVALID_DEVICE = 101,
+
+
+ /**
+ * This indicates that the device kernel image is invalid. This can also
+ * indicate an invalid CUDA module.
+ */
+ CUDA_ERROR_INVALID_IMAGE = 200,
+
+ /**
+ * This most frequently indicates that there is no context bound to the
+ * current thread. This can also be returned if the context passed to an
+ * API call is not a valid handle (such as a context that has had
+ * ::cuCtxDestroy() invoked on it). This can also be returned if a user
+ * mixes different API versions (i.e. 3010 context with 3020 API calls).
+ * See ::cuCtxGetApiVersion() for more details.
+ */
+ CUDA_ERROR_INVALID_CONTEXT = 201,
+
+ /**
+ * This indicated that the context being supplied as a parameter to the
+ * API call was already the active context.
+ * \deprecated
+ * This error return is deprecated as of CUDA 3.2. It is no longer an
+ * error to attempt to push the active context via ::cuCtxPushCurrent().
+ */
+ CUDA_ERROR_CONTEXT_ALREADY_CURRENT = 202,
+
+ /**
+ * This indicates that a map or register operation has failed.
+ */
+ CUDA_ERROR_MAP_FAILED = 205,
+
+ /**
+ * This indicates that an unmap or unregister operation has failed.
+ */
+ CUDA_ERROR_UNMAP_FAILED = 206,
+
+ /**
+ * This indicates that the specified array is currently mapped and thus
+ * cannot be destroyed.
+ */
+ CUDA_ERROR_ARRAY_IS_MAPPED = 207,
+
+ /**
+ * This indicates that the resource is already mapped.
+ */
+ CUDA_ERROR_ALREADY_MAPPED = 208,
+
+ /**
+ * This indicates that there is no kernel image available that is suitable
+ * for the device. This can occur when a user specifies code generation
+ * options for a particular CUDA source file that do not include the
+ * corresponding device configuration.
+ */
+ CUDA_ERROR_NO_BINARY_FOR_GPU = 209,
+
+ /**
+ * This indicates that a resource has already been acquired.
+ */
+ CUDA_ERROR_ALREADY_ACQUIRED = 210,
+
+ /**
+ * This indicates that a resource is not mapped.
+ */
+ CUDA_ERROR_NOT_MAPPED = 211,
+
+ /**
+ * This indicates that a mapped resource is not available for access as an
+ * array.
+ */
+ CUDA_ERROR_NOT_MAPPED_AS_ARRAY = 212,
+
+ /**
+ * This indicates that a mapped resource is not available for access as a
+ * pointer.
+ */
+ CUDA_ERROR_NOT_MAPPED_AS_POINTER = 213,
+
+ /**
+ * This indicates that an uncorrectable ECC error was detected during
+ * execution.
+ */
+ CUDA_ERROR_ECC_UNCORRECTABLE = 214,
+
+ /**
+ * This indicates that the ::CUlimit passed to the API call is not
+ * supported by the active device.
+ */
+ CUDA_ERROR_UNSUPPORTED_LIMIT = 215,
+
+ /**
+ * This indicates that the ::CUcontext passed to the API call can
+ * only be bound to a single CPU thread at a time but is already
+ * bound to a CPU thread.
+ */
+ CUDA_ERROR_CONTEXT_ALREADY_IN_USE = 216,
+
+ /**
+ * This indicates that the device kernel source is invalid.
+ */
+ CUDA_ERROR_INVALID_SOURCE = 300,
+
+ /**
+ * This indicates that the file specified was not found.
+ */
+ CUDA_ERROR_FILE_NOT_FOUND = 301,
+
+ /**
+ * This indicates that a link to a shared object failed to resolve.
+ */
+ CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND = 302,
+
+ /**
+ * This indicates that initialization of a shared object failed.
+ */
+ CUDA_ERROR_SHARED_OBJECT_INIT_FAILED = 303,
+
+ /**
+ * This indicates that an OS call failed.
+ */
+ CUDA_ERROR_OPERATING_SYSTEM = 304,
+
+
+ /**
+ * This indicates that a resource handle passed to the API call was not
+ * valid. Resource handles are opaque types like ::CUstream and ::CUevent.
+ */
+ CUDA_ERROR_INVALID_HANDLE = 400,
+
+
+ /**
+ * This indicates that a named symbol was not found. Examples of symbols
+ * are global/constant variable names, texture names, and surface names.
+ */
+ CUDA_ERROR_NOT_FOUND = 500,
+
+
+ /**
+ * This indicates that asynchronous operations issued previously have not
+ * completed yet. This result is not actually an error, but must be indicated
+ * differently than ::CUDA_SUCCESS (which indicates completion). Calls that
+ * may return this value include ::cuEventQuery() and ::cuStreamQuery().
+ */
+ CUDA_ERROR_NOT_READY = 600,
+
+
+ /**
+ * An exception occurred on the device while executing a kernel. Common
+ * causes include dereferencing an invalid device pointer and accessing
+ * out of bounds shared memory. The context cannot be used, so it must
+ * be destroyed (and a new one should be created). All existing device
+ * memory allocations from this context are invalid and must be
+ * reconstructed if the program is to continue using CUDA.
+ */
+ CUDA_ERROR_LAUNCH_FAILED = 700,
+
+ /**
+ * This indicates that a launch did not occur because it did not have
+ * appropriate resources. This error usually indicates that the user has
+ * attempted to pass too many arguments to the device kernel, or the
+ * kernel launch specifies too many threads for the kernel's register
+ * count. Passing arguments of the wrong size (i.e. a 64-bit pointer
+ * when a 32-bit int is expected) is equivalent to passing too many
+ * arguments and can also result in this error.
+ */
+ CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES = 701,
+
+ /**
+ * This indicates that the device kernel took too long to execute. This can
+ * only occur if timeouts are enabled - see the device attribute
+ * ::CU_DEVICE_ATTRIBUTE_KERNEL_EXEC_TIMEOUT for more information. The
+ * context cannot be used (and must be destroyed similar to
+ * ::CUDA_ERROR_LAUNCH_FAILED). All existing device memory allocations from
+ * this context are invalid and must be reconstructed if the program is to
+ * continue using CUDA.
+ */
+ CUDA_ERROR_LAUNCH_TIMEOUT = 702,
+
+ /**
+ * This error indicates a kernel launch that uses an incompatible texturing
+ * mode.
+ */
+ CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING = 703,
+
+ /**
+ * This error indicates that a call to ::cuCtxEnablePeerAccess() is
+ * trying to re-enable peer access to a context which has already
+ * had peer access to it enabled.
+ */
+ CUDA_ERROR_PEER_ACCESS_ALREADY_ENABLED = 704,
+
+ /**
+ * This error indicates that a call to ::cuMemPeerRegister is trying to
+ * register memory from a context which has not had peer access
+ * enabled yet via ::cuCtxEnablePeerAccess(), or that
+ * ::cuCtxDisablePeerAccess() is trying to disable peer access
+ * which has not been enabled yet.
+ */
+ CUDA_ERROR_PEER_ACCESS_NOT_ENABLED = 705,
+
+ /**
+ * This error indicates that a call to ::cuMemPeerRegister is trying to
+ * register already-registered memory.
+ */
+ CUDA_ERROR_PEER_MEMORY_ALREADY_REGISTERED = 706,
+
+ /**
+ * This error indicates that a call to ::cuMemPeerUnregister is trying to
+ * unregister memory that has not been registered.
+ */
+ CUDA_ERROR_PEER_MEMORY_NOT_REGISTERED = 707,
+
+ /**
+ * This error indicates that ::cuCtxCreate was called with the flag
+ * ::CU_CTX_PRIMARY on a device which already has initialized its
+ * primary context.
+ */
+ CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE = 708,
+
+ /**
+ * This error indicates that the context current to the calling thread
+ * has been destroyed using ::cuCtxDestroy, or is a primary context which
+ * has not yet been initialized.
+ */
+ CUDA_ERROR_CONTEXT_IS_DESTROYED = 709,
+
+ /**
+ * This indicates that an unknown internal error has occurred.
+ */
+ CUDA_ERROR_UNKNOWN = 999
+} CUresult;
+
+/**
+ * Memory types
+ */
+typedef enum CUmemorytype_enum
+{
+ CU_MEMORYTYPE_HOST = 0x01, /**< Host memory */
+ CU_MEMORYTYPE_DEVICE = 0x02, /**< Device memory */
+ CU_MEMORYTYPE_ARRAY = 0x03 /**< Array memory */
+#if __CUDA_API_VERSION >= 4000
+ , CU_MEMORYTYPE_UNIFIED = 0x04 /**< Unified device or host memory */
+#endif
+} CUmemorytype;
+
+/**
+ * Compute Modes
+ */
+typedef enum CUcomputemode_enum
+{
+ CU_COMPUTEMODE_DEFAULT = 0, /**< Default compute mode (Multiple contexts allowed per device) */
+ CU_COMPUTEMODE_EXCLUSIVE = 1, /**< Compute-exclusive-thread mode (Only one context used by a single thread can be present on this device at a time) */
+ CU_COMPUTEMODE_PROHIBITED = 2 /**< Compute-prohibited mode (No contexts can be created on this device at this time) */
+#if __CUDA_API_VERSION >= 4000
+ , CU_COMPUTEMODE_EXCLUSIVE_PROCESS = 3 /**< Compute-exclusive-process mode (Only one context used by a single process can be present on this device at a time) */
+#endif
+} CUcomputemode;
+
+/**
+ * Flags to register a graphics resource
+ */
+typedef enum CUgraphicsRegisterFlags_enum
+{
+ CU_GRAPHICS_REGISTER_FLAGS_NONE = 0x00,
+ CU_GRAPHICS_REGISTER_FLAGS_READ_ONLY = 0x01,
+ CU_GRAPHICS_REGISTER_FLAGS_WRITE_DISCARD = 0x02,
+ CU_GRAPHICS_REGISTER_FLAGS_SURFACE_LDST = 0x04
+} CUgraphicsRegisterFlags;
+
+/**
+ * Flags for mapping and unmapping interop resources
+ */
+typedef enum CUgraphicsMapResourceFlags_enum
+{
+ CU_GRAPHICS_MAP_RESOURCE_FLAGS_NONE = 0x00,
+ CU_GRAPHICS_MAP_RESOURCE_FLAGS_READ_ONLY = 0x01,
+ CU_GRAPHICS_MAP_RESOURCE_FLAGS_WRITE_DISCARD = 0x02
+} CUgraphicsMapResourceFlags;
+
+typedef struct CUDA_MEMCPY2D_st {
+ size_t srcXInBytes;
+ size_t srcY;
+ CUmemorytype srcMemoryType;
+ const void *srcHost;
+ CUdeviceptr srcDevice;
+ CUarray srcArray;
+ size_t srcPitch;
+
+ size_t dstXInBytes;
+ size_t dstY;
+ CUmemorytype dstMemoryType;
+ void *dstHost;
+ CUdeviceptr dstDevice;
+ CUarray dstArray;
+ size_t dstPitch;
+
+ size_t WidthInBytes;
+ size_t Height;
+} CUDA_MEMCPY2D;
+#endif

QtAV-1.12.0.tar.gz/src/cuda/dynlink_cuviddec.h Added

@@ -0,0 +1,732 @@
+/*
+ * This copyright notice applies to this header file only:
+ *
+ * Copyright (c) 2010-2016 NVIDIA Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the software, and to permit persons to whom the
+ * software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * \file cuviddec.h
+ * NvCuvid API provides Video Decoding interface to NVIDIA GPU devices.
+ * \date 2015-2016
+ * This file contains constants, structure definitions and function prototypes used for decoding.
+ */
+
+#if !defined(__CUDA_VIDEO_H__)
+#define __CUDA_VIDEO_H__
+
+#if defined(__x86_64) || defined(AMD64) || defined(_M_AMD64)
+#if (CUDA_VERSION >= 3020) && (!defined(CUDA_FORCE_API_VERSION) || (CUDA_FORCE_API_VERSION >= 3020))
+#define __CUVID_DEVPTR64
+#endif
+#endif
+
+#if defined(__cplusplus)
+extern "C" {
+#endif /* __cplusplus */
+
+typedef void *CUvideodecoder;
+typedef struct _CUcontextlock_st *CUvideoctxlock;
+
+/**
+ * \addtogroup VIDEO_DECODER Video Decoder
+ * @{
+ */
+
+/*!
+ * \enum cudaVideoCodec
+ * Video Codec Enums
+ */
+typedef enum cudaVideoCodec_enum {
+ cudaVideoCodec_MPEG1=0, /**< MPEG1 */
+ cudaVideoCodec_MPEG2, /**< MPEG2 */
+ cudaVideoCodec_MPEG4, /**< MPEG4 */
+ cudaVideoCodec_VC1, /**< VC1 */
+ cudaVideoCodec_H264, /**< H264 */
+ cudaVideoCodec_JPEG, /**< JPEG */
+ cudaVideoCodec_H264_SVC, /**< H264-SVC */
+ cudaVideoCodec_H264_MVC, /**< H264-MVC */
+ cudaVideoCodec_HEVC, /**< HEVC */
+ cudaVideoCodec_VP8, /**< VP8 */
+ cudaVideoCodec_VP9, /**< VP9 */
+ cudaVideoCodec_NumCodecs, /**< Max COdecs */
+ // Uncompressed YUV
+ cudaVideoCodec_YUV420 = (('I'<<24)|('Y'<<16)|('U'<<8)|('V')), /**< Y,U,V (4:2:0) */
+ cudaVideoCodec_YV12 = (('Y'<<24)|('V'<<16)|('1'<<8)|('2')), /**< Y,V,U (4:2:0) */
+ cudaVideoCodec_NV12 = (('N'<<24)|('V'<<16)|('1'<<8)|('2')), /**< Y,UV (4:2:0) */
+ cudaVideoCodec_YUYV = (('Y'<<24)|('U'<<16)|('Y'<<8)|('V')), /**< YUYV/YUY2 (4:2:2) */
+ cudaVideoCodec_UYVY = (('U'<<24)|('Y'<<16)|('V'<<8)|('Y')) /**< UYVY (4:2:2) */
+} cudaVideoCodec;
+
+/*!
+ * \enum cudaVideoSurfaceFormat
+ * Video Surface Formats Enums
+ */
+typedef enum cudaVideoSurfaceFormat_enum {
+ cudaVideoSurfaceFormat_NV12=0, /**< NV12 */
+ cudaVideoSurfaceFormat_P016=1 /**< P016 */
+} cudaVideoSurfaceFormat;
+
+/*!
+ * \enum cudaVideoDeinterlaceMode
+ * Deinterlacing Modes Enums
+ */
+typedef enum cudaVideoDeinterlaceMode_enum {
+ cudaVideoDeinterlaceMode_Weave=0, /**< Weave both fields (no deinterlacing) */
+ cudaVideoDeinterlaceMode_Bob, /**< Drop one field */
+ cudaVideoDeinterlaceMode_Adaptive /**< Adaptive deinterlacing */
+} cudaVideoDeinterlaceMode;
+
+/*!
+ * \enum cudaVideoChromaFormat
+ * Chroma Formats Enums
+ */
+typedef enum cudaVideoChromaFormat_enum {
+ cudaVideoChromaFormat_Monochrome=0, /**< MonoChrome */
+ cudaVideoChromaFormat_420, /**< 4:2:0 */
+ cudaVideoChromaFormat_422, /**< 4:2:2 */
+ cudaVideoChromaFormat_444 /**< 4:4:4 */
+} cudaVideoChromaFormat;
+
+/*!
+ * \enum cudaVideoCreateFlags
+ * Decoder Flags Enums
+ */
+typedef enum cudaVideoCreateFlags_enum {
+ cudaVideoCreate_Default = 0x00, /**< Default operation mode: use dedicated video engines */
+ cudaVideoCreate_PreferCUDA = 0x01, /**< Use a CUDA-based decoder if faster than dedicated engines (requires a valid vidLock object for multi-threading) */
+ cudaVideoCreate_PreferDXVA = 0x02, /**< Go through DXVA internally if possible (requires D3D9 interop) */
+ cudaVideoCreate_PreferCUVID = 0x04 /**< Use dedicated video engines directly */
+} cudaVideoCreateFlags;
+
+/*!
+ * \struct CUVIDDECODECREATEINFO
+ * Struct used in create decoder
+ */
+typedef struct _CUVIDDECODECREATEINFO
+{
+ unsigned long ulWidth; /**< Coded Sequence Width */
+ unsigned long ulHeight; /**< Coded Sequence Height */
+ unsigned long ulNumDecodeSurfaces; /**< Maximum number of internal decode surfaces */
+ cudaVideoCodec CodecType; /**< cudaVideoCodec_XXX */
+ cudaVideoChromaFormat ChromaFormat; /**< cudaVideoChromaFormat_XXX (only 4:2:0 is currently supported) */
+ unsigned long ulCreationFlags; /**< Decoder creation flags (cudaVideoCreateFlags_XXX) */
+ unsigned long bitDepthMinus8;
+ unsigned long Reserved1[4]; /**< Reserved for future use - set to zero */
+ /**
+ * area of the frame that should be displayed
+ */
+ struct {
+ short left;
+ short top;
+ short right;
+ short bottom;
+ } display_area;
+
+ cudaVideoSurfaceFormat OutputFormat; /**< cudaVideoSurfaceFormat_XXX */
+ cudaVideoDeinterlaceMode DeinterlaceMode; /**< cudaVideoDeinterlaceMode_XXX */
+ unsigned long ulTargetWidth; /**< Post-processed Output Width (Should be aligned to 2) */
+ unsigned long ulTargetHeight; /**< Post-processed Output Height (Should be aligbed to 2) */
+ unsigned long ulNumOutputSurfaces; /**< Maximum number of output surfaces simultaneously mapped */
+ CUvideoctxlock vidLock; /**< If non-NULL, context lock used for synchronizing ownership of the cuda context */
+ /**
+ * target rectangle in the output frame (for aspect ratio conversion)
+ * if a null rectangle is specified, {0,0,ulTargetWidth,ulTargetHeight} will be used
+ */
+ struct {
+ short left;
+ short top;
+ short right;
+ short bottom;
+ } target_rect;
+ unsigned long Reserved2[5]; /**< Reserved for future use - set to zero */
+} CUVIDDECODECREATEINFO;
+
+/*!
+ * \struct CUVIDH264DPBENTRY
+ * H.264 DPB Entry
+ */
+typedef struct _CUVIDH264DPBENTRY
+{
+ int PicIdx; /**< picture index of reference frame */
+ int FrameIdx; /**< frame_num(short-term) or LongTermFrameIdx(long-term) */
+ int is_long_term; /**< 0=short term reference, 1=long term reference */
+ int not_existing; /**< non-existing reference frame (corresponding PicIdx should be set to -1) */
+ int used_for_reference; /**< 0=unused, 1=top_field, 2=bottom_field, 3=both_fields */
+ int FieldOrderCnt[2]; /**< field order count of top and bottom fields */
+} CUVIDH264DPBENTRY;
+
+/*!
+ * \struct CUVIDH264MVCEXT
+ * H.264 MVC Picture Parameters Ext
+ */
+typedef struct _CUVIDH264MVCEXT
+{
+ int num_views_minus1;
+ int view_id;
+ unsigned char inter_view_flag;
+ unsigned char num_inter_view_refs_l0;
+ unsigned char num_inter_view_refs_l1;
+ unsigned char MVCReserved8Bits;
+ int InterViewRefsL0[16];
+ int InterViewRefsL1[16];
+} CUVIDH264MVCEXT;
+
+/*!
+ * \struct CUVIDH264SVCEXT
+ * H.264 SVC Picture Parameters Ext
+ */
+typedef struct _CUVIDH264SVCEXT
+{
+ unsigned char profile_idc;
+ unsigned char level_idc;
+ unsigned char DQId;
+ unsigned char DQIdMax;
+ unsigned char disable_inter_layer_deblocking_filter_idc;
+ unsigned char ref_layer_chroma_phase_y_plus1;
+ signed char inter_layer_slice_alpha_c0_offset_div2;
+ signed char inter_layer_slice_beta_offset_div2;
+
+ unsigned short DPBEntryValidFlag;
+ unsigned char inter_layer_deblocking_filter_control_present_flag;
+ unsigned char extended_spatial_scalability_idc;
+ unsigned char adaptive_tcoeff_level_prediction_flag;
+ unsigned char slice_header_restriction_flag;
+ unsigned char chroma_phase_x_plus1_flag;
+ unsigned char chroma_phase_y_plus1;
+
+ unsigned char tcoeff_level_prediction_flag;
+ unsigned char constrained_intra_resampling_flag;
+ unsigned char ref_layer_chroma_phase_x_plus1_flag;
+ unsigned char store_ref_base_pic_flag;
+ unsigned char Reserved8BitsA;
+ unsigned char Reserved8BitsB;
+ // For the 4 scaled_ref_layer_XX fields below,
+ // if (extended_spatial_scalability_idc == 1), SPS field, G.7.3.2.1.4, add prefix "seq_"
+ // if (extended_spatial_scalability_idc == 2), SLH field, G.7.3.3.4,
+ short scaled_ref_layer_left_offset;
+ short scaled_ref_layer_top_offset;
+ short scaled_ref_layer_right_offset;
+ short scaled_ref_layer_bottom_offset;
+ unsigned short Reserved16Bits;
+ struct _CUVIDPICPARAMS *pNextLayer; /**< Points to the picparams for the next layer to be decoded. Linked list ends at the target layer. */
+ int bRefBaseLayer; /**< whether to store ref base pic */
+} CUVIDH264SVCEXT;
+
+/*!
+ * \struct CUVIDH264PICPARAMS
+ * H.264 Picture Parameters
+ */
+typedef struct _CUVIDH264PICPARAMS
+{
+ // SPS
+ int log2_max_frame_num_minus4;
+ int pic_order_cnt_type;
+ int log2_max_pic_order_cnt_lsb_minus4;
+ int delta_pic_order_always_zero_flag;
+ int frame_mbs_only_flag;
+ int direct_8x8_inference_flag;
+ int num_ref_frames; // NOTE: shall meet level 4.1 restrictions
+ unsigned char residual_colour_transform_flag;
+ unsigned char bit_depth_luma_minus8; // Must be 0 (only 8-bit supported)
+ unsigned char bit_depth_chroma_minus8; // Must be 0 (only 8-bit supported)
+ unsigned char qpprime_y_zero_transform_bypass_flag;
+ // PPS
+ int entropy_coding_mode_flag;
+ int pic_order_present_flag;
+ int num_ref_idx_l0_active_minus1;
+ int num_ref_idx_l1_active_minus1;
+ int weighted_pred_flag;
+ int weighted_bipred_idc;
+ int pic_init_qp_minus26;
+ int deblocking_filter_control_present_flag;
+ int redundant_pic_cnt_present_flag;
+ int transform_8x8_mode_flag;
+ int MbaffFrameFlag;
+ int constrained_intra_pred_flag;
+ int chroma_qp_index_offset;
+ int second_chroma_qp_index_offset;
+ int ref_pic_flag;
+ int frame_num;
+ int CurrFieldOrderCnt[2];
+ // DPB
+ CUVIDH264DPBENTRY dpb[16]; // List of reference frames within the DPB
+ // Quantization Matrices (raster-order)
+ unsigned char WeightScale4x4[6][16];
+ unsigned char WeightScale8x8[2][64];
+ // FMO/ASO
+ unsigned char fmo_aso_enable;
+ unsigned char num_slice_groups_minus1;
+ unsigned char slice_group_map_type;
+ signed char pic_init_qs_minus26;
+ unsigned int slice_group_change_rate_minus1;
+ union
+ {
+ unsigned long long slice_group_map_addr;
+ const unsigned char *pMb2SliceGroupMap;
+ } fmo;
+ unsigned int Reserved[12];
+ // SVC/MVC
+ union
+ {
+ CUVIDH264MVCEXT mvcext;
+ CUVIDH264SVCEXT svcext;
+ } svcmvc;
+} CUVIDH264PICPARAMS;
+
+
+/*!
+ * \struct CUVIDMPEG2PICPARAMS
+ * MPEG-2 Picture Parameters
+ */
+typedef struct _CUVIDMPEG2PICPARAMS
+{
+ int ForwardRefIdx; // Picture index of forward reference (P/B-frames)
+ int BackwardRefIdx; // Picture index of backward reference (B-frames)
+ int picture_coding_type;
+ int full_pel_forward_vector;
+ int full_pel_backward_vector;
+ int f_code[2][2];
+ int intra_dc_precision;
+ int frame_pred_frame_dct;
+ int concealment_motion_vectors;
+ int q_scale_type;
+ int intra_vlc_format;
+ int alternate_scan;
+ int top_field_first;
+ // Quantization matrices (raster order)
+ unsigned char QuantMatrixIntra[64];
+ unsigned char QuantMatrixInter[64];
+} CUVIDMPEG2PICPARAMS;
+
+////////////////////////////////////////////////////////////////////////////////////////////////
+//
+// MPEG-4 Picture Parameters
+//
+
+// MPEG-4 has VOP types instead of Picture types
+#define I_VOP 0
+#define P_VOP 1
+#define B_VOP 2
+#define S_VOP 3
+
+/*!
+ * \struct CUVIDMPEG4PICPARAMS
+ * MPEG-4 Picture Parameters
+ */
+typedef struct _CUVIDMPEG4PICPARAMS
+{
+ int ForwardRefIdx; // Picture index of forward reference (P/B-frames)
+ int BackwardRefIdx; // Picture index of backward reference (B-frames)
+ // VOL
+ int video_object_layer_width;
+ int video_object_layer_height;
+ int vop_time_increment_bitcount;
+ int top_field_first;
+ int resync_marker_disable;
+ int quant_type;
+ int quarter_sample;
+ int short_video_header;
+ int divx_flags;
+ // VOP
+ int vop_coding_type;
+ int vop_coded;
+ int vop_rounding_type;
+ int alternate_vertical_scan_flag;
+ int interlaced;
+ int vop_fcode_forward;
+ int vop_fcode_backward;
+ int trd[2];
+ int trb[2];
+ // Quantization matrices (raster order)
+ unsigned char QuantMatrixIntra[64];
+ unsigned char QuantMatrixInter[64];
+ int gmc_enabled;
+} CUVIDMPEG4PICPARAMS;
+
+/*!
+ * \struct CUVIDVC1PICPARAMS
+ * VC1 Picture Parameters
+ */
+typedef struct _CUVIDVC1PICPARAMS
+{
+ int ForwardRefIdx; /**< Picture index of forward reference (P/B-frames) */
+ int BackwardRefIdx; /**< Picture index of backward reference (B-frames) */
+ int FrameWidth; /**< Actual frame width */
+ int FrameHeight; /**< Actual frame height */
+ // PICTURE
+ int intra_pic_flag; /**< Set to 1 for I,BI frames */
+ int ref_pic_flag; /**< Set to 1 for I,P frames */
+ int progressive_fcm; /**< Progressive frame */
+ // SEQUENCE
+ int profile;
+ int postprocflag;
+ int pulldown;
+ int interlace;
+ int tfcntrflag;
+ int finterpflag;
+ int psf;
+ int multires;
+ int syncmarker;
+ int rangered;
+ int maxbframes;
+ // ENTRYPOINT
+ int panscan_flag;
+ int refdist_flag;
+ int extended_mv;
+ int dquant;
+ int vstransform;
+ int loopfilter;
+ int fastuvmc;
+ int overlap;
+ int quantizer;
+ int extended_dmv;
+ int range_mapy_flag;
+ int range_mapy;
+ int range_mapuv_flag;
+ int range_mapuv;
+ int rangeredfrm; // range reduction state
+} CUVIDVC1PICPARAMS;
+
+/*!
+ * \struct CUVIDJPEGPICPARAMS
+ * JPEG Picture Parameters
+ */
+typedef struct _CUVIDJPEGPICPARAMS
+{
+ int Reserved;
+} CUVIDJPEGPICPARAMS;
+
+
+ /*!
+ * \struct CUVIDHEVCPICPARAMS
+ * HEVC Picture Parameters
+ */
+typedef struct _CUVIDHEVCPICPARAMS
+{
+ // sps
+ int pic_width_in_luma_samples;
+ int pic_height_in_luma_samples;
+ unsigned char log2_min_luma_coding_block_size_minus3;
+ unsigned char log2_diff_max_min_luma_coding_block_size;
+ unsigned char log2_min_transform_block_size_minus2;
+ unsigned char log2_diff_max_min_transform_block_size;
+ unsigned char pcm_enabled_flag;
+ unsigned char log2_min_pcm_luma_coding_block_size_minus3;
+ unsigned char log2_diff_max_min_pcm_luma_coding_block_size;
+ unsigned char pcm_sample_bit_depth_luma_minus1;
+
+ unsigned char pcm_sample_bit_depth_chroma_minus1;
+ unsigned char pcm_loop_filter_disabled_flag;
+ unsigned char strong_intra_smoothing_enabled_flag;
+ unsigned char max_transform_hierarchy_depth_intra;
+ unsigned char max_transform_hierarchy_depth_inter;
+ unsigned char amp_enabled_flag;
+ unsigned char separate_colour_plane_flag;
+ unsigned char log2_max_pic_order_cnt_lsb_minus4;
+
+ unsigned char num_short_term_ref_pic_sets;
+ unsigned char long_term_ref_pics_present_flag;
+ unsigned char num_long_term_ref_pics_sps;
+ unsigned char sps_temporal_mvp_enabled_flag;
+ unsigned char sample_adaptive_offset_enabled_flag;
+ unsigned char scaling_list_enable_flag;
+ unsigned char IrapPicFlag;
+ unsigned char IdrPicFlag;
+
+ unsigned char bit_depth_luma_minus8;
+ unsigned char bit_depth_chroma_minus8;
+ unsigned char reserved1[14];
+
+ // pps
+ unsigned char dependent_slice_segments_enabled_flag;
+ unsigned char slice_segment_header_extension_present_flag;
+ unsigned char sign_data_hiding_enabled_flag;
+ unsigned char cu_qp_delta_enabled_flag;
+ unsigned char diff_cu_qp_delta_depth;
+ signed char init_qp_minus26;
+ signed char pps_cb_qp_offset;
+ signed char pps_cr_qp_offset;
+
+ unsigned char constrained_intra_pred_flag;
+ unsigned char weighted_pred_flag;
+ unsigned char weighted_bipred_flag;
+ unsigned char transform_skip_enabled_flag;
+ unsigned char transquant_bypass_enabled_flag;
+ unsigned char entropy_coding_sync_enabled_flag;
+ unsigned char log2_parallel_merge_level_minus2;
+ unsigned char num_extra_slice_header_bits;
+
+ unsigned char loop_filter_across_tiles_enabled_flag;
+ unsigned char loop_filter_across_slices_enabled_flag;
+ unsigned char output_flag_present_flag;
+ unsigned char num_ref_idx_l0_default_active_minus1;
+ unsigned char num_ref_idx_l1_default_active_minus1;
+ unsigned char lists_modification_present_flag;
+ unsigned char cabac_init_present_flag;
+ unsigned char pps_slice_chroma_qp_offsets_present_flag;
+
+ unsigned char deblocking_filter_override_enabled_flag;
+ unsigned char pps_deblocking_filter_disabled_flag;
+ signed char pps_beta_offset_div2;
+ signed char pps_tc_offset_div2;
+ unsigned char tiles_enabled_flag;
+ unsigned char uniform_spacing_flag;
+ unsigned char num_tile_columns_minus1;
+ unsigned char num_tile_rows_minus1;
+
+ unsigned short column_width_minus1[21];
+ unsigned short row_height_minus1[21];
+ unsigned int reserved3[15];
+
+ // RefPicSets
+ int NumBitsForShortTermRPSInSlice;
+ int NumDeltaPocsOfRefRpsIdx;
+ int NumPocTotalCurr;
+ int NumPocStCurrBefore;
+ int NumPocStCurrAfter;
+ int NumPocLtCurr;
+ int CurrPicOrderCntVal;
+ int RefPicIdx[16]; // [refpic] Indices of valid reference pictures (-1 if unused for reference)
+ int PicOrderCntVal[16]; // [refpic]
+ unsigned char IsLongTerm[16]; // [refpic] 0=not a long-term reference, 1=long-term reference
+ unsigned char RefPicSetStCurrBefore[8]; // [0..NumPocStCurrBefore-1] -> refpic (0..15)
+ unsigned char RefPicSetStCurrAfter[8]; // [0..NumPocStCurrAfter-1] -> refpic (0..15)
+ unsigned char RefPicSetLtCurr[8]; // [0..NumPocLtCurr-1] -> refpic (0..15)
+ unsigned char RefPicSetInterLayer0[8];
+ unsigned char RefPicSetInterLayer1[8];
+ unsigned int reserved4[12];
+
+ // scaling lists (diag order)
+ unsigned char ScalingList4x4[6][16]; // [matrixId][i]
+ unsigned char ScalingList8x8[6][64]; // [matrixId][i]
+ unsigned char ScalingList16x16[6][64]; // [matrixId][i]
+ unsigned char ScalingList32x32[2][64]; // [matrixId][i]
+ unsigned char ScalingListDCCoeff16x16[6]; // [matrixId]
+ unsigned char ScalingListDCCoeff32x32[2]; // [matrixId]
+} CUVIDHEVCPICPARAMS;
+
+
+/*!
+ * \struct CUVIDVP8PICPARAMS
+ * VP8 Picture Parameters
+ */
+typedef struct _CUVIDVP8PICPARAMS
+{
+ int width;
+ int height;
+ unsigned int first_partition_size;
+ //Frame Indexes
+ unsigned char LastRefIdx;
+ unsigned char GoldenRefIdx;
+ unsigned char AltRefIdx;
+ union {
+ struct {
+ unsigned char frame_type : 1; /**< 0 = KEYFRAME, 1 = INTERFRAME */
+ unsigned char version : 3;
+ unsigned char show_frame : 1;
+ unsigned char update_mb_segmentation_data : 1; /**< Must be 0 if segmentation is not enabled */
+ unsigned char Reserved2Bits : 2;
+ };
+ unsigned char wFrameTagFlags;
+ } tagflags;
+ unsigned char Reserved1[4];
+ unsigned int Reserved2[3];
+} CUVIDVP8PICPARAMS;
+
+/*!
+ * \struct CUVIDVP9PICPARAMS
+ * VP9 Picture Parameters
+ */
+typedef struct _CUVIDVP9PICPARAMS
+{
+ unsigned int width;
+ unsigned int height;
+
+ //Frame Indices
+ unsigned char LastRefIdx;
+ unsigned char GoldenRefIdx;
+ unsigned char AltRefIdx;
+ unsigned char colorSpace;
+
+ unsigned short profile : 3;
+ unsigned short frameContextIdx : 2;
+ unsigned short frameType : 1;
+ unsigned short showFrame : 1;
+ unsigned short errorResilient : 1;
+ unsigned short frameParallelDecoding : 1;
+ unsigned short subSamplingX : 1;
+ unsigned short subSamplingY : 1;
+ unsigned short intraOnly : 1;
+ unsigned short allow_high_precision_mv : 1;
+ unsigned short refreshEntropyProbs : 1;
+ unsigned short reserved2Bits : 2;
+
+ unsigned short reserved16Bits;
+
+ unsigned char refFrameSignBias[4];
+
+ unsigned char bitDepthMinus8Luma;
+ unsigned char bitDepthMinus8Chroma;
+ unsigned char loopFilterLevel;
+ unsigned char loopFilterSharpness;
+
+ unsigned char modeRefLfEnabled;
+ unsigned char log2_tile_columns;
+ unsigned char log2_tile_rows;
+
+ unsigned char segmentEnabled : 1;
+ unsigned char segmentMapUpdate : 1;
+ unsigned char segmentMapTemporalUpdate : 1;
+ unsigned char segmentFeatureMode : 1;
+ unsigned char reserved4Bits : 4;
+
+
+ unsigned char segmentFeatureEnable[8][4];
+ short segmentFeatureData[8][4];
+ unsigned char mb_segment_tree_probs[7];
+ unsigned char segment_pred_probs[3];
+ unsigned char reservedSegment16Bits[2];
+
+ int qpYAc;
+ int qpYDc;
+ int qpChDc;
+ int qpChAc;
+
+ unsigned int activeRefIdx[3];
+ unsigned int resetFrameContext;
+ unsigned int mcomp_filter_type;
+ unsigned int mbRefLfDelta[4];
+ unsigned int mbModeLfDelta[2];
+ unsigned int frameTagSize;
+ unsigned int offsetToDctParts;
+ unsigned int reserved128Bits[4];
+
+} CUVIDVP9PICPARAMS;
+
+
+/*!
+ * \struct CUVIDPICPARAMS
+ * Picture Parameters for Decoding
+ */
+typedef struct _CUVIDPICPARAMS
+{
+ int PicWidthInMbs; /**< Coded Frame Size */
+ int FrameHeightInMbs; /**< Coded Frame Height */
+ int CurrPicIdx; /**< Output index of the current picture */
+ int field_pic_flag; /**< 0=frame picture, 1=field picture */
+ int bottom_field_flag; /**< 0=top field, 1=bottom field (ignored if field_pic_flag=0) */
+ int second_field; /**< Second field of a complementary field pair */
+ // Bitstream data
+ unsigned int nBitstreamDataLen; /**< Number of bytes in bitstream data buffer */
+ const unsigned char *pBitstreamData; /**< Ptr to bitstream data for this picture (slice-layer) */
+ unsigned int nNumSlices; /**< Number of slices in this picture */
+ const unsigned int *pSliceDataOffsets; /**< nNumSlices entries, contains offset of each slice within the bitstream data buffer */
+ int ref_pic_flag; /**< This picture is a reference picture */
+ int intra_pic_flag; /**< This picture is entirely intra coded */
+ unsigned int Reserved[30]; /**< Reserved for future use */
+ // Codec-specific data
+ union {
+ CUVIDMPEG2PICPARAMS mpeg2; /**< Also used for MPEG-1 */
+ CUVIDH264PICPARAMS h264;
+ CUVIDVC1PICPARAMS vc1;
+ CUVIDMPEG4PICPARAMS mpeg4;
+ CUVIDJPEGPICPARAMS jpeg;
+ CUVIDHEVCPICPARAMS hevc;
+ CUVIDVP8PICPARAMS vp8;
+ CUVIDVP9PICPARAMS vp9;
+ unsigned int CodecReserved[1024];
+ } CodecSpecific;
+} CUVIDPICPARAMS;
+
+
+/*!
+ * \struct CUVIDPROCPARAMS
+ * Picture Parameters for Postprocessing
+ */
+typedef struct _CUVIDPROCPARAMS
+{
+ int progressive_frame; /**< Input is progressive (deinterlace_mode will be ignored) */
+ int second_field; /**< Output the second field (ignored if deinterlace mode is Weave) */
+ int top_field_first; /**< Input frame is top field first (1st field is top, 2nd field is bottom) */
+ int unpaired_field; /**< Input only contains one field (2nd field is invalid) */
+ // The fields below are used for raw YUV input
+ unsigned int reserved_flags; /**< Reserved for future use (set to zero) */
+ unsigned int reserved_zero; /**< Reserved (set to zero) */
+ unsigned long long raw_input_dptr; /**< Input CUdeviceptr for raw YUV extensions */
+ unsigned int raw_input_pitch; /**< pitch in bytes of raw YUV input (should be aligned appropriately) */
+ unsigned int raw_input_format; /**< Reserved for future use (set to zero) */
+ unsigned long long raw_output_dptr; /**< Reserved for future use (set to zero) */
+ unsigned int raw_output_pitch; /**< Reserved for future use (set to zero) */
+ unsigned int Reserved[48];
+ void *Reserved3[3];
+} CUVIDPROCPARAMS;
+
+
+/**
+ *
+ * In order to minimize decode latencies, there should be always at least 2 pictures in the decode
+ * queue at any time, in order to make sure that all decode engines are always busy.
+ *
+ * Overall data flow:
+ * - cuvidCreateDecoder(...)
+ * For each picture:
+ * - cuvidDecodePicture(N)
+ * - cuvidMapVideoFrame(N-4)
+ * - do some processing in cuda
+ * - cuvidUnmapVideoFrame(N-4)
+ * - cuvidDecodePicture(N+1)
+ * - cuvidMapVideoFrame(N-3)
+ * ...
+ * - cuvidDestroyDecoder(...)
+ *
+ * NOTE:
+ * - When the cuda context is created from a D3D device, the D3D device must also be created
+ * with the D3DCREATE_MULTITHREADED flag.
+ * - There is a limit to how many pictures can be mapped simultaneously (ulNumOutputSurfaces)
+ * - cuVidDecodePicture may block the calling thread if there are too many pictures pending
+ * in the decode queue
+ */
+
+/**
+ *
+ * Context-locking: to facilitate multi-threaded implementations, the following 4 functions
+ * provide a simple mutex-style host synchronization. If a non-NULL context is specified
+ * in CUVIDDECODECREATEINFO, the codec library will acquire the mutex associated with the given
+ * context before making any cuda calls.
+ * A multi-threaded application could create a lock associated with a context handle so that
+ * multiple threads can safely share the same cuda context:
+ * - use cuCtxPopCurrent immediately after context creation in order to create a 'floating' context
+ * that can be passed to cuvidCtxLockCreate.
+ * - When using a floating context, all cuda calls should only be made within a cuvidCtxLock/cuvidCtxUnlock section.
+ *
+ * NOTE: This is a safer alternative to cuCtxPushCurrent and cuCtxPopCurrent, and is not related to video
+ * decoder in any way (implemented as a critical section associated with cuCtx{Push|Pop}Current calls).
+*/
+/** @} */ /* End VIDEO_DECODER */
+
+#if defined(__cplusplus)
+}
+#endif /* __cplusplus */
+
+#endif // __CUDA_VIDEO_H__

QtAV-1.12.0.tar.gz/src/cuda/dynlink_nvcuvid.h Added

@@ -0,0 +1,256 @@
+/*
+ * This copyright notice applies to this header file only:
+ *
+ * Copyright (c) 2010-2016 NVIDIA Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the software, and to permit persons to whom the
+ * software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * \file nvcuvid.h
+ * NvCuvid API provides Video Decoding interface to NVIDIA GPU devices.
+ * \date 2015-2015
+ * This file contains the interface constants, structure definitions and function prototypes.
+ */
+
+#if !defined(__NVCUVID_H__)
+#define __NVCUVID_H__
+
+#include "dynlink_cuviddec.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif /* __cplusplus */
+
+////////////////////////////////////////////////////////////////////////////////////////////////
+//
+// High-level helper APIs for video sources
+//
+
+typedef void *CUvideosource;
+typedef void *CUvideoparser;
+typedef long long CUvideotimestamp;
+
+/**
+ * \addtogroup VIDEO_PARSER Video Parser
+ * @{
+ */
+
+/*!
+ * \enum cudaVideoState
+ * Video Source State
+ */
+typedef enum {
+ cudaVideoState_Error = -1, /**< Error state (invalid source) */
+ cudaVideoState_Stopped = 0, /**< Source is stopped (or reached end-of-stream) */
+ cudaVideoState_Started = 1 /**< Source is running and delivering data */
+} cudaVideoState;
+
+/*!
+ * \enum cudaAudioCodec
+ * Audio compression
+ */
+typedef enum {
+ cudaAudioCodec_MPEG1=0, /**< MPEG-1 Audio */
+ cudaAudioCodec_MPEG2, /**< MPEG-2 Audio */
+ cudaAudioCodec_MP3, /**< MPEG-1 Layer III Audio */
+ cudaAudioCodec_AC3, /**< Dolby Digital (AC3) Audio */
+ cudaAudioCodec_LPCM /**< PCM Audio */
+} cudaAudioCodec;
+
+/*!
+ * \struct CUVIDEOFORMAT
+ * Video format
+ */
+typedef struct
+{
+ cudaVideoCodec codec; /**< Compression format */
+ /**
+ * frame rate = numerator / denominator (for example: 30000/1001)
+ */
+ struct {
+ unsigned int numerator; /**< frame rate numerator (0 = unspecified or variable frame rate) */
+ unsigned int denominator; /**< frame rate denominator (0 = unspecified or variable frame rate) */
+ } frame_rate;
+ unsigned char progressive_sequence; /**< 0=interlaced, 1=progressive */
+ unsigned char bit_depth_luma_minus8; /**< high bit depth Luma */
+ unsigned char bit_depth_chroma_minus8; /**< high bit depth Chroma */
+ unsigned char reserved1; /**< Reserved for future use */
+ unsigned int coded_width; /**< coded frame width */
+ unsigned int coded_height; /**< coded frame height */
+ /**
+ * area of the frame that should be displayed
+ * typical example:
+ * coded_width = 1920, coded_height = 1088
+ * display_area = { 0,0,1920,1080 }
+ */
+ struct {
+ int left; /**< left position of display rect */
+ int top; /**< top position of display rect */
+ int right; /**< right position of display rect */
+ int bottom; /**< bottom position of display rect */
+ } display_area;
+ cudaVideoChromaFormat chroma_format; /**< Chroma format */
+ unsigned int bitrate; /**< video bitrate (bps, 0=unknown) */
+ /**
+ * Display Aspect Ratio = x:y (4:3, 16:9, etc)
+ */
+ struct {
+ int x;
+ int y;
+ } display_aspect_ratio;
+ /**
+ * Video Signal Description
+ */
+ struct {
+ unsigned char video_format : 3;
+ unsigned char video_full_range_flag : 1;
+ unsigned char reserved_zero_bits : 4;
+ unsigned char color_primaries;
+ unsigned char transfer_characteristics;
+ unsigned char matrix_coefficients;
+ } video_signal_description;
+ unsigned int seqhdr_data_length; /**< Additional bytes following (CUVIDEOFORMATEX) */
+} CUVIDEOFORMAT;
+
+/*!
+ * \struct CUVIDEOFORMATEX
+ * Video format including raw sequence header information
+ */
+typedef struct
+{
+ CUVIDEOFORMAT format;
+ unsigned char raw_seqhdr_data[1024];
+} CUVIDEOFORMATEX;
+
+/*!
+ * \struct CUAUDIOFORMAT
+ * Audio Formats
+ */
+typedef struct
+{
+ cudaAudioCodec codec; /**< Compression format */
+ unsigned int channels; /**< number of audio channels */
+ unsigned int samplespersec; /**< sampling frequency */
+ unsigned int bitrate; /**< For uncompressed, can also be used to determine bits per sample */
+ unsigned int reserved1; /**< Reserved for future use */
+ unsigned int reserved2; /**< Reserved for future use */
+} CUAUDIOFORMAT;
+
+
+/*!
+ * \enum CUvideopacketflags
+ * Data packet flags
+ */
+typedef enum {
+ CUVID_PKT_ENDOFSTREAM = 0x01, /**< Set when this is the last packet for this stream */
+ CUVID_PKT_TIMESTAMP = 0x02, /**< Timestamp is valid */
+ CUVID_PKT_DISCONTINUITY = 0x04 /**< Set when a discontinuity has to be signalled */
+} CUvideopacketflags;
+
+/*!
+ * \struct CUVIDSOURCEDATAPACKET
+ * Data Packet
+ */
+typedef struct _CUVIDSOURCEDATAPACKET
+{
+ unsigned long flags; /**< Combination of CUVID_PKT_XXX flags */
+ unsigned long payload_size; /**< number of bytes in the payload (may be zero if EOS flag is set) */
+ const unsigned char *payload; /**< Pointer to packet payload data (may be NULL if EOS flag is set) */
+ CUvideotimestamp timestamp; /**< Presentation timestamp (10MHz clock), only valid if CUVID_PKT_TIMESTAMP flag is set */
+} CUVIDSOURCEDATAPACKET;
+
+// Callback for packet delivery
+typedef int (CUDAAPI *PFNVIDSOURCECALLBACK)(void *, CUVIDSOURCEDATAPACKET *);
+
+/*!
+ * \struct CUVIDSOURCEPARAMS
+ * Source Params
+ */
+typedef struct _CUVIDSOURCEPARAMS
+{
+ unsigned int ulClockRate; /**< Timestamp units in Hz (0=default=10000000Hz) */
+ unsigned int uReserved1[7]; /**< Reserved for future use - set to zero */
+ void *pUserData; /**< Parameter passed in to the data handlers */
+ PFNVIDSOURCECALLBACK pfnVideoDataHandler; /**< Called to deliver audio packets */
+ PFNVIDSOURCECALLBACK pfnAudioDataHandler; /**< Called to deliver video packets */
+ void *pvReserved2[8]; /**< Reserved for future use - set to NULL */
+} CUVIDSOURCEPARAMS;
+
+/*!
+ * \enum CUvideosourceformat_flags
+ * CUvideosourceformat_flags
+ */
+typedef enum {
+ CUVID_FMT_EXTFORMATINFO = 0x100 /**< Return extended format structure (CUVIDEOFORMATEX) */
+} CUvideosourceformat_flags;
+
+/**
+ * \struct CUVIDPARSERDISPINFO
+ */
+typedef struct _CUVIDPARSERDISPINFO
+{
+ int picture_index; /**< */
+ int progressive_frame; /**< */
+ int top_field_first; /**< */
+ int repeat_first_field; /**< Number of additional fields (1=ivtc, 2=frame doubling, 4=frame tripling, -1=unpaired field) */
+ CUvideotimestamp timestamp; /**< */
+} CUVIDPARSERDISPINFO;
+
+//
+// Parser callbacks
+// The parser will call these synchronously from within cuvidParseVideoData(), whenever a picture is ready to
+// be decoded and/or displayed.
+//
+typedef int (CUDAAPI *PFNVIDSEQUENCECALLBACK)(void *, CUVIDEOFORMAT *);
+typedef int (CUDAAPI *PFNVIDDECODECALLBACK)(void *, CUVIDPICPARAMS *);
+typedef int (CUDAAPI *PFNVIDDISPLAYCALLBACK)(void *, CUVIDPARSERDISPINFO *);
+
+/**
+ * \struct CUVIDPARSERPARAMS
+ */
+typedef struct _CUVIDPARSERPARAMS
+{
+ cudaVideoCodec CodecType; /**< cudaVideoCodec_XXX */
+ unsigned int ulMaxNumDecodeSurfaces; /**< Max # of decode surfaces (parser will cycle through these) */
+ unsigned int ulClockRate; /**< Timestamp units in Hz (0=default=10000000Hz) */
+ unsigned int ulErrorThreshold; /**< % Error threshold (0-100) for calling pfnDecodePicture (100=always call pfnDecodePicture even if picture bitstream is fully corrupted) */
+ unsigned int ulMaxDisplayDelay; /**< Max display queue delay (improves pipelining of decode with display) - 0=no delay (recommended values: 2..4) */
+ unsigned int uReserved1[5]; /**< Reserved for future use - set to 0 */
+ void *pUserData; /**< User data for callbacks */
+ PFNVIDSEQUENCECALLBACK pfnSequenceCallback; /**< Called before decoding frames and/or whenever there is a format change */
+ PFNVIDDECODECALLBACK pfnDecodePicture; /**< Called when a picture is ready to be decoded (decode order) */
+ PFNVIDDISPLAYCALLBACK pfnDisplayPicture; /**< Called whenever a picture is ready to be displayed (display order) */
+ void *pvReserved2[7]; /**< Reserved for future use - set to NULL */
+ CUVIDEOFORMATEX *pExtVideoInfo; /**< [Optional] sequence header data from system layer */
+} CUVIDPARSERPARAMS;
+
+/** @} */ /* END VIDEO_PARSER */
+////////////////////////////////////////////////////////////////////////////////////////////////
+
+#if defined(__cplusplus)
+}
+#endif /* __cplusplus */
+
+#endif // __NVCUVID_H__
+
+

QtAV-1.11.0.tar.gz/src/cuda/helper_cuda.h -> QtAV-1.12.0.tar.gz/src/cuda/helper_cuda.h Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -60,9 +60,6 @@
 case CUDA_ERROR_ECC_UNCORRECTABLE: return "CUDA_ERROR_ECC_UNCORRECTABLE";
 case CUDA_ERROR_UNSUPPORTED_LIMIT: return "CUDA_ERROR_UNSUPPORTED_LIMIT";
 case CUDA_ERROR_CONTEXT_ALREADY_IN_USE: return "CUDA_ERROR_CONTEXT_ALREADY_IN_USE";
- case CUDA_ERROR_PEER_ACCESS_UNSUPPORTED: return "CUDA_ERROR_PEER_ACCESS_UNSUPPORTED";
- case CUDA_ERROR_INVALID_PTX: return "CUDA_ERROR_INVALID_PTX";
- case CUDA_ERROR_INVALID_GRAPHICS_CONTEXT: return "CUDA_ERROR_INVALID_GRAPHICS_CONTEXT";
 case CUDA_ERROR_INVALID_SOURCE: return "CUDA_ERROR_INVALID_SOURCE";
 case CUDA_ERROR_FILE_NOT_FOUND: return "CUDA_ERROR_FILE_NOT_FOUND";
 case CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND: return "CUDA_ERROR_SHARED_OBJECT_SYMBOL_NOT_FOUND";
@@ -71,7 +68,6 @@
 case CUDA_ERROR_INVALID_HANDLE: return "CUDA_ERROR_INVALID_HANDLE";
 case CUDA_ERROR_NOT_FOUND: return "CUDA_ERROR_NOT_FOUND";
 case CUDA_ERROR_NOT_READY: return "CUDA_ERROR_NOT_READY";
- case CUDA_ERROR_ILLEGAL_ADDRESS: return "CUDA_ERROR_ILLEGAL_ADDRESS";
 case CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES: return "CUDA_ERROR_LAUNCH_OUT_OF_RESOURCES";
 case CUDA_ERROR_LAUNCH_TIMEOUT: return "CUDA_ERROR_LAUNCH_TIMEOUT";
 case CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING: return "CUDA_ERROR_LAUNCH_INCOMPATIBLE_TEXTURING";
@@ -79,18 +75,7 @@
 case CUDA_ERROR_PEER_ACCESS_NOT_ENABLED: return "CUDA_ERROR_PEER_ACCESS_NOT_ENABLED";
 case CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE: return "CUDA_ERROR_PRIMARY_CONTEXT_ACTIVE";
 case CUDA_ERROR_CONTEXT_IS_DESTROYED: return "CUDA_ERROR_CONTEXT_IS_DESTROYED";
- case CUDA_ERROR_ASSERT: return "CUDA_ERROR_ASSERT";
- case CUDA_ERROR_TOO_MANY_PEERS: return "CUDA_ERROR_TOO_MANY_PEERS";
- case CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED: return "CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED";
- case CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED: return "CUDA_ERROR_HOST_MEMORY_NOT_REGISTERED";
- case CUDA_ERROR_HARDWARE_STACK_ERROR: return "CUDA_ERROR_HARDWARE_STACK_ERROR";
- case CUDA_ERROR_ILLEGAL_INSTRUCTION: return "CUDA_ERROR_ILLEGAL_INSTRUCTION";
- case CUDA_ERROR_MISALIGNED_ADDRESS: return "CUDA_ERROR_MISALIGNED_ADDRESS";
- case CUDA_ERROR_INVALID_ADDRESS_SPACE: return "CUDA_ERROR_INVALID_ADDRESS_SPACE";
- case CUDA_ERROR_INVALID_PC: return "CUDA_ERROR_INVALID_PC";
 case CUDA_ERROR_LAUNCH_FAILED: return "CUDA_ERROR_LAUNCH_FAILED";
- case CUDA_ERROR_NOT_PERMITTED: return "CUDA_ERROR_NOT_PERMITTED";
- case CUDA_ERROR_NOT_SUPPORTED: return "CUDA_ERROR_NOT_SUPPORTED";
 case CUDA_ERROR_UNKNOWN: return "CUDA_ERROR_UNKNOWN";
 default:
 return "CUDA_ERROR_UNKNOWN";
@@ -124,7 +109,7 @@
 { 0x35, 192}, // Kepler Generation (SM 3.5) GK11x class
 { 0x37, 192}, // Kepler Generation (SM 3.7) GK21x class
 { 0x50, 128}, // Maxwell Generation (SM 5.0) GM10x class
- { 0x52, 128}, // Maxwell Generation (SM 5.2) GM20x class
+ { 0x52, 128}, // Maxwell Generation (SM 5.2) GM20x class //enc: h264 yuv444p, hevc (libavcodec/nvenc.c)
 { -1, -1 }
 };
 int index = 0;

QtAV-1.11.0.tar.gz/src/filter/EncodeFilter.cpp -> QtAV-1.12.0.tar.gz/src/filter/EncodeFilter.cpp Changed

QtAV-1.11.0.tar.gz/src/filter/SubtitleFilter.cpp -> QtAV-1.12.0.tar.gz/src/filter/SubtitleFilter.cpp Changed

QtAV-1.12.0.tar.gz/src/i18n/QtAV.ts Added

@@ -0,0 +1,481 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!DOCTYPE TS>
+<TS version="2.1">
+<context>
+ <name>AudioOutputPulse</name>
+ <message>
+ <location filename="../output/audio/AudioOutputPulse.cpp" line="268"/>
+ <source>PulseAudio %1, protocol: %2, server protocol: %3</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QObject</name>
+ <message>
+ <location filename="../AVError.cpp" line="136"/>
+ <source>No error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="139"/>
+ <source>Open error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="142"/>
+ <source>Open timed out</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="145"/>
+ <source>Parse stream timed out</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="148"/>
+ <source>Parse stream error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="151"/>
+ <source>Stream not found</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="154"/>
+ <source>Read packet timed out</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="157"/>
+ <source>Read error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="160"/>
+ <source>Seek error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="163"/>
+ <source>Resource error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="167"/>
+ <source>Open codec error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="170"/>
+ <source>Close codec error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="173"/>
+ <source>Video codec not found</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="176"/>
+ <source>Audio codec not found</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="179"/>
+ <source>Subtitle codec not found</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="182"/>
+ <source>Codec error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="186"/>
+ <source>Format error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="190"/>
+ <source>Network error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="194"/>
+ <source>Access denied</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVError.cpp" line="198"/>
+ <source>Unknow error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="163"/>
+ <source>Build version</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="172"/>
+ <source>Runtime version</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="197"/>
+ <source>Multimedia framework base on Qt and FFmpeg.
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="198"/>
+ <source>Distributed under the terms of LGPLv2.1 or later.
+</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="199"/>
+ <source>Shanghai University-&gt;S3 Graphics-&gt;Deepin, Shanghai, China</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="200"/>
+ <source>Donate</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="201"/>
+ <source>Source</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../QtAV_Global.cpp" line="202"/>
+ <source>Home page</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="342"/>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="239"/>
+ <source>ZeroCopy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="343"/>
+ <source>DirectCopy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="344"/>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="241"/>
+ <source>GenericCopy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="345"/>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="242"/>
+ <source>copyMode</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="629"/>
+ <source>Codec %1 is not supported by CUDA</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="426"/>
+ <source>codecName</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="427"/>
+ <source>skip_loop_filter</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="428"/>
+ <source>skip_idct</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="429"/>
+ <source>strict</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="430"/>
+ <source>skip_frame</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="431"/>
+ <source>threads</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="432"/>
+ <source>thread_type</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="433"/>
+ <source>vismv</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="434"/>
+ <source>bug</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="240"/>
+ <source>OptimizedCopy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVAAPI.cpp" line="499"/>
+ <source>VA API version %1.%2; Vendor: %3;</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="160"/>
+ <source>interop</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="161"/>
+ <source>format</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../filter/LibAVFilter.cpp" line="208"/>
+ <source>Options:</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::AVDecoder</name>
+ <message>
+ <location filename="../codec/AVDecoder.cpp" line="79"/>
+ <source>No codec could be found for &apos;%1&apos;</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::AVDemuxer</name>
+ <message>
+ <location filename="../AVDemuxer.cpp" line="441"/>
+ <location filename="../AVDemuxer.cpp" line="463"/>
+ <source>error reading stream data</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVDemuxer.cpp" line="597"/>
+ <source>seek error</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVDemuxer.cpp" line="801"/>
+ <source>failed to open media</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVDemuxer.cpp" line="819"/>
+ <source>failed to find stream info</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVDemuxer.cpp" line="1209"/>
+ <source>interrupted by user</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../AVDemuxer.cpp" line="1215"/>
+ <source>timeout</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderCUDA</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="334"/>
+ <source>Decoding surfaces</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="335"/>
+ <source>Decoder flags</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="337"/>
+ <source>Performace: ZeroCopy &gt; DirectCopy &gt; GenericCopy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="338"/>
+ <source>ZeroCopy: no copy back from GPU to System memory. Directly render the decoded data on GPU</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="339"/>
+ <source>DirectCopy: copy back to host memory but video frames and map to GL texture</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderCUDA.cpp" line="340"/>
+ <source>GenericCopy: copy back to host memory and each video frame</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderD3D</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderD3D.cpp" line="315"/>
+ <source>Decoding surfaces</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderD3D.cpp" line="315"/>
+ <source>0: auto</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderFFmpeg</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="263"/>
+ <source>Skipping the loop filter (aka deblocking) usually has determinal effect on quality. However it provides a big speedup for hi definition streams</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="265"/>
+ <source>Force skipping of idct to speed up decoding for frame types (-1=None, 0=Default, 1=B-frames, 2=P-frames, 3=B+P frames, 4=all frames)</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="267"/>
+ <source>Force skipping frames for speed up decoding.</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="269"/>
+ <source>Number of decoding threads. Set before open. Maybe no effect for some decoders</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="270"/>
+ <source>0: auto</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpeg.cpp" line="271"/>
+ <source>1: single thread decoding</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderFFmpegHW</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="229"/>
+ <source>ZeroCopy: fastest. Direct rendering without data copy between CPU and GPU</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="230"/>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="231"/>
+ <source>Not implemented for all codecs</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="232"/>
+ <source>OptimizedCopy: copy from USWC memory optimized by SSE4.1</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="233"/>
+ <source>GenericCopy: slowest. Generic cpu copy</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="235"/>
+ <source>Number of decoding threads. Set before open. Maybe no effect for some decoders</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="236"/>
+ <source>Multithread decoding may crash</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="237"/>
+ <source>0: auto</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderFFmpegHW.cpp" line="238"/>
+ <source>1: single thread decoding</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderVAAPI</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderVAAPI.cpp" line="269"/>
+ <source>Decoding surfaces</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVAAPI.cpp" line="269"/>
+ <source>0: auto</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVAAPI.cpp" line="270"/>
+ <source>Maybe faster</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderVDA</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderVDA.cpp" line="159"/>
+ <source>Output pixel format from decoder. Performance NV12 &gt; UYVY &gt; YUV420P &gt; YUYV.
+OSX &lt; 10.7 only supports UYVY and YUV420p</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+<context>
+ <name>QtAV::VideoDecoderVideoToolbox</name>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="153"/>
+ <source>Output pixel format from decoder. Performance NV12 &gt; UYVY &gt; BGRA &gt; YUV420P &gt; YUYV.
+OSX &lt; 10.7 only supports UYVY, BGRA and YUV420p</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="155"/>
+ <source>Interop with OpenGL</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="156"/>
+ <source>CVPixelBuffer: macOS+iOS</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="157"/>
+ <source>CVOpenGLES: iOS, no copy, fast</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="158"/>
+ <source>IOSurface: macOS, no copy, fast</source>
+ <translation type="unfinished"></translation>
+ </message>
+ <message>
+ <location filename="../codec/video/VideoDecoderVideoToolbox.cpp" line="159"/>
+ <source>Auto: choose the fastest</source>
+ <translation type="unfinished"></translation>
+ </message>
+</context>
+</TS>

QtAV-1.11.0.tar.gz/src/io/MediaIO.cpp -> QtAV-1.12.0.tar.gz/src/io/MediaIO.cpp Changed

@@ -171,16 +171,32 @@
     return no_protocols;
 }
 
-#define IODATA_BUFFER_SIZE 32768 //
+#define IODATA_BUFFER_SIZE 32768 // TODO: user configurable
+static const int kBufferSizeDefault = 32768;
+
+void MediaIO::setBufferSize(int value)
+{
+    DPTR_D(MediaIO);
+    if (d.buffer_size == value)
+        return;
+    d.buffer_size = value;
+}
+
+int MediaIO::bufferSize() const
+{
+    return d_func().buffer_size;
+}
 
 void* MediaIO::avioContext()
 {
     DPTR_D(MediaIO);
+    if (d.ctx)
+        return d.ctx;
     // buffer will be released in av_probe_input_buffer2=>ffio_rewind_with_probe_data. always is? may be another context
     unsigned char* buf = (unsigned char*)av_malloc(IODATA_BUFFER_SIZE);
     // open for write if 1. SET 0 if open for read otherwise data ptr in av_read(data, ...) does not change
     const int write_flag = (accessMode() == Write) && isWritable();
-    d.ctx = avio_alloc_context(buf, IODATA_BUFFER_SIZE, write_flag, this, &av_read, write_flag ? &av_write : NULL, &av_seek);
+    d.ctx = avio_alloc_context(buf, bufferSize() > 0 ? bufferSize() : kBufferSizeDefault, write_flag, this, &av_read, write_flag ? &av_write : NULL, &av_seek);
     // if seekable==false, containers that estimate duration from pts(or bit rate) will not seek to the last frame when computing duration
     // but it's still seekable if call seek outside(e.g. from demuxer)
     // TODO: isVariableSize: size = -real_size

QtAV-1.11.0.tar.gz/src/libQtAV.pri -> QtAV-1.12.0.tar.gz/src/libQtAV.pri Changed

QtAV-1.11.0.tar.gz/src/libQtAV.pro -> QtAV-1.12.0.tar.gz/src/libQtAV.pro Changed

@@ -14,24 +14,24 @@
   config_gl: QT += opengl
 }
 CONFIG *= qtav-buildlib
-staticlib: DEFINES += BUILD_QTAV_STATIC
 static: CONFIG *= static_ffmpeg
-INCLUDEPATH += $$[QT_INSTALL_HEADERS]
-icon.files = $$PWD/$${TARGET}.svg
-icon.path = /usr/share/icons/hicolor/scalable/apps
-!contains(QMAKE_HOST.os, Windows):INSTALLS += icon
+INCLUDEPATH += $$[QT_INSTALL_HEADERS] # TODO: ffmpeg dir
 
 #mac: simd.prf will load qt_build_config and the result is soname will prefixed with QT_INSTALL_LIBS and link flag will append soname after QMAKE_LFLAGS_SONAME
 config_libcedarv: CONFIG *= neon config_simd #need by qt4 addSimdCompiler(). neon or config_neon is required because tests/arch can not detect neon
 ## sse2 sse4_1 may be defined in Qt5 qmodule.pri but is not included. Qt4 defines sse and sse2
 sse4_1|config_sse4_1|contains(TARGET_ARCH_SUB, sse4.1): CONFIG *= sse4_1 config_simd
 sse2|config_sse2|contains(TARGET_ARCH_SUB, sse2): CONFIG *= sse2 config_simd
-
+CONFIG(debug, debug|release): DEFINES += DEBUG
 #release: DEFINES += QT_NO_DEBUG_OUTPUT
 #var with '_' can not pass to pri?
 PROJECTROOT = $$PWD/..
 !include(libQtAV.pri): error("could not find libQtAV.pri")
 preparePaths($$OUT_PWD/../out)
+exists($$PROJECTROOT/extra/qtLongName(include)): INCLUDEPATH += $$PROJECTROOT/extra/qtLongName(include)
+exists($$PROJECTROOT/extra/qtLongName(lib)): LIBS += -L$$PROJECTROOT/extra/qtLongName(lib)
+staticlib: DEFINES += BUILD_QTAV_STATIC
+
 config_uchardet {
   DEFINES += LINK_UCHARDET
   LIBS *= -luchardet
@@ -53,7 +53,7 @@
     RC_ICONS = QtAV.ico
     QMAKE_TARGET_COMPANY = "Shanghai University->S3 Graphics->Deepin | wbsecg1@gmail.com"
     QMAKE_TARGET_DESCRIPTION = "QtAV Multimedia framework. http://qtav.org"
-    QMAKE_TARGET_COPYRIGHT = "Copyright (C) 2012-2016 WangBin, wbsecg1@gmail.com"
+    QMAKE_TARGET_COPYRIGHT = "Copyright (C) 2012-2017 WangBin, wbsecg1@gmail.com"
     QMAKE_TARGET_PRODUCT = "QtAV"
 } else:win32 {
     RC_FILE = QtAV.rc
@@ -70,7 +70,7 @@
 }
 
 OTHER_FILES += $$RC_FILE QtAV.svg
-TRANSLATIONS = i18n/QtAV_zh_CN.ts
+TRANSLATIONS = i18n/QtAV_zh_CN.ts i18n/QtAV.ts
 
 sse4_1 {
   CONFIG += sse2 #only sse4.1 is checked. sse2 now can be disabled if sse4.1 is disabled
@@ -88,13 +88,15 @@
 # cross build, old vc etc.
   !config_dx: INCLUDEPATH += $$PROJECTROOT/contrib/dxsdk
 }
-*msvc* {
+*msvc*:!winrt {
 #link FFmpeg and portaudio which are built by gcc need /SAFESEH:NO
-win32-msvc2010|win32-msvc2008: QMAKE_LFLAGS *= /DEBUG #workaround for CoInitializeEx() and other symbols not found at runtime
+  win32-msvc2010|win32-msvc2008|win32-msvc2012 {
+    QMAKE_LFLAGS *= /DEBUG #workaround for CoInitializeEx() and other symbols not found at runtime
+    INCLUDEPATH *= compat/msvc # vs2012 only has stdint.h
+  }
     debug: QMAKE_LFLAGS += /SAFESEH:NO
 #CXXFLAGS debug: /MTd
-    QMAKE_LFLAGS *= /NODEFAULTLIB:libcmt.lib /NODEFAULTLIB:libcmtd.lib #for msbuild vs2013
-    INCLUDEPATH *= compat/msvc
+    !static:QMAKE_LFLAGS *= /NODEFAULTLIB:libcmt.lib /NODEFAULTLIB:libcmtd.lib #for msbuild vs2013
 }
 capi {
 contains(QT_CONFIG, egl)|contains(QT_CONFIG, dynamicgl)|contains(QT_CONFIG, opengles2) {
@@ -348,6 +350,8 @@
   }
   OTHER_FILES += shaders/planar.f.glsl shaders/rgb.f.glsl
   SDK_HEADERS *= \
+    QtAV/Geometry.h \
+    QtAV/GeometryRenderer.h \
     QtAV/GLSLFilter.h \
     QtAV/OpenGLRendererBase.h \
     QtAV/OpenGLTypes.h \
@@ -360,8 +364,6 @@
   HEADERS *= \
     opengl/gl_api.h \
     opengl/OpenGLHelper.h \
-    opengl/Geometry.h \
-    opengl/GeometryRenderer.h \
     opengl/SubImagesGeometry.h \
     opengl/SubImagesRenderer.h \
     opengl/ShaderManager.h
@@ -412,8 +414,8 @@
 # use old libva.so to link against
 glibc_compat: *linux*: LIBS += -lrt  # do not use clock_gettime in libc, GLIBC_2.17 is not available on old system
 static_ffmpeg {
-# libs needed by mac static ffmpeg. corefoundation: vda, avdevice
-  mac|ios: LIBS += -liconv -lbz2 -llzma -lz -framework CoreFoundation  -Wl,-framework,Security
+# libs needed by mac static ffmpeg. corefoundation: vda, avdevice. coca: vf_coreimage
+  mac|ios: LIBS += -liconv -lbz2 -llzma -lz -framework CoreFoundation -framework Security # -framework Cocoa Cocoa is not available on ios10
   win32: LIBS *= -lws2_32 -lstrmiids -lvfw32 -luuid
   !mac:*g++* {
     LIBS *= -lz
@@ -610,7 +612,10 @@
    }
 }
 
-unix:!android:!mac {
+unix:!mac:!cross_compile {
+icon.files = $$PWD/$${TARGET}.svg
+icon.path = /usr/share/icons/hicolor/scalable/apps
+INSTALLS += icon
 #debian
 DEB_INSTALL_LIST = .$$[QT_INSTALL_LIBS]/libQt*AV.so.*
 libqtav.target = libqtav.install
@@ -620,14 +625,15 @@
 
 DEB_INSTALL_LIST = $$join(SDK_HEADERS, \\n.$$[QT_INSTALL_HEADERS]/, .$$[QT_INSTALL_HEADERS]/)
 DEB_INSTALL_LIST += .$$[QT_INSTALL_LIBS]/libQt*AV.prl .$$[QT_INSTALL_LIBS]/libQt*AV.so
-DEB_INSTALL_LIST += .$$[QT_INSTALL_BINS]/../mkspecs/features/av.prf .$$[QT_INSTALL_BINS]/../mkspecs/modules/qt_lib_av.pri
+MKSPECS_DIR=$$[QT_HOST_DATA]/mkspecs # we only build deb for qt5, so QT_HOST_DATA is fine. qt4 can use $$[QMAKE_MKSPECS]
+DEB_INSTALL_LIST += .$${MKSPECS_DIR}/features/av.prf .$${MKSPECS_DIR}/modules/qt_lib_av.pri
 qtav_dev.target = qtav-dev.install
 qtav_dev.commands = echo \"$$join(DEB_INSTALL_LIST, \\n)\" >$$PROJECTROOT/debian/$${qtav_dev.target}
 QMAKE_EXTRA_TARGETS += qtav_dev
 target.depends *= $${qtav_dev.target}
 
 DEB_INSTALL_LIST = $$join(SDK_PRIVATE_HEADERS, \\n.$$[QT_INSTALL_HEADERS]/QtAV/*/, .$$[QT_INSTALL_HEADERS]/QtAV/*/)
-DEB_INSTALL_LIST += .$$[QT_INSTALL_BINS]/../mkspecs/modules/qt_lib_av_private.pri
+DEB_INSTALL_LIST += .$${MKSPECS_DIR}/modules/qt_lib_av_private.pri
 qtav_private_dev.target = qtav-private-dev.install
 qtav_private_dev.commands = echo \"$$join(DEB_INSTALL_LIST, \\n)\" >$$PROJECTROOT/debian/$${qtav_private_dev.target}
 QMAKE_EXTRA_TARGETS += qtav_private_dev

QtAV-1.11.0.tar.gz/src/opengl/Geometry.cpp -> QtAV-1.12.0.tar.gz/src/opengl/Geometry.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2016)
 
@@ -19,8 +19,9 @@
 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 ******************************************************************************/
 
-#include "Geometry.h"
-#include "opengl/OpenGLHelper.h"
+#include "QtAV/Geometry.h"
+#include <QtDebug>
+#include <QtCore/qmath.h>
 
 namespace QtAV {
 
@@ -45,6 +46,7 @@
 dbg.nospace() << ", offset " << a.offset();
 dbg.nospace() << ", tupleSize " << a.tupleSize();
 dbg.nospace() << ", dataType " << a.type();
+ dbg.nospace() << ", normalize " << a.normalize();
 return dbg.space();
 }
 #endif
@@ -56,56 +58,161 @@
 , m_icount(indexCount)
 {}
 
+int Geometry::indexDataSize() const
+{
+ switch (indexType()) {
+ case TypeU16: return indexCount()*2;
+ case TypeU32: return indexCount()*4;
+ default: return indexCount();
+ }
+}
+
+void Geometry::setIndexValue(int index, int value)
+{
+ switch (indexType()) {
+ case TypeU8: {
+ quint8* d = (quint8*)m_idata.constData();
+ *(d+index) = value;
+ }
+ break;
+ case TypeU16: {
+ quint16* d = (quint16*)m_idata.constData();
+ *(d+index) = value;
+ }
+ break;
+ case TypeU32: {
+ quint32* d = (quint32*)m_idata.constData();
+ *(d+index) = value;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+void Geometry::setIndexValue(int index, int v1, int v2, int v3)
+{
+ // TODO: *(d + 3*index), *(d + 3*index + 1), *(d + 3*index + 2)
+ switch (indexType()) {
+ case TypeU8: {
+ quint8* d = (quint8*)m_idata.constData();
+ *(d+index++) = v1;
+ *(d+index++) = v2;
+ *(d+index++) = v2;
+ }
+ break;
+ case TypeU16: {
+ quint16* d = (quint16*)m_idata.constData();
+ *(d+index++) = v1;
+ *(d+index++) = v2;
+ *(d+index++) = v3;
+ }
+ break;
+ case TypeU32: {
+ quint32* d = (quint32*)m_idata.constData();
+ *(d+index++) = v1;
+ *(d+index++) = v2;
+ *(d+index++) = v3;
+ }
+ break;
+ default:
+ break;
+ }
+}
+
+void Geometry::dumpVertexData()
+{
+ printf("vertex %p: ", m_vdata.constData());
+ const int n = stride()/sizeof(float);
+ for (int i = 0; i < m_vcount; ++i) {
+ const float* f = (const float*)(m_vdata.constData()+i*stride());
+ for (int j = 0; j < n; ++j) {
+ printf("%f, ", *(f+j));
+ }
+ printf(";");
+ }
+ printf("\n");fflush(0);
+}
+
+void Geometry::dumpIndexData()
+{
+ switch (indexType()) {
+ case TypeU8: {
+ quint8* d = (quint8*)m_idata.constData();
+ for (int i = 0; i < m_icount; ++i) printf("%u, ", *(d+i));
+ }
+ break;
+ case TypeU16: {
+ quint16* d = (quint16*)m_idata.constData();
+ for (int i = 0; i < m_icount; ++i) printf("%u, ", *(d+i));
+ }
+ break;
+ case TypeU32: {
+ quint32* d = (quint32*)m_idata.constData();
+ for (int i = 0; i < m_icount; ++i) printf("%u, ", *(d+i));
+ }
+ break;
+ default:
+ break;
+ }
+ printf("\n");fflush(0);
+}
+
 void Geometry::allocate(int nbVertex, int nbIndex)
 {
 m_icount = nbIndex;
 m_vcount = nbVertex;
 m_vdata.resize(nbVertex*stride());
+ memset(m_vdata.data(), 0, m_vdata.size());
 if (nbIndex <= 0) {
 m_idata.clear(); // required?
 return;
 }
 switch (indexType()) {
- case GL_UNSIGNED_BYTE:
+ case TypeU8:
 m_idata.resize(nbIndex*sizeof(quint8));
 break;
- case GL_UNSIGNED_SHORT:
+ case TypeU16:
 m_idata.resize(nbIndex*sizeof(quint16));
 break;
- case GL_UNSIGNED_INT:
- m_idata.resize(nbIndex*sizeof(quint16));
+ case TypeU32:
+ m_idata.resize(nbIndex*sizeof(quint32));
 break;
 default:
 break;
 }
+ memset((void*)m_idata.constData(), 0, m_idata.size());
+}
+
+bool Geometry::compare(const Geometry *other) const
+{
+ // this == other: attributes and stride can be different
+ if (!other)
+ return false;
+ if (stride() != other->stride())
+ return false;
+ return attributes() == other->attributes();
 }
 
 TexturedGeometry::TexturedGeometry()
 : Geometry()
 , nb_tex(0)
+ , geo_rect(-1, 1, 2, -2) // (-1, -1, 2, 2) flip y
 {
 setVertexCount(4);
 a = QVector<Attribute>()
- << Attribute(TypeFloat, 2, 0)
- << Attribute(TypeFloat, 2, 2*sizeof(float))
+ << Attribute(TypeF32, 2, 0)
+ << Attribute(TypeF32, 2, 2*sizeof(float))
 ;
 setTextureCount(1);
 }
 
 void TexturedGeometry::setTextureCount(int value)
 {
- if (value < 1)
- value = 1;
 if (value == nb_tex)
 return;
+ texRect.resize(value);
 nb_tex = value;
- allocate(vertexCount());
- if (a.size()-1 < value) { // the first is position
- for (int i = a.size()-1; i < value; ++i)
- a << Attribute(TypeFloat, 2, (i+1)* 2*sizeof(float));
- } else {
- a.resize(value + 1);
- }
 }
 
 int TexturedGeometry::textureCount() const
@@ -121,14 +228,14 @@
 
 void TexturedGeometry::setGeometryPoint(int index, const QPointF &p)
 {
- float *v = (float*)(m_vdata.data() + index*stride());
+ float *v = (float*)(m_vdata.constData() + index*stride());
 *v = p.x();
 *(v+1) = p.y();
 }
 
 void TexturedGeometry::setTexturePoint(int index, const QPointF &tp, int texIndex)
 {
- float *v = (float*)(m_vdata.data() + index*stride() + (texIndex+1)*2*sizeof(float));
+ float *v = (float*)(m_vdata.constData() + index*stride() + (texIndex+1)*2*sizeof(float));
 *v = tp.x();
 *(v+1) = tp.y();
 }
@@ -137,7 +244,7 @@
 {
 setPoint(0, r.topLeft(), tr.topLeft(), texIndex);
 setPoint(1, r.bottomLeft(), tr.bottomLeft(), texIndex);
- switch (primitiveType()) {
+ switch (primitive()) {
 case TriangleStrip:
 setPoint(2, r.topRight(), tr.topRight(), texIndex);
 setPoint(3, r.bottomRight(), tr.bottomRight(), texIndex);
@@ -155,46 +262,146 @@
 
 void TexturedGeometry::setGeometryRect(const QRectF &r)
 {
- setGeometryPoint(0, r.topLeft());
- setGeometryPoint(1, r.bottomLeft());
- switch (primitiveType()) {
- case TriangleStrip:
- setGeometryPoint(2, r.topRight());
- setGeometryPoint(3, r.bottomRight());
- break;
- case TriangleFan:
- setGeometryPoint(3, r.topRight());
- setGeometryPoint(2, r.bottomRight());
- break;
- case Triangles:
- break;
- default:
- break;
- }
+ geo_rect = r;
 }
 
 void TexturedGeometry::setTextureRect(const QRectF &tr, int texIndex)
 {
- setTexturePoint(0, tr.topLeft(), texIndex);
- setTexturePoint(1, tr.bottomLeft(), texIndex);
- switch (primitiveType()) {
+ if (texRect.size() <= texIndex)
+ texRect.resize(texIndex+1);
+ texRect[texIndex] = tr;
+}
+
+const QVector<Attribute>& TexturedGeometry::attributes() const
+{
+ return a;
+}
+
+void TexturedGeometry::create()
+{
+ allocate(vertexCount());
+ if (a.size()-1 < textureCount()) { // the first is position
+ for (int i = a.size()-1; i < textureCount(); ++i)
+ a << Attribute(TypeF32, 2, int((i+1)* 2*sizeof(float)));
+ } else {
+ a.resize(textureCount() + 1);
+ }
+
+ setGeometryPoint(0, geo_rect.topLeft());
+ setGeometryPoint(1, geo_rect.bottomLeft());
+ switch (primitive()) {
 case TriangleStrip:
- setTexturePoint(2, tr.topRight(), texIndex);
- setTexturePoint(3, tr.bottomRight(), texIndex);
+ setGeometryPoint(2, geo_rect.topRight());
+ setGeometryPoint(3, geo_rect.bottomRight());
 break;
 case TriangleFan:
- setTexturePoint(3, tr.topRight(), texIndex);
- setTexturePoint(2, tr.bottomRight(), texIndex);
+ setGeometryPoint(3, geo_rect.topRight());
+ setGeometryPoint(2, geo_rect.bottomRight());
 break;
 case Triangles:
 break;
 default:
 break;
 }
+
+ for (int i = 0; i < texRect.size(); ++i) {
+ const QRectF tr = texRect[i];
+ setTexturePoint(0, tr.topLeft(), i);
+ setTexturePoint(1, tr.bottomLeft(), i);
+ switch (primitive()) {
+ case TriangleStrip:
+ setTexturePoint(2, tr.topRight(), i);
+ setTexturePoint(3, tr.bottomRight(), i);
+ break;
+ case TriangleFan:
+ setTexturePoint(3, tr.topRight(), i);
+ setTexturePoint(2, tr.bottomRight(), i);
+ break;
+ case Triangles:
+ break;
+ default:
+ break;
+ }
+ }
 }
 
-const QVector<Attribute>& TexturedGeometry::attributes() const
+
+Sphere::Sphere()
+ : TexturedGeometry()
+ , r(1)
 {
- return a;
+ setPrimitive(Triangles);
+ setResolution(128, 128);
+ a = QVector<Attribute>()
+ << Attribute(TypeF32, 3, 0)
+ << Attribute(TypeF32, 2, 3*sizeof(float))
+ ;
+}
+
+void Sphere::setResolution(int w, int h)
+{
+ ru = w;
+ rv = h;
+ setVertexCount((ru+1)*(rv+1));
+}
+
+void Sphere::setRadius(float value)
+{
+ r = value;
+}
+
+float Sphere::radius() const
+{
+ return r;
+}
+
+void Sphere::create()
+{
+ allocate(vertexCount(), ru*rv*3*2); // quads * 2 triangles,
+ if (a.size()-1 < nb_tex) { // the first is position
+ for (int i = a.size()-1; i < nb_tex; ++i)
+ a << Attribute(TypeF32, 2, 3*sizeof(float) + int(i* 2*sizeof(float)));
+ } else {
+ a.resize(nb_tex + 1);
+ }
+
+ // TODO: use geo_rect?
+ float *vd = (float*)m_vdata.constData();
+ const float dTheta = M_PI*2.0/float(ru);
+ const float dPhi = M_PI/float(rv);
+ //const float du = 1.0f/float(ru);
+ //const float dv = 1.0f/float(rv);
+ for (int lat = 0; lat <= rv; ++lat) {
+ const float phi = M_PI_2 - float(lat)*dPhi;
+ const float cosPhi = qCos(phi);
+ const float sinPhi = qSin(phi);
+ //const float v = 1.0f - float(lat)*dv; // flip y?
+ for (int lon = 0; lon <= ru; ++lon) {
+ const float theta = float(lon)*dTheta;
+ const float cosTheta = qCos(theta);
+ const float sinTheta = qSin(theta);
+ //const float u = float(lon) * du;
+ *vd++ = r*cosPhi*cosTheta;//2.0*float(lon)/float(ru) -1.0;//
+ *vd++ = r*sinPhi;//2.0*float(lat)/float(rv)-1.0;//
+ *vd++ = r*cosPhi*sinTheta;
+ for (int i = 0; i < nb_tex; ++i) {
+ *vd++ = texRect[i].x()+texRect[i].width()/float(ru) * float(lon);
+ *vd++ = texRect[i].y()+texRect[i].height()/float(rv) * float(lat);
+ }
+ }
+ }
+ // create index data
+ if (m_icount > 0) {
+ int idx = 0;
+ for (int lat = 0; lat < rv; ++lat) {
+ for (int lon = 0; lon < ru; ++lon) {
+ const int ring = lat*(ru+1) + lon;
+ const int ringNext = ring + ru+1;
+ setIndexValue(idx, ring, ringNext, ring+1);
+ setIndexValue(idx+3, ringNext, ringNext+1, ring+1);
+ idx += 6;
+ }
+ }
+ }
 }
 } //namespace QtAV

QtAV-1.11.0.tar.gz/src/opengl/GeometryRenderer.cpp -> QtAV-1.12.0.tar.gz/src/opengl/GeometryRenderer.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2016)
 
@@ -18,124 +18,259 @@
 License along with this library; if not, write to the Free Software
 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 ******************************************************************************/
-#include "GeometryRenderer.h"
-
+#include "QtAV/GeometryRenderer.h"
+#include "opengl/OpenGLHelper.h"
+#if QT_VERSION >= QT_VERSION_CHECK(5, 0, 0)
+#define QGLF(f) QOpenGLContext::currentContext()->functions()->f
+#else
+#define QGLF(f) QGLFunctions(NULL).f
+#endif
 namespace QtAV {
 
 GeometryRenderer::GeometryRenderer()
- : program(NULL)
- , try_vbo(true)
- , try_vao(true)
+ : g(NULL)
+ , features_(kVBO|kIBO|kVAO|kMapBuffer)
+ , vbo_size(0)
+ , ibo_size(0)
+ , ibo(QOpenGLBuffer::IndexBuffer)
+ , stride(0)
 {
+ static bool disable_ibo = qgetenv("QTAV_NO_IBO").toInt() > 0;
+ setFeature(kIBO, !disable_ibo);
 static bool disable_vbo = qgetenv("QTAV_NO_VBO").toInt() > 0;
- try_vbo = !disable_vbo;
+ setFeature(kVBO, !disable_vbo);
 static bool disable_vao = qgetenv("QTAV_NO_VAO").toInt() > 0;
- try_vao = !disable_vao;
+ setFeature(kVAO, !disable_vao);
+}
+
+void GeometryRenderer::setFeature(int f, bool on)
+{
+ if (on)
+ features_ |= f;
+ else
+ features_ ^= f;
+}
+
+void GeometryRenderer::setFeatures(int value)
+{
+ features_ = value;
+}
+
+int GeometryRenderer::features() const
+{
+ return features_;
+}
+
+int GeometryRenderer::actualFeatures() const
+{
+ int f = 0;
+ if (vbo.isCreated())
+ f |= kVBO;
+ if (ibo.isCreated())
+ f |= kIBO;
+#if QT_VAO
+ if (vao.isCreated())
+ f |= kVAO;
+#endif
+ return f;
 }
 
-void GeometryRenderer::setShaderProgram(QOpenGLShaderProgram *sp)
+bool GeometryRenderer::testFeatures(int value) const
 {
- program = sp;
+ return !!(features() & value);
 }
 
-bool GeometryRenderer::updateBuffers(Geometry *g)
+void GeometryRenderer::updateGeometry(Geometry *geo)
 {
+ g = geo;
 if (!g) {
+ ibo.destroy();
 vbo.destroy();
 #if QT_VAO
 vao.destroy();
 #endif
- return true;
+ vbo_size = 0;
+ ibo_size = 0;
+ return;
 }
- if (!try_vbo)
- return false;
-#if QT_VAO
- if (try_vao) {
- qDebug("updating vao...");
- if (!vao.isCreated()) {
- if (!vao.create()) {
- try_vao = false;
- qDebug("VAO is not supported");
+ static int support_map = -1;
+ if (support_map < 0) {
+ static const char* ext[] = { "GL_OES_mapbuffer", NULL};
+ if (OpenGLHelper::isOpenGLES()) {
+ support_map = QOpenGLContext::currentContext()->format().majorVersion() > 2 ||
+ OpenGLHelper::hasExtension(ext);
+ } else {
+ support_map = 1;
+ }
+ }
+ if (testFeatures(kIBO) && !ibo.isCreated()) {
+ if (g->indexCount() > 0) {
+ qDebug("creating IBO...");
+ if (!ibo.create())
+ qDebug("IBO create error");
+ }
+ }
+ if (ibo.isCreated()) {
+ ibo.bind();
+ const int bs = g->indexDataSize();
+ if (bs == ibo_size) {
+ void * p = NULL;
+ if (support_map && testFeatures(kMapBuffer))
+ p = ibo.map(QOpenGLBuffer::WriteOnly);
+ if (p) {
+ memcpy(p, g->constIndexData(), bs);
+ ibo.unmap();
+ } else {
+ ibo.write(0, g->constIndexData(), bs);
 }
+ } else {
+ ibo.allocate(g->indexData(), bs); // TODO: allocate NULL and then map or BufferSubData?
+ ibo_size = bs;
 }
+ ibo.release();
 }
- QOpenGLVertexArrayObject::Binder vao_bind(&vao);
- Q_UNUSED(vao_bind);
-#endif
- if (!vbo.isCreated()) {
- if (!vbo.create()) {
- try_vbo = false; // not supported by OpenGL
- try_vao = false; // also disable VAO. destroy?
- qWarning("VBO is not supported");
- return false;
+ if (testFeatures(kVBO) && !vbo.isCreated()) {
+ qDebug("creating VBO...");
+ if (!vbo.create())
+ qWarning("VBO create error");
+ }
+ if (vbo.isCreated()) {
+ vbo.bind();
+ const int bs = g->vertexCount()*g->stride();
+ /* Notes from https://www.opengl.org/sdk/docs/man/html/glBufferSubData.xhtml
+ When replacing the entire data store, consider using glBufferSubData rather than completely recreating the data store with glBufferData. This avoids the cost of reallocating the data store.
+ */
+ if (bs == vbo_size) { // vbo.size() error 0x501 on rpi, and query gl value can be slow
+ void* p = NULL;
+ if (support_map && testFeatures(kMapBuffer))
+ p = vbo.map(QOpenGLBuffer::WriteOnly);
+ if (p) {
+ memcpy(p, g->constVertexData(), bs);
+ vbo.unmap();
+ } else {
+ vbo.write(0, g->constVertexData(), bs);
+ vbo_size = bs;
+ }
+ } else {
+ vbo.allocate(g->vertexData(), bs);
 }
+ vbo.release();
 }
- qDebug("updating vbo...");
- vbo.bind(); //check here
- vbo.allocate(g->vertexData(), g->vertexCount()*g->stride());
 #if QT_VAO
- if (try_vao) {
+ if (stride == g->stride() && attrib == g->attributes())
+ return;
+ stride = g->stride();
+ attrib = g->attributes();
+
+ if (testFeatures(kVAO) && !vao.isCreated()) {
+ qDebug("creating VAO...");
+ if (!vao.create())
+ qDebug("VAO create error");
+ }
+ qDebug("vao updated");
+ if (vao.isCreated()) // can not use vao binder because it will create a vao if necessary
+ vao.bind();
+// can set data before vao bind
+ if (!vao.isCreated())
+ return;
+ qDebug("geometry attributes changed, rebind vao...");
+ // call once is enough if no feature and no geometry attribute is changed
+ if (vbo.isCreated()) {
+ vbo.bind();
 for (int an = 0; an < g->attributes().size(); ++an) {
 // FIXME: assume bind order is 0,1,2...
 const Attribute& a = g->attributes().at(an);
- program->setAttributeBuffer(an, a.type(), a.offset(), a.tupleSize(), g->stride());
- program->enableAttributeArray(an); //TODO: in setActiveShader
+ QGLF(glVertexAttribPointer(an, a.tupleSize(), a.type(), a.normalize(), g->stride(), reinterpret_cast<const void *>(qptrdiff(a.offset())))); //TODO: in setActiveShader
+ QGLF(glEnableVertexAttribArray(an));
 }
- }
+ vbo.release(); // unbind after vao unbind? http://www.zwqxin.com/archives/opengl/vao-and-vbo-stuff.html
+ } // TODO: bind pointers if vbo is disabled
+ // bind ibo to vao thus no bind is required later
+ if (ibo.isCreated())// if not bind here, glDrawElements(...,NULL) crashes and must use ibo data ptr, why?
+ ibo.bind();
+ vao.release();
+ if (ibo.isCreated())
+ ibo.release();
 #endif
- vbo.release();
- return true;
+ qDebug("geometry updated");
 }
 
-void GeometryRenderer::bindBuffers(Geometry *g)
+void GeometryRenderer::bindBuffers()
 {
+ bool bind_vbo = vbo.isCreated();
+ bool bind_ibo = ibo.isCreated();
+ bool setv_skip = false;
 #if QT_VAO
- if (try_vao && vao.isCreated()) {
- vao.bind();
- return;
+ if (vao.isCreated()) {
+ vao.bind(); // vbo, ibo is ok now
+ setv_skip = bind_vbo;
+ bind_vbo = false;
+ bind_ibo = false;
 }
 #endif
- if (try_vbo && vbo.isCreated()) {
+ //qDebug("bind ibo: %d vbo: %d; set v: %d", bind_ibo, bind_vbo, !setv_skip);
+ if (bind_ibo)
+ ibo.bind();
+ // no vbo: set vertex attributes
+ // has vbo, no vao: bind vbo & set vertex attributes
+ // has vbo, has vao: skip
+ if (setv_skip)
+ return;
+ if (!g)
+ return;
+ const char* vdata = static_cast<const char*>(g->vertexData());
+ if (bind_vbo) {
 vbo.bind();
- // normalized
- for (int an = 0; an < g->attributes().size(); ++an) {
- const Attribute& a = g->attributes().at(an);
- program->setAttributeBuffer(an, a.type(), a.offset(), a.tupleSize(), g->stride());
- program->enableAttributeArray(an); //TODO: in setActiveShader
- }
- } else {
- for (int an = 0; an < g->attributes().size(); ++an) {
- const Attribute& a = g->attributes().at(an);
- program->setAttributeArray(an, a.type(), (const char*)g->vertexData() + a.offset(), a.tupleSize(), g->stride());
- program->enableAttributeArray(an); //TODO: in setActiveShader
- }
+ vdata = NULL;
+ }
+ for (int an = 0; an < g->attributes().size(); ++an) {
+ const Attribute& a = g->attributes().at(an);
+ QGLF(glVertexAttribPointer(an, a.tupleSize(), a.type(), a.normalize(), g->stride(), vdata + a.offset()));
+ QGLF(glEnableVertexAttribArray(an)); //TODO: in setActiveShader
 }
 }
 
-void GeometryRenderer::unbindBuffers(Geometry *g)
+void GeometryRenderer::unbindBuffers()
 {
+ bool unbind_vbo = vbo.isCreated();
+ bool unbind_ibo = ibo.isCreated();
+ bool unsetv_skip = false;
 #if QT_VAO
- if (try_vao && vao.isCreated()) {
+ if (vao.isCreated()) {
 vao.release();
- return;
+ unsetv_skip = unbind_vbo;
+ unbind_vbo = false;
+ unbind_ibo = false;
 }
 #endif //QT_VAO
- for (int an = 0; an < g->attributes().size(); ++an) {
- program->disableAttributeArray(an); //TODO: in setActiveShader
- }
+ //qDebug("unbind ibo: %d vbo: %d; unset v: %d", unbind_ibo, unbind_vbo, !unsetv_skip);
+ if (unbind_ibo)
+ ibo.release();
 // release vbo. qpainter is affected if vbo is bound
- if (try_vbo && vbo.isCreated()) {
+ if (unbind_vbo)
 vbo.release();
+ // no vbo: disable vertex attributes
+ // has vbo, no vao: unbind vbo & set vertex attributes
+ // has vbo, has vao: skip
+ if (unsetv_skip)
+ return;
+ if (!g)
+ return;
+ for (int an = 0; an < g->attributes().size(); ++an) {
+ QGLF(glDisableVertexAttribArray(an));
 }
 }
 
-void GeometryRenderer::render(Geometry *g)
+void GeometryRenderer::render()
 {
+ if (!g)
+ return;
+ bindBuffers();
 if (g->indexCount() > 0) {
- // IBO
-
+ DYGL(glDrawElements(g->primitive(), g->indexCount(), g->indexType(), ibo.isCreated() ? NULL : g->indexData())); // null: data in vao or ibo. not null: data in memory
 } else {
- DYGL(glDrawArrays(g->primitiveType(), 0, g->vertexCount()));
+ DYGL(glDrawArrays(g->primitive(), 0, g->vertexCount()));
 }
+ unbindBuffers();
 }
 } //namespace QtAV

QtAV-1.11.0.tar.gz/src/opengl/OpenGLHelper.cpp -> QtAV-1.12.0.tar.gz/src/opengl/OpenGLHelper.cpp Changed

@@ -55,7 +55,7 @@
 
 bool useDeprecatedFormats()
 {
- static int v = qgetenv("QTAV_GL_DEPRECATED").toInt() == 1;
+ static bool v = qgetenv("QTAV_GL_DEPRECATED").toInt() == 1;
 return v;
 }
 
@@ -87,6 +87,8 @@
 // we can't check GLSLVersion() here because it the actually version used can be defined by "#version"
 h += "#if __VERSION__ < 130\n"
 "#define texture texture2D\n"
+ "#else\n"
+ "#define texture2D texture\n"
 "#endif // < 130\n"
 ;
 }
@@ -194,9 +196,13 @@
 {
 #ifdef QT_OPENGL_DYNAMIC
 QOpenGLContext *ctx = QOpenGLContext::currentContext();
+ if (ctx)
+ return ctx->isOpenGLES();
+ if (qstrcmp(qApp->metaObject()->className(), "QCoreApplication") == 0) // QGuiApplication is required by QOpenGLContext::openGLModuleType
+ return false;
 // desktop openGLModuleType() can create es compatible context, so prefer QOpenGLContext::isOpenGLES().
 // qApp->testAttribute(Qt::AA_UseOpenGLES) is what user requested, but not the result can be different. reproduce: dygl set AA_ShareOpenGLContexts|AA_UseOpenGLES, fallback to desktop (why?)
- return ctx ? ctx->isOpenGLES() : QOpenGLContext::openGLModuleType() != QOpenGLContext::LibGL;
+ return QOpenGLContext::openGLModuleType() != QOpenGLContext::LibGL;
 #endif //QT_OPENGL_DYNAMIC
 #ifdef QT_OPENGL_ES_2
 return true;
@@ -271,6 +277,8 @@
 NULL
 };
 support = hasExtension(exts);
+ if (QOpenGLContext::currentContext()->format().majorVersion() > 2)
+ support = true;
 pbo_checked = true;
 return support;
 }
@@ -296,11 +304,11 @@
 { GL_LUMINANCE_ALPHA, GL_LUMINANCE_ALPHA, GL_UNSIGNED_BYTE}, //2 x 8 fallback to ra
 {0,0,0},
 };
-static const gl_param_t gl_param_desktop[] = {
+static const gl_param_t gl_param_3r16[] = {
 {GL_R8, GL_RED, GL_UNSIGNED_BYTE}, // 1 x 8
- {GL_RG, GL_RG, GL_UNSIGNED_BYTE}, // 2 x 8 //FIXME: OSX error in hasRG(), internal format GL_RG8 is ok
- {GL_RGB, GL_RGB, GL_UNSIGNED_BYTE}, // 3 x 8
- {GL_RGBA, GL_RGBA, GL_UNSIGNED_BYTE}, // 4 x 8
+ {GL_RG8, GL_RG, GL_UNSIGNED_BYTE}, // 2 x 8
+ {GL_RGB8, GL_RGB, GL_UNSIGNED_BYTE}, // 3 x 8
+ {GL_RGBA8, GL_RGBA, GL_UNSIGNED_BYTE}, // 4 x 8
 {GL_R16, GL_RED, GL_UNSIGNED_SHORT}, // 1 x 16
 {GL_RG16, GL_RG, GL_UNSIGNED_SHORT}, // 2 x 16
 {GL_RGB16, GL_RGB, GL_UNSIGNED_SHORT}, // 3 x 16
@@ -315,7 +323,7 @@
 {GL_RG, GL_RG, GL_UNSIGNED_BYTE}, // 2 x 8
 {0,0,0},
 };
-static const gl_param_t gl_param_es3[] = {
+static const gl_param_t gl_param_es3rg8[] = {
 {GL_R8, GL_RED, GL_UNSIGNED_BYTE}, // 1 x 8
 {GL_RG8, GL_RG, GL_UNSIGNED_BYTE}, // 2 x 8
 {GL_RGB8, GL_RGB, GL_UNSIGNED_BYTE}, // 3 x 8
@@ -340,21 +348,26 @@
 qWarning("%s: current context is null", __FUNCTION__);
 return false;
 }
- if (!gl().GetTexLevelParameteriv) {
- qDebug("Do not support glGetTexLevelParameteriv. test_gl_param returns false");
- return false;
- }
 GLuint tex;
 DYGL(glGenTextures(1, &tex));
 DYGL(glBindTexture(GL_TEXTURE_2D, tex));
+ while (DYGL(glGetError()) != GL_NO_ERROR) {}
 DYGL(glTexImage2D(GL_TEXTURE_2D, 0, gp.internal_format, 64, 64, 0, gp.format, gp.type, NULL));
+ if (DYGL(glGetError()) != GL_NO_ERROR) {
+ DYGL(glDeleteTextures(1, &tex));
+ return false;
+ }
+ if (!gl().GetTexLevelParameteriv) {
+ qDebug("Do not support glGetTexLevelParameteriv. test_gl_param returns false");
+ DYGL(glDeleteTextures(1, &tex));
+ return false;
+ }
 GLint param = 0;
 //GL_PROXY_TEXTURE_2D and no glGenTextures?
 #ifndef GL_TEXTURE_INTERNAL_FORMAT //only in desktop
 #define GL_TEXTURE_INTERNAL_FORMAT 0x1003
 #endif
 gl().GetTexLevelParameteriv(GL_TEXTURE_2D, 0, GL_TEXTURE_INTERNAL_FORMAT, &param);
- // TODO: check glGetError()?
 if (param != gp.internal_format) {
 qDebug("Do not support texture internal format: %#x (result %#x)", gp.internal_format, param);
 DYGL(glDeleteTextures(1, &tex));
@@ -392,13 +405,13 @@
 static int has_rg = -1;
 if (has_rg >= 0)
 return !!has_rg;
- qDebug("check desktop rg: %#X", gl_param_desktop[1].internal_format);
- if (test_gl_param(gl_param_desktop[1])) {
+ qDebug("check gl3 rg: %#X", gl_param_3r16[1].internal_format);
+ if (test_gl_param(gl_param_3r16[1])) {
 has_rg = 1;
 return true;
 }
- qDebug("check es3 rg: %#X", gl_param_es3[1].internal_format);
- if (test_gl_param(gl_param_es3[1])) {
+ qDebug("check es3 rg: %#X", gl_param_es3rg8[1].internal_format);
+ if (test_gl_param(gl_param_es3rg8[1])) {
 has_rg = 1;
 return true;
 }
@@ -427,31 +440,31 @@
 return gp;
 bool has_16 = false;
 // [4] is always available
- if (test_gl_param(gl_param_desktop[4], &has_16)) {
+ if (test_gl_param(gl_param_3r16[4], &has_16)) {
 if (has_16 && depth16BitTexture() == 16)
- gp = (gl_param_t*)gl_param_desktop;
+ gp = (gl_param_t*)gl_param_3r16;
 else
 gp = (gl_param_t*)gl_param_desktop_fallback;
 has_16_tex = has_16;
 if (!useDeprecatedFormats()) {
- qDebug("using gl_param_desktop%s", gp == gl_param_desktop? "" : "_fallback");
+ qDebug("using gl_param_%s", gp == gl_param_3r16? "3r16" : "desktop_fallback");
 return gp;
 }
- } else if (test_gl_param(gl_param_es3[4], &has_16)) { //3.0 will fail because no glGetTexLevelParameteriv
- gp = (gl_param_t*)gl_param_es3;
+ } else if (test_gl_param(gl_param_es3rg8[4], &has_16)) { //3.0 will fail because no glGetTexLevelParameteriv
+ gp = (gl_param_t*)gl_param_es3rg8;
 has_16_tex = has_16;
 if (!useDeprecatedFormats()) {
- qDebug("using gl_param_es3");
+ qDebug("using gl_param_es3rg8");
 return gp;
 }
 } else if (isOpenGLES()) {
 if (QOpenGLContext::currentContext()->format().majorVersion() > 2)
- gp = (gl_param_t*)gl_param_es3; //for 3.0
+ gp = (gl_param_t*)gl_param_es3rg8; //for 3.0
 else if (hasRG())
 gp = (gl_param_t*)gl_param_es2rg;
 has_16_tex = has_16;
 if (gp && !useDeprecatedFormats()) {
- qDebug("using gl_param_%s", gp == gl_param_es3 ? "es3" : "es2rg");
+ qDebug("using gl_param_%s", gp == gl_param_es3rg8 ? "es3rg8" : "es2rg");
 return gp;
 }
 }
@@ -562,19 +575,19 @@
 };
 Q_UNUSED(pixfmt_to_gles);
 static const fmt_entry pixfmt_to_desktop[] = {
- {VideoFormat::Format_BGRA32, GL_RGBA, GL_BGRA, GL_UNSIGNED_BYTE }, //bgra bgra works on win but not osx
+ {VideoFormat::Format_BGRA32, GL_RGBA, GL_BGRA, GL_UNSIGNED_BYTE }, //bgra bgra works on win but not macOS
 {VideoFormat::Format_RGB32, GL_RGBA, GL_BGRA, GL_UNSIGNED_BYTE }, //FIXMEL endian check
 //{VideoFormat::Format_BGRA32, GL_RGBA, GL_RGBA, GL_UNSIGNED_BYTE }, //{2,1,0,3}
 //{VideoFormat::Format_BGR24, GL_RGB, GL_BGR, GL_UNSIGNED_BYTE }, //{0,1,2,3}
- #ifdef GL_UNSIGNED_SHORT_5_6_5_REV
+#ifdef GL_UNSIGNED_SHORT_5_6_5_REV
 {VideoFormat::Format_BGR565, GL_RGB, GL_RGB, GL_UNSIGNED_SHORT_5_6_5_REV}, // es error, use channel map
- #endif
- #ifdef GL_UNSIGNED_SHORT_1_5_5_5_REV
+#endif
+#ifdef GL_UNSIGNED_SHORT_1_5_5_5_REV
 {VideoFormat::Format_RGB555, GL_RGBA, GL_BGRA, GL_UNSIGNED_SHORT_1_5_5_5_REV},
- #endif
- #ifdef GL_UNSIGNED_SHORT_1_5_5_5_REV
+#endif
+#ifdef GL_UNSIGNED_SHORT_1_5_5_5_REV
 {VideoFormat::Format_BGR555, GL_RGBA, GL_RGBA, GL_UNSIGNED_SHORT_1_5_5_5_REV},
- #endif
+#endif
 // TODO: BE formats not implemeted
 {VideoFormat::Format_RGB48, GL_RGB, GL_RGB, GL_UNSIGNED_SHORT }, //TODO: they are not work for ANGLE, and rgb16 works on desktop gl, so remove these lines to use rgb16?
 {VideoFormat::Format_RGB48LE, GL_RGB, GL_RGB, GL_UNSIGNED_SHORT },
@@ -594,7 +607,7 @@
 pixfmt_gl_entry = pixfmt_to_gles;
 // Very special formats, for which OpenGL happens to have direct support
 static const fmt_entry pixfmt_gl_base[] = {
- {VideoFormat::Format_RGBA32, GL_RGBA, GL_RGBA, GL_UNSIGNED_BYTE }, // only tested for osx, win, angle
+ {VideoFormat::Format_RGBA32, GL_RGBA, GL_RGBA, GL_UNSIGNED_BYTE }, // only tested for macOS, win, angle
 {VideoFormat::Format_RGB24, GL_RGB, GL_RGB, GL_UNSIGNED_BYTE },
 {VideoFormat::Format_RGB565, GL_RGB, GL_RGB, GL_UNSIGNED_SHORT_5_6_5},
 {VideoFormat::Format_BGR32, GL_BGRA, GL_BGRA, GL_UNSIGNED_BYTE }, //rgba(tested) or abgr, depending on endian
@@ -648,9 +661,9 @@
 GLenum *d_t = data_type;
 gl_param_t* gp = (gl_param_t*)get_gl_param();
 const int nb_planes = fmt.planeCount();
- if (gp == gl_param_desktop && (
- nb_planes == 2 // nv12 UV plane is 16bit, but we use rg
- || (OpenGLHelper::depth16BitTexture() == 16 && OpenGLHelper::has16BitTexture() && fmt.isBigEndian() && fmt.bitsPerComponent() > 8) // 16bit texture does not support be channel now
+ if (gp == gl_param_3r16 && (
+ //nb_planes == 2 || // nv12 UV plane is 16bit, but we use rg
+ (OpenGLHelper::depth16BitTexture() == 16 && OpenGLHelper::has16BitTexture() && fmt.isBigEndian() && fmt.bitsPerComponent() > 8) // 16bit texture does not support be channel now
 )) {
 gp = (gl_param_t*)gl_param_desktop_fallback;
 qDebug("desktop_fallback for %s", nb_planes == 2 ? "bi-plane format" : "16bit big endian channel");
@@ -677,7 +690,8 @@
 
 // TODO: format + datatype? internal format == format?
 //https://www.khronos.org/registry/gles/extensions/EXT/EXT_texture_format_BGRA8888.txt
-int bytesOfGLFormat(GLenum format, GLenum dataType)
+// TODO: special format size, or componentsize(dataType)*components(format)
+int bytesOfGLFormat(GLenum format, GLenum dataType) // TODO: rename bytesOfTexel
 {
 int component_size = 0;
 switch (dataType) {
@@ -721,49 +735,30 @@
 }
 switch (format) {
 case GL_RED:
- case GL_R8:
- case GL_R16: //?
+ case GL_LUMINANCE:
+ case GL_ALPHA:
 return component_size;
 case GL_RG:
- case GL_RG8:
- case GL_RG16: //?
+ case GL_LUMINANCE_ALPHA:
 return 2*component_size;
 #ifdef GL_YCBCR_422_APPLE
- case GL_YCBCR_422_APPLE:
+ case GL_YCBCR_422_APPLE:
 return 2;
 #endif
 #ifdef GL_RGB_422_APPLE
- case GL_RGB_422_APPLE:
+ case GL_RGB_422_APPLE:
 return 2;
 #endif
+#ifdef GL_BGR //ifndef GL_ES
+ case GL_BGR:
+#endif
+ case GL_RGB:
+ return 3*component_size;
 #ifdef GL_BGRA //ifndef GL_ES
 case GL_BGRA:
 #endif
 case GL_RGBA:
- case GL_RGBA8:
- case GL_RGBA16:
 return 4*component_size;
-#ifdef GL_BGR //ifndef GL_ES
- case GL_BGR:
-#endif
- case GL_RGB:
- case GL_RGB8:
- case GL_RGB16:
- return 3*component_size;
- case GL_LUMINANCE_ALPHA:
- // mpv returns 2
- return 2*component_size;
- case GL_LUMINANCE:
- case GL_ALPHA:
- return 1*component_size;
-#ifdef GL_LUMINANCE16
- case GL_LUMINANCE16:
- return 2*component_size;
-#endif //GL_LUMINANCE16
-#ifdef GL_ALPHA16
- case GL_ALPHA16:
- return 2*component_size;
-#endif //GL_ALPHA16
 default:
 qWarning("bytesOfGLFormat - Unknown format %u", format);
 return 1;

QtAV-1.11.0.tar.gz/src/opengl/OpenGLVideo.cpp -> QtAV-1.12.0.tar.gz/src/opengl/OpenGLVideo.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2014)
 
@@ -20,6 +20,7 @@
 ******************************************************************************/
 
 #include "QtAV/OpenGLVideo.h"
+#include <QtCore/QThreadStorage>
 #include <QtGui/QColor>
 #if QT_VERSION >= QT_VERSION_CHECK(5, 0, 0)
 #include <QtGui/QGuiApplication>
@@ -29,7 +30,7 @@
 #include "QtAV/SurfaceInterop.h"
 #include "QtAV/VideoShader.h"
 #include "ShaderManager.h"
-#include "opengl/GeometryRenderer.h"
+#include "QtAV/GeometryRenderer.h"
 #include "opengl/OpenGLHelper.h"
 #include "utils/Logger.h"
 
@@ -44,9 +45,13 @@
 , manager(0)
 , material(new VideoMaterial())
 , material_type(0)
+ , norm_viewport(true)
 , update_geo(true)
 , tex_target(0)
 , valiad_tex_width(1.0)
+ , mesh_type(OpenGLVideo::RectMesh)
+ , geometry(NULL)
+ , gr(NULL)
 , user_shader(NULL)
 {
 }
@@ -55,11 +60,16 @@
 delete material;
 material = 0;
 }
+ delete geometry;
+#if QT_VERSION < QT_VERSION_CHECK(5, 0, 0) || !defined(Q_COMPILER_LAMBDA)
+ delete gr;
+#endif
 }
 
 void resetGL() {
 ctx = 0;
- gr.updateBuffers(NULL);
+ if (gr)
+ gr->updateGeometry(NULL);
 if (!manager)
 return;
 manager->setParent(0);
@@ -71,29 +81,29 @@
 }
 }
 // update geometry(vertex array) set attributes or bind VAO/VBO.
- void bindAttributes(VideoShader* shader, const QRectF& t, const QRectF& r);
- void unbindAttributes(VideoShader*) {
- gr.unbindBuffers(&geometry);
- }
+ void updateGeometry(VideoShader* shader, const QRectF& t, const QRectF& r);
 public:
 QOpenGLContext *ctx;
 ShaderManager *manager;
 VideoMaterial *material;
 qint64 material_type;
+ bool norm_viewport;
+ bool has_a;
 bool update_geo;
 int tex_target;
 qreal valiad_tex_width;
 QSize video_size;
 QRectF target;
 QRectF roi; //including invalid padding width
- TexturedGeometry geometry;
- GeometryRenderer gr;
+ OpenGLVideo::MeshType mesh_type;
+ TexturedGeometry *geometry;
+ GeometryRenderer* gr;
 QRectF rect;
 QMatrix4x4 matrix;
 VideoShader *user_shader;
 };
 
-void OpenGLVideoPrivate::bindAttributes(VideoShader* shader, const QRectF &t, const QRectF &r)
+void OpenGLVideoPrivate::updateGeometry(VideoShader* shader, const QRectF &t, const QRectF &r)
 {
 // also check size change for normalizedROI computation if roi is not normalized
 const bool roi_changed = valiad_tex_width != material->validTextureWidth() || roi != r || video_size != material->frameSize();
@@ -107,7 +117,26 @@
 tex_target = shader->textureTarget();
 update_geo = true;
 }
- QRectF& target_rect = rect;
+ bool update_gr = false;
+ static QThreadStorage<bool> new_thread;
+ if (!new_thread.hasLocalData())
+ new_thread.setLocalData(true);
+ 
+ update_gr = new_thread.localData();
+ if (!gr || update_gr) { // TODO: only update VAO, not the whole GeometryRenderer
+ update_geo = true;
+ new_thread.setLocalData(false);
+ GeometryRenderer *r = new GeometryRenderer(); // local var is captured by lambda 
+ gr = r;
+#if QT_VERSION >= QT_VERSION_CHECK(5, 0, 0) && defined(Q_COMPILER_LAMBDA)
+ QObject::connect(QOpenGLContext::currentContext(), &QOpenGLContext::aboutToBeDestroyed, [r]{
+ qDebug("destroy GeometryRenderer %p", r);
+ delete r;
+ });
+#endif
+ }
+ // (-1, -1, 2, 2) must flip y
+ QRectF target_rect = norm_viewport ? QRectF(-1, 1, 2, -2) : rect;
 if (target.isValid()) {
 if (roi_changed || target != t) {
 target = t;
@@ -119,30 +148,36 @@
 update_geo = true;
 }
 }
- if (!update_geo) {
- gr.bindBuffers(&geometry);
+ if (!update_geo)
 return;
- }
+ delete geometry;
+ geometry = NULL;
+ if (mesh_type == OpenGLVideo::SphereMesh)
+ geometry = new Sphere();
+ else
+ geometry = new TexturedGeometry();
 //qDebug("updating geometry...");
 // setTextureCount may change the vertex data. Call it before setRect()
- geometry.setTextureCount(shader->textureTarget() == GL_TEXTURE_RECTANGLE ? tc : 1);
- geometry.setRect(target_rect, material->mapToTexture(0, roi));
+ qDebug() << "target rect: " << target_rect ;
+ geometry->setTextureCount(shader->textureTarget() == GL_TEXTURE_RECTANGLE ? tc : 1);
+ geometry->setGeometryRect(target_rect);
+ geometry->setTextureRect(material->mapToTexture(0, roi));
 if (shader->textureTarget() == GL_TEXTURE_RECTANGLE) {
 for (int i = 1; i < tc; ++i) {
 // tc can > planes, but that will compute chroma plane
- geometry.setTextureRect(material->mapToTexture(i, roi), i);
+ geometry->setTextureRect(material->mapToTexture(i, roi), i);
 }
 }
+ geometry->create();
 update_geo = false;
- gr.updateBuffers(&geometry);
- gr.bindBuffers(&geometry);
+ gr->updateGeometry(geometry);
 }
 
 OpenGLVideo::OpenGLVideo() {}
 
 bool OpenGLVideo::isSupported(VideoFormat::PixelFormat pixfmt)
 {
- return pixfmt != VideoFormat::Format_RGB48BE;
+ return pixfmt != VideoFormat::Format_RGB48BE && pixfmt != VideoFormat::Format_Invalid;
 }
 
 void OpenGLVideo::setOpenGLContext(QOpenGLContext *ctx)
@@ -186,7 +221,7 @@
 // TODO: what if ctx is delete?
 #if QT_VERSION >= QT_VERSION_CHECK(5, 0, 0)
 d.manager = new ShaderManager(ctx);
- QObject::connect(ctx, SIGNAL(aboutToBeDestroyed()), this, SLOT(resetGL()), Qt::DirectConnection); //direct?
+ QObject::connect(ctx, SIGNAL(aboutToBeDestroyed()), this, SLOT(resetGL()), Qt::DirectConnection); // direct to make sure there is a valid context. makeCurrent in window.aboutToBeDestroyed()?
 #else
 d.manager = new ShaderManager(this);
 #endif
@@ -227,17 +262,29 @@
 void OpenGLVideo::setCurrentFrame(const VideoFrame &frame)
 {
 d_func().material->setCurrentFrame(frame);
+ d_func().has_a = frame.format().hasAlpha();
 }
 
 void OpenGLVideo::setProjectionMatrixToRect(const QRectF &v)
 {
+ setViewport(v);
+}
+
+void OpenGLVideo::setViewport(const QRectF &r)
+{
 DPTR_D(OpenGLVideo);
- d.rect = v;
- d.matrix.setToIdentity();
- d.matrix.ortho(v);
+ d.rect = r;
+ if (d.norm_viewport) {
+ d.matrix.setToIdentity();
+ if (d.mesh_type == SphereMesh)
+ d.matrix.perspective(45, 1, 0.1, 100); // for sphere
+ } else {
+ d.matrix.setToIdentity();
+ d.matrix.ortho(r);
+ d.update_geo = true; // even true for target_rect != d.rect
+ }
 // Mirrored relative to the usual Qt coordinate system with origin in the top left corner.
 //mirrored = mat(0, 0) * mat(1, 1) - mat(0, 1) * mat(1, 0) > 0;
- d.update_geo = true; // even true for target_rect != d.rect
 if (d.ctx && d.ctx == QOpenGLContext::currentContext()) {
 DYGL(glViewport(d.rect.x(), d.rect.y(), d.rect.width(), d.rect.height()));
 }
@@ -273,9 +320,27 @@
 return d_func().user_shader;
 }
 
+void OpenGLVideo::setMeshType(MeshType value)
+{
+ DPTR_D(OpenGLVideo);
+ if (d.mesh_type == value)
+ return;
+ d.mesh_type = value;
+ d.update_geo = true;
+ if (d.mesh_type == SphereMesh && d.norm_viewport) {
+ d.matrix.setToIdentity();
+ d.matrix.perspective(45, 1, 0.1, 100); // for sphere
+ }
+}
+
+OpenGLVideo::MeshType OpenGLVideo::meshType() const
+{
+ return d_func().mesh_type;
+}
+
 void OpenGLVideo::fill(const QColor &color)
 {
- DYGL(glClearColor(color.red(), color.green(), color.blue(), color.alpha()));
+ DYGL(glClearColor(color.redF(), color.greenF(), color.blueF(), color.alphaF()));
 DYGL(glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT));
 }
 
@@ -290,26 +355,27 @@
 qDebug() << "material changed: " << VideoMaterial::typeName(d.material_type) << " => " << VideoMaterial::typeName(mt);
 d.material_type = mt;
 }
+ if (!d.material->bind()) // bind first because texture parameters(target) mapped from native buffer is unknown before it
+ return;
 VideoShader *shader = d.user_shader;
 if (!shader)
 shader = d.manager->prepareMaterial(d.material, mt); //TODO: print shader type name if changed. prepareMaterial(,sample_code, pp_code)
 shader->update(d.material);
- d.material->setDirty(false); //
 shader->program()->setUniformValue(shader->matrixLocation(), transform*d.matrix);
- d.gr.setShaderProgram(shader->program());
 // uniform end. attribute begin
- d.bindAttributes(shader, target, roi);
+ d.updateGeometry(shader, target, roi);
 // normalize?
- const bool blending = d.material->hasAlpha();
+ const bool blending = d.has_a;
 if (blending) {
 DYGL(glEnable(GL_BLEND));
- DYGL(glBlendFunc(GL_SRC_ALPHA , GL_ONE_MINUS_SRC_ALPHA));
+ gl().BlendFuncSeparate(GL_SRC_ALPHA , GL_ONE_MINUS_SRC_ALPHA, GL_SRC_ALPHA , GL_ONE_MINUS_SRC_ALPHA); //
 }
- d.gr.render(&d.geometry);
+ //if (d.mesh_type == OpenGLVideo::SphereMesh)
+ //DYGL(glEnable(GL_CULL_FACE)); // required for sphere! FIXME: broken in qml and qgvf
+ d.gr->render();
 if (blending)
 DYGL(glDisable(GL_BLEND));
 // d.shader->program()->release(); //glUseProgram(0)
- d.unbindAttributes(shader);
 d.material->unbind();
 
 Q_EMIT afterRendering();

QtAV-1.11.0.tar.gz/src/opengl/SubImagesGeometry.cpp -> QtAV-1.12.0.tar.gz/src/opengl/SubImagesGeometry.cpp Changed

@@ -120,13 +120,13 @@
 , m_w(0)
 , m_h(0)
 {
- setPrimitiveType(Geometry::Triangles);
- m_attributes << Attribute(TypeFloat, 2)
- << Attribute(TypeFloat, 2, 2*sizeof(float))
+ setPrimitive(Geometry::Triangles);
+ m_attributes << Attribute(TypeF32, 2)
+ << Attribute(TypeF32, 2, 2*sizeof(float))
 #if U8COLOR
- << Attribute(TypeUnsignedByte, 4, 4*sizeof(float), true);
+ << Attribute(TypeU8, 4, 4*sizeof(float), true);
 #else
- << Attribute(TypeFloat, 4, 4*sizeof(float));
+ << Attribute(TypeF32, 4, 4*sizeof(float));
 #endif
 }
 
@@ -141,6 +141,8 @@
 
 bool SubImagesGeometry::generateVertexData(const QRect &rect, bool useIndecies, int maxWidth)
 {
+ if (maxWidth < 0)
+ maxWidth = kMaxTexWidth;
 if (useIndecies)
 allocate(4*m_images.images.size(), 6*m_images.images.size());
 else
@@ -155,6 +157,7 @@
 int W = 0, H = 0;
 int x = 0, h = 0;
 VertexData* vd = (VertexData*)vertexData();
+ int index = 0;
 foreach (const SubImage& i, m_images.images) {
 if (x + i.stride > maxWidth && maxWidth > 0) {
 W = qMax(W, x);
@@ -165,6 +168,12 @@
 // we use w instead of stride even if we must upload stride. when maping texture coordinates and view port coordinates, we can use the visual rects instead of stride, i.e. the geometry vertices are (x, y, w, h), not (x, y, stride, h)
 m_rects_upload.append(QRect(x, H, i.stride, i.h));
 vd = SetUnnormalizedVertexData(vd, x, H, i.w, i.h, i.color, useIndecies);
+ if (useIndecies) { // TODO: set only once because it never changes, use IBO
+ const int v0 = index*4/6;
+ setIndexValue(index, v0, v0+1, v0+2);
+ setIndexValue(index+3, v0+1, v0+2, v0+3);
+ index += 6;
+ }
 x += i.w;
 h = qMax(h, i.h);
 }

QtAV-1.11.0.tar.gz/src/opengl/SubImagesGeometry.h -> QtAV-1.12.0.tar.gz/src/opengl/SubImagesGeometry.h Changed

QtAV-1.11.0.tar.gz/src/opengl/SubImagesRenderer.cpp -> QtAV-1.12.0.tar.gz/src/opengl/SubImagesRenderer.cpp Changed

@@ -1,6 +1,27 @@
+/******************************************************************************
+ QtAV: Multimedia framework based on Qt and FFmpeg
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
+
+* This file is part of QtAV (from 2016)
+
+ This library is free software; you can redistribute it and/or
+ modify it under the terms of the GNU Lesser General Public
+ License as published by the Free Software Foundation; either
+ version 2.1 of the License, or (at your option) any later version.
+
+ This library is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+******************************************************************************/
+
 #include "SubImagesRenderer.h"
 #include "opengl/SubImagesGeometry.h"
-#include "opengl/GeometryRenderer.h"
+#include "QtAV/GeometryRenderer.h"
 
 namespace QtAV {
 
@@ -45,11 +66,10 @@
 {
 if (m_geometry->setSubImages(ass) || m_rect != target) {
 m_rect = target;
- if (!m_geometry->generateVertexData(m_rect))
+ if (!m_geometry->generateVertexData(m_rect, true))
 return;
-
 uploadTexture(m_geometry);
- m_renderer->updateBuffers(m_geometry);
+ m_renderer->updateGeometry(m_geometry);
 }
 if (!m_program.isLinked()) {
 m_program.removeAllShaders();
@@ -71,18 +91,15 @@
 DYGL(glBindTexture(GL_TEXTURE_2D, m_tex));
 m_program.setUniformValue("u_Texture", 0);
 m_program.setUniformValue("u_Matrix", transform*m_mat);
- m_renderer->setShaderProgram(&m_program);
- m_renderer->bindBuffers(m_geometry);
 DYGL(glEnable(GL_BLEND));
 if (m_geometry->images().format() == SubImageSet::ASS)
 gl().BlendFuncSeparate(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA, GL_ONE, GL_ONE_MINUS_SRC_ALPHA);
 else
 gl().BlendFuncSeparate(GL_ONE, GL_ONE_MINUS_SRC_ALPHA, GL_ONE, GL_ONE_MINUS_SRC_ALPHA);
 
- m_renderer->render(m_geometry);
+ m_renderer->render();
 
 DYGL(glDisable(GL_BLEND));
- m_renderer->unbindBuffers(m_geometry);
 }
 
 void SubImagesRenderer::setProjectionMatrixToRect(const QRectF &v)

QtAV-1.11.0.tar.gz/src/opengl/VideoShader.cpp -> QtAV-1.12.0.tar.gz/src/opengl/VideoShader.cpp Changed

@@ -156,6 +156,8 @@
 } else {
 if (has_alpha)
 frag.prepend("#define HAS_ALPHA\n");
+ if (d.video_format.isXYZ())
+ frag.prepend("#define XYZ_GAMMA\n");
 }
 
 if (d.texture_target == GL_TEXTURE_RECTANGLE) {
@@ -165,9 +167,8 @@
 frag.prepend("#undef texture\n"
 "#define texture texture2DRect\n"
 );
- }
- if (textureTarget() == GL_TEXTURE_RECTANGLE)
 frag.prepend("#define MULTI_COORD\n");
+ }
 frag.prepend(OpenGLHelper::compatibleShaderHeader(QOpenGLShader::Fragment));
 
 QByteArray header("*/");
@@ -347,19 +348,20 @@
 
 bool VideoShader::update(VideoMaterial *material)
 {
- if (!material)
- return false;
+ Q_ASSERT(material && "null material");
 DPTR_D(VideoShader);
 const qint32 mt = material->type();
 if (mt != d.material_type || d.rebuild_program) {
 // TODO: use shader program cache (per shader), check shader type
 qDebug("Rebuild shader program requested: %d. Material type %d=>%d", d.rebuild_program, d.material_type, mt);
 program()->removeAllShaders(); //not linked
- material->initializeShader(this);
+ // initialize shader, the same as VideoMaterial::createShader
+ setVideoFormat(material->currentFormat());
+ setTextureTarget(material->textureTarget());
+ setMaterialType(material->type());
+
 initialize();
 }
- if (!material->bind())
- return false;
 //material->unbind();
 const VideoFormat fmt(material->currentFormat()); //FIXME: maybe changed in setCurrentFrame(
 //format is out of date because we may use the same shader for different formats
@@ -524,6 +526,8 @@
 cs = ColorSpace_GBR;
 else
 cs = ColorSpace_RGB;
+ } else if (fmt.isXYZ()) {
+ cs = ColorSpace_XYZ;
 } else {
 if (frame.width() >= 1280 || frame.height() > 576) //values from mpv
 cs = ColorSpace_BT709;
@@ -554,27 +558,23 @@
 VideoShader* VideoMaterial::createShader() const
 {
 VideoShader *shader = new VideoShader();
- initializeShader(shader);
+ // initialize shader
+ shader->setVideoFormat(currentFormat());
+ shader->setTextureTarget(textureTarget());
+ shader->setMaterialType(type());
 //resize texture locations to avoid access format later
 return shader;
 }
 
-void VideoMaterial::initializeShader(VideoShader *shader) const
-{
- DPTR_D(const VideoMaterial);
- shader->setVideoFormat(d.video_format);
- shader->setTextureTarget(d.target);
- shader->setMaterialType(type());
-}
-
 QString VideoMaterial::typeName(qint32 value)
 {
- return QString("gl material 16to8bit: %1, planar: %2, has alpha: %3, 2d texture: %4, 2nd plane rg: %5")
+ return QString("gl material 16to8bit: %1, planar: %2, has alpha: %3, 2d texture: %4, 2nd plane rg: %5, xyz: %6")
 .arg(!!(value&1))
 .arg(!!(value&(1<<1)))
 .arg(!!(value&(1<<2)))
 .arg(!!(value&(1<<3)))
 .arg(!!(value&(1<<4)))
+ .arg(!!(value&(1<<5)))
 ;
 }
 
@@ -585,10 +585,8 @@
 const bool tex_2d = d.target == GL_TEXTURE_2D;
 // 2d,alpha,planar,8bit
 const int rg_biplane = fmt.planeCount()==2 && !OpenGLHelper::useDeprecatedFormats() && OpenGLHelper::hasRG();
- // nv21 bpc=1?
- const int bpc = fmt.bitsPerComponent();
- const int channel16_to8 = bpc > 8 && (OpenGLHelper::depth16BitTexture() < 16 || !OpenGLHelper::has16BitTexture() || fmt.isBigEndian());
- return (rg_biplane<<4)|(tex_2d<<3)|(fmt.hasAlpha()<<2)|(fmt.isPlanar()<<1)|(channel16_to8);
+ const int channel16_to8 = d.bpc > 8 && (OpenGLHelper::depth16BitTexture() < 16 || !OpenGLHelper::has16BitTexture() || fmt.isBigEndian());
+ return (fmt.isXYZ()<<5)|(rg_biplane<<4)|(tex_2d<<3)|(fmt.hasAlpha()<<2)|(fmt.isPlanar()<<1)|(channel16_to8);
 }
 
 bool VideoMaterial::bind()
@@ -604,7 +602,7 @@
 d.ensureTextures();
 for (int i = 0; i < nb_planes; ++i) {
 const int p = (i + 1) % nb_planes; //0 must active at last?
- bindPlane(p, d.update_texure); // why? i: quick items display wrong textures
+ d.uploadPlane(p, d.update_texure);
 }
 #if 0 //move to unbind should be fine
 if (d.update_texure) {
@@ -616,38 +614,36 @@
 }
 
 // TODO: move bindPlane to d.uploadPlane
-void VideoMaterial::bindPlane(int p, bool updateTexture)
+void VideoMaterialPrivate::uploadPlane(int p, bool updateTexture)
 {
- DPTR_D(VideoMaterial);
- GLuint &tex = d.textures[p];
+ GLuint &tex = textures[p];
 gl().ActiveTexture(GL_TEXTURE0 + p); //0 must active?
 if (!updateTexture) {
- DYGL(glBindTexture(d.target, tex));
+ DYGL(glBindTexture(target, tex));
 return;
 }
- // try_pbo ? pbo_id : 0. 0= > interop.createHandle
- GLuint tex0 = tex;
- if (d.frame.map(GLTextureSurface, &tex, p)) {
- if (tex0 != tex) {
- if (d.owns_texture[tex0])
- DYGL(glDeleteTextures(1, &tex0));
- d.owns_texture.remove(tex0);
- d.owns_texture[tex] = false;
+ if (!frame.constBits(0)) {
+ // try_pbo ? pbo_id : 0. 0= > interop.createHandle
+ GLuint tex0 = tex;
+ if (frame.map(GLTextureSurface, &tex, p)) {
+ if (tex0 != tex) {
+ if (owns_texture[tex0])
+ DYGL(glDeleteTextures(1, &tex0));
+ owns_texture.remove(tex0);
+ owns_texture[tex] = false;
+ }
+ DYGL(glBindTexture(target, tex)); // glActiveTexture was called, but maybe bind to 0 in map
+ return;
 }
- DYGL(glBindTexture(d.target, tex)); // glActiveTexture was called, but maybe bind to 0 in map
- return;
- }
- if (!d.frame.constBits(0)) {
 qWarning("map hw surface error");
 return;
 }
- // TODO if a hw frame map() failed, do not upload. upload only for host memory surfaces
 // FIXME: why happens on win?
- if (d.frame.bytesPerLine(p) <= 0)
+ if (frame.bytesPerLine(p) <= 0)
 return;
- if (d.try_pbo) {
+ if (try_pbo) {
 //qDebug("bind PBO %d", p);
- QOpenGLBuffer &pb = d.pbo[p];
+ QOpenGLBuffer &pb = pbo[p];
 pb.bind();
 // glMapBuffer() causes sync issue.
 // Call glBufferData() with NULL pointer before glMapBuffer(), the previous data in PBO will be discarded and
@@ -656,43 +652,27 @@
 pb.allocate(pb.size());
 GLubyte* ptr = (GLubyte*)pb.map(QOpenGLBuffer::WriteOnly);
 if (ptr) {
- memcpy(ptr, d.frame.constBits(p), pb.size());
+ memcpy(ptr, frame.constBits(p), pb.size());
 pb.unmap();
 }
 }
 //qDebug("bpl[%d]=%d width=%d", p, frame.bytesPerLine(p), frame.planeWidth(p));
- DYGL(glBindTexture(d.target, tex));
- //d.setupQuality();
- //DYGL(glTexParameteri(d.target, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE));
- //DYGL(glTexParameteri(d.target, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE));
+ DYGL(glBindTexture(target, tex));
+ //setupQuality();
+ //DYGL(glTexParameteri(target, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE));
+ //DYGL(glTexParameteri(target, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE));
 // This is necessary for non-power-of-two textures
 //glPixelStorei(GL_UNPACK_ALIGNMENT, get_alignment(stride)); 8, 4, 2, 1
 // glPixelStorei(GL_UNPACK_ROW_LENGTH, stride/glbpp); // for stride%glbpp > 0?
- DYGL(glTexSubImage2D(d.target, 0, 0, 0, d.texture_upload_size[p].width(), d.texture_upload_size[p].height(), d.data_format[p], d.data_type[p], d.try_pbo ? 0 : d.frame.constBits(p)));
- if (false) { //texture_upload_size[].width()*gl_bpp != bytesPerLine[]
- for (int y = 0; y < d.plane0Size.height(); ++y)
- DYGL(glTexSubImage2D(d.target, 0, 0, y, d.texture_upload_size[p].width(), 1, d.data_format[p], d.data_type[p], d.try_pbo ? 0 : d.frame.constBits(p)+y*d.plane0Size.width()));
- }
- //DYGL(glBindTexture(d.target, 0)); // no bind 0 because glActiveTexture was called
- if (d.try_pbo) {
- d.pbo[p].release();
+ DYGL(glTexSubImage2D(target, 0, 0, 0, texture_size[p].width(), texture_size[p].height(), data_format[p], data_type[p], try_pbo ? 0 : frame.constBits(p)));
+ if (false) { //texture_size[].width()*gl_bpp != bytesPerLine[]
+ for (int y = 0; y < plane0Size.height(); ++y)
+ DYGL(glTexSubImage2D(target, 0, 0, y, texture_size[p].width(), 1, data_format[p], data_type[p], try_pbo ? 0 : frame.constBits(p)+y*plane0Size.width()));
 }
-}
-
-int VideoMaterial::compare(const VideoMaterial *other) const
-{
- DPTR_D(const VideoMaterial);
- for (int i = 0; i < d.textures.size(); ++i) {
- const int diff = d.textures[i] - other->d_func().textures[i]; //TODO
- if (diff)
- return diff;
+ //DYGL(glBindTexture(target, 0)); // no bind 0 because glActiveTexture was called
+ if (try_pbo) {
+ pbo[p].release();
 }
- return d.bpc - other->bitsPerComponent();
-}
-
-bool VideoMaterial::hasAlpha() const
-{
- return d_func().video_format.hasAlpha();
 }
 
 void VideoMaterial::unbind()
@@ -708,6 +688,23 @@
 d.update_texure = false;
 d.frame = VideoFrame(); //FIXME: why need this? we must unmap correctly before frame is reset.
 }
+ setDirty(false);
+}
+
+int VideoMaterial::compare(const VideoMaterial *other) const
+{
+ DPTR_D(const VideoMaterial);
+ for (int i = 0; i < d.textures.size(); ++i) {
+ const int diff = d.textures[i] - other->d_func().textures[i]; //TODO
+ if (diff)
+ return diff;
+ }
+ return d.bpc - other->bitsPerComponent();
+}
+
+int VideoMaterial::textureTarget() const
+{
+ return d_func().target;
 }
 
 bool VideoMaterial::isDirty() const
@@ -997,7 +994,6 @@
 const int bpp_gl = OpenGLHelper::bytesOfGLFormat(data_format[i], data_type[i]);
 const int pad = std::ceil((qreal)(texture_size[i].width() - effective_tex_width[i])/(qreal)bpp_gl);
 texture_size[i].setWidth(std::ceil((qreal)texture_size[i].width()/(qreal)bpp_gl));
- texture_upload_size[i].setWidth(std::ceil((qreal)texture_upload_size[i].width()/(qreal)bpp_gl));
 effective_tex_width[i] /= bpp_gl; //fmt.bytesPerPixel(i);
 v_texture_size[i] = QVector2D(texture_size[i].width(), texture_size[i].height());
 //effective_tex_width_ratio =
@@ -1064,14 +1060,12 @@
 v_texel_size.resize(nb_planes);
 v_texture_size.resize(nb_planes);
 texture_size.resize(nb_planes);
- texture_upload_size.resize(nb_planes);
 effective_tex_width.resize(nb_planes);
 effective_tex_width_ratio = 1.0;
 for (int i = 0; i < nb_planes; ++i) {
 qDebug("plane linesize %d: padded = %d, effective = %d. theoretical plane size: %dx%d", i, frame.bytesPerLine(i), frame.effectiveBytesPerLine(i), frame.planeWidth(i), frame.planeHeight(i));
 // we have to consider size of opengl format. set bytesPerLine here and change to width later
 texture_size[i] = QSize(frame.bytesPerLine(i), frame.planeHeight(i));
- texture_upload_size[i] = texture_size[i];
 effective_tex_width[i] = frame.effectiveBytesPerLine(i); //store bytes here, modify as width later
 // usually they are the same. If not, the difference is small. min value can avoid rendering the invalid data.
 effective_tex_width_ratio = qMin(effective_tex_width_ratio, (qreal)frame.effectiveBytesPerLine(i)/(qreal)frame.bytesPerLine(i));

QtAV-1.11.0.tar.gz/src/opengl/gl_api.cpp -> QtAV-1.12.0.tar.gz/src/opengl/gl_api.cpp Changed

@@ -41,6 +41,37 @@
     return p;
 }
 
+static void* GetProcAddressWithExt(GetProcAddress_t get, const char *name)
+{
+    void* fp = get(name);
+    if (fp)
+        return fp;
+    static const char *ext[] = {
+        "ARB", "OES", "EXT", "ANGLE", "NV" //TODO: MESA, INTEL?
+#ifdef __APPLE__
+        , "APPLE"
+#endif
+        , NULL
+    };
+    char f[512];
+    memcpy(f, name, strlen(name));
+    char* const p = f + strlen(name);
+    for (int i = 0; ext[i]; ++i) {
+        memcpy(p, ext[i], sizeof(ext[i]) + 1); //copy trail '\0'
+        fp = get(f);
+        if (fp) {
+            printf("extension resolved: %s", f);
+            return fp;
+        }
+    }
+    return NULL;
+}
+
+static void* GetProcAddressDefault(const char *name)
+{
+    return GetProcAddressWithExt(GetProcAddress_Qt, name);
+}
+
 #ifdef QT_OPENGL_DYNAMIC
 #define GETPROCADDRESS_RESOLVE
 // GL_RESOLVE_ES_X_X will link to lib or use getProcAddress
@@ -50,12 +81,12 @@
 #else
 #ifdef GL_ES_VERSION_2_0
 #define GL_RESOLVE_ES_2_0(name) GL_RESOLVE(name)
-#define GL_RESOLVE_ES_3_0(name) GL_RESOLVE_NONE(name)
-#define GL_RESOLVE_ES_3_1(name) GL_RESOLVE_NONE(name)
+#define GL_RESOLVE_ES_3_0(name) GL_RESOLVE_EXT(name)
+#define GL_RESOLVE_ES_3_1(name) GL_RESOLVE_EXT(name)
 #elif GL_ES_VERSION_3_0
 #define GL_RESOLVE_ES_2_0(name) GL_RESOLVE(name)
 #define GL_RESOLVE_ES_3_0(name) GL_RESOLVE(name)
-#define GL_RESOLVE_ES_3_1(name) GL_RESOLVE_NONE(name)
+#define GL_RESOLVE_ES_3_1(name) GL_RESOLVE_NONE(name) //gl3ext is empty
 #elif GL_ES_VERSION_3_1
 #define GL_RESOLVE_ES_2_0(name) GL_RESOLVE(name)
 #define GL_RESOLVE_ES_3_0(name) GL_RESOLVE(name)
@@ -69,14 +100,14 @@
 #endif
 #endif //QT_OPENGL_DYNAMIC
 
+
 #define GL_RESOLVE_NONE(name) do { name = NULL;}while(0)
-#ifdef GETPROCADDRESS_RESOLVE
-#define GL_RESOLVE(name) do {\
+#define GL_RESOLVE_EXT(name) do {\
     void** fp = (void**)(&name); \
-    *fp = sGetProcAddress("gl" # name); \
-    if (!*fp) \
-        *fp = sGetProcAddress("gl" # name "ARB"); \
+    *fp = GetProcAddressDefault("gl" # name); \
 } while(0)
+#ifdef GETPROCADDRESS_RESOLVE
+#define GL_RESOLVE(name) GL_RESOLVE_EXT(name)
 #else
 #define GL_RESOLVE(name)  do {\
     name = ::gl##name; \
@@ -91,7 +122,7 @@
 void api::resolve()
 {
     //memset(g, 0, sizeof(g));
-    sGetProcAddress = GetProcAddress_Qt;
+    sGetProcAddress = GetProcAddressDefault;
     GL_RESOLVE(GetString);
     GL_RESOLVE(GetError);
     GL_RESOLVE(ActiveTexture);

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutput.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutput.cpp Changed

@@ -152,9 +152,10 @@
 }
 
 struct FrameInfo {
- FrameInfo(qreal t = 0, int s = 0) : timestamp(t), data_size(s) {}
+ FrameInfo(const QByteArray& d = QByteArray(), qreal t = 0, int us = 0) : timestamp(t), duration(us), data(d) {}
 qreal timestamp;
- int data_size;
+ int duration; // in us
+ QByteArray data;
 };
 
 void resetStatus() {
@@ -177,7 +178,7 @@
 qreal vol;
 qreal speed;
 AudioFormat format;
- QByteArray data;
+ AudioFormat requested;
 //AudioFrame audio_frame;
 quint32 nb_buffers;
 qint32 buffer_samples;
@@ -213,14 +214,13 @@
 
 void AudioOutputPrivate::playInitialData()
 {
- if (!backend)
- return;
 const char c = (format.sampleFormat() == AudioFormat::SampleFormat_Unsigned8
 || format.sampleFormat() == AudioFormat::SampleFormat_Unsigned8Planar)
 ? 0x80 : 0;
 for (quint32 i = 0; i < nb_buffers; ++i) {
- backend->write(QByteArray(buffer_samples*format.bytesPerSample(), c)); // fill silence byte, not always 0. AudioFormat.silenceByte
- frame_infos.push_back(FrameInfo(0, 1*format.bytesPerSample())); // initial data can be small (1 instead of buffer_samples)
+ const QByteArray data(backend->buffer_size, c);
+ backend->write(data); // fill silence byte, not always 0. AudioFormat.silenceByte
+ frame_infos.push_back(FrameInfo(data, 0, 0)); // initial data can be small (1 instead of buffer_samples)
 }
 backend->play();
 }
@@ -257,8 +257,6 @@
 , AVOutput(*new AudioOutputPrivate())
 {
 qDebug() << "Registered audio backends: " << AudioOutput::backendsAvailable(); // call this to register
- d_func().format.setSampleFormat(AudioFormat::SampleFormat_Signed16);
- d_func().format.setChannelLayout(AudioFormat::ChannelLayout_Stereo);
 setBackends(AudioOutputBackend::defaultPriority()); //ensure a backend is available
 }
 
@@ -317,7 +315,7 @@
 connect(d.backend, SIGNAL(muteReported(bool)), SLOT(reportMute(bool)));
 }
 
- emit backendsChanged();
+ Q_EMIT backendsChanged();
 }
 
 QStringList AudioOutput::backends() const
@@ -357,6 +355,7 @@
 QMutexLocker lock(&d.mutex);
 Q_UNUSED(lock);
 d.available = false;
+ d.paused = false;
 d.resetStatus();
 if (!d.backend)
 return false;
@@ -380,6 +379,7 @@
 QMutexLocker lock(&d.mutex);
 Q_UNUSED(lock);
 d.available = false;
+ d.paused = false;
 d.resetStatus();
 if (!d.backend)
 return false;
@@ -398,57 +398,108 @@
 DPTR_D(AudioOutput);
 if (!d.backend)
 return false;
- receiveData(data, pts);
+ if (!receiveData(data, pts))
+ return false;
 return d.backend->play();
 }
 
+void AudioOutput::pause(bool value)
+{
+ DPTR_D(AudioOutput);
+ d.paused = value;
+ // backend pause? Without backend pause, the buffered data will be played
+}
+
+bool AudioOutput::isPaused() const
+{
+ return d_func().paused;
+}
+
 bool AudioOutput::receiveData(const QByteArray &data, qreal pts)
 {
 DPTR_D(AudioOutput);
- if (d.paused)
+ if (isPaused())
 return false;
- d.data = data;
+ QByteArray queue_data(data);
 if (isMute() && d.sw_mute) {
 char s = 0;
 if (d.format.isUnsigned() && !d.format.isFloat())
 s = 1<<((d.format.bytesPerSample() << 3)-1);
- d.data.fill(s);
+ queue_data.fill(s);
 } else {
 if (!qFuzzyCompare(volume(), (qreal)1.0)
 && d.sw_volume
 && d.scale_samples
 ) {
 // TODO: af_volume needs samples_align to get nb_samples
- const int nb_samples = d.data.size()/d.format.bytesPerSample();
- quint8 *dst = (quint8*)d.data.constData();
+ const int nb_samples = queue_data.size()/d.format.bytesPerSample();
+ quint8 *dst = (quint8*)queue_data.constData();
 d.scale_samples(dst, dst, nb_samples, d.volume_i, volume());
 }
 }
 // wait after all data processing finished to reduce time error
- if (!waitForNextBuffer()) {
+ if (!waitForNextBuffer()) { // TODO: wait or not parameter, set by user (async)
 qWarning("ao backend maybe not open");
 d.resetStatus();
 return false;
 }
- d.frame_infos.push_back(AudioOutputPrivate::FrameInfo(pts, data.size()));
- if (!d.backend || !isOpen())
- return false;
- return d.backend->write(d.data);
+ d.frame_infos.push_back(AudioOutputPrivate::FrameInfo(queue_data, pts, d.format.durationForBytes(queue_data.size())));
+ return d.backend->write(queue_data); // backend is not null here
 }
 
-void AudioOutput::setAudioFormat(const AudioFormat& format)
+AudioFormat AudioOutput::setAudioFormat(const AudioFormat& format)
 {
 DPTR_D(AudioOutput);
 // no support check because that may require an open device(AL) while this function is called before ao.open()
 if (d.format == format)
- return;
+ return format;
+ d.requested = format;
+ if (!d.backend) {
+ d.format = AudioFormat();
+ d.scale_samples = NULL;
+ return AudioFormat();
+ }
+ if (d.backend->isSupported(format)) {
+ d.format = format;
+ d.updateSampleScaleFunc();
+ return format;
+ }
+ AudioFormat af(format);
+ // set channel layout first so that isSupported(AudioFormat) will not always false
+ if (!d.backend->isSupported(format.channelLayout()))
+ af.setChannelLayout(AudioFormat::ChannelLayout_Stereo); // assume stereo is supported
+ bool check_up = af.bytesPerSample() == 1;
+ while (!d.backend->isSupported(af) && !d.backend->isSupported(af.sampleFormat())) {
+ if (af.isPlanar()) {
+ af.setSampleFormat(ToPacked(af.sampleFormat()));
+ continue;
+ }
+ if (af.isFloat()) {
+ if (af.bytesPerSample() == 8)
+ af.setSampleFormat(AudioFormat::SampleFormat_Float);
+ else
+ af.setSampleFormat(AudioFormat::SampleFormat_Signed32);
+ } else {
+ af.setSampleFormat(AudioFormat::make(af.bytesPerSample()/2, false, (af.bytesPerSample() == 2) | af.isUnsigned() /* U8, no S8 */, false));
+ }
+ if (af.bytesPerSample() < 1) {
+ if (!check_up) {
+ qWarning("No sample format found");
+ break;
+ }
+ af.setSampleFormat(AudioFormat::SampleFormat_Float);
+ check_up = false;
+ continue;
+ }
+ }
+ d.format = af;
 d.updateSampleScaleFunc();
- d.format = format;
+ return af;
 }
 
-AudioFormat& AudioOutput::audioFormat()
+const AudioFormat& AudioOutput::requestedFormat() const
 {
- return d_func().format;
+ return d_func().requested;
 }
 
 const AudioFormat& AudioOutput::audioFormat() const
@@ -456,28 +507,6 @@
 return d_func().format;
 }
 
-void AudioOutput::setSampleRate(int rate)
-{
- d_func().format.setSampleRate(rate);
-}
-
-int AudioOutput::sampleRate() const
-{
- return d_func().format.sampleRate();
-}
-
-// TODO: check isSupported
-void AudioOutput::setChannels(int channels)
-{
- DPTR_D(AudioOutput);
- d.format.setChannels(channels);
-}
-
-int AudioOutput::channels() const
-{
- return d_func().format.channels();
-}
-
 void AudioOutput::setVolume(qreal value)
 {
 DPTR_D(AudioOutput);
@@ -529,38 +558,6 @@
 return d.backend->isSupported(format);
 }
 
-bool AudioOutput::isSupported(AudioFormat::SampleFormat sampleFormat) const
-{
- DPTR_D(const AudioOutput);
- if (!d.backend)
- return false;
- return d.backend->isSupported(sampleFormat);
-}
-
-bool AudioOutput::isSupported(AudioFormat::ChannelLayout channelLayout) const
-{
- DPTR_D(const AudioOutput);
- if (!d.backend)
- return false;
- return d.backend->isSupported(channelLayout);
-}
-
-AudioFormat::SampleFormat AudioOutput::preferredSampleFormat() const
-{
- DPTR_D(const AudioOutput);
- if (!d.backend)
- return AudioFormat::SampleFormat_Signed16;
- return d.backend->preferredSampleFormat();
-}
-
-AudioFormat::ChannelLayout AudioOutput::preferredChannelLayout() const
-{
- DPTR_D(const AudioOutput);
- if (!d.backend)
- return AudioFormat::ChannelLayout_Stereo;
- return d.backend->preferredChannelLayout();
-}
-
 int AudioOutput::bufferSize() const
 {
 return bufferSamples() * d_func().format.bytesPerSample();
@@ -612,21 +609,21 @@
 return d.backend->supportedFeatures();
 }
 
-bool AudioOutput::waitForNextBuffer()
+bool AudioOutput::waitForNextBuffer() // parameter bool wait: if no wait and no next buffer, return false
 {
 DPTR_D(AudioOutput);
 if (d.frame_infos.empty())
 return true;
- if (!d.backend)
- return false;
 //don't return even if we can add buffer because we don't know when a buffer is processed and we have /to update dequeue index
 // openal need enqueue to a dequeued buffer! why sl crash
 bool no_wait = false;//d.canAddBuffer();
 const AudioOutputBackend::BufferControl f = d.backend->bufferControl();
 int remove = 0;
+ const AudioOutputPrivate::FrameInfo &fi(d.frame_infos.front());
 if (f & AudioOutputBackend::Blocking) {
 remove = 1;
 } else if (f & AudioOutputBackend::CountCallback) {
+ d.backend->acquireNextBuffer();
 remove = 1;
 } else if (f & AudioOutputBackend::BytesCallback) {
 #if AO_USE_TIMER
@@ -636,21 +633,21 @@
 d.processed_remain = d.backend->getWritableBytes();
 if (d.processed_remain < 0)
 return false;
- const int next = d.frame_infos.front().data_size;
+ const int next = fi.data.size();
 //qDebug("remain: %d-%d, size: %d, next: %d", processed, d.processed_remain, d.data.size(), next);
 qint64 last_wait = 0LL;
- while (d.processed_remain - processed < next || d.processed_remain < d.data.size()) { //implies next > 0
+ while (d.processed_remain - processed < next || d.processed_remain < fi.data.size()) { //implies next > 0
 const qint64 us = d.format.durationForBytes(next - (d.processed_remain - processed));
- QMutexLocker lock(&d.mutex);
- Q_UNUSED(lock);
- d.cond.wait(&d.mutex, us/1000LL);
+ d.uwait(us);
 d.processed_remain = d.backend->getWritableBytes();
 if (d.processed_remain < 0)
 return false;
+#if AO_USE_TIMER
 if (!d.timer.isValid()) {
 qWarning("invalid timer. closed in another thread");
 return false;
 }
+#endif
 if (us >= last_wait
 #if AO_USE_TIMER
 && d.timer.elapsed() > 1000
@@ -661,13 +658,13 @@
 last_wait = us;
 }
 processed = d.processed_remain - processed;
- d.processed_remain -= d.data.size(); //ensure d.processed_remain later is greater
+ d.processed_remain -= fi.data.size(); //ensure d.processed_remain later is greater
 remove = -processed; // processed_this_period
 } else if (f & AudioOutputBackend::PlayedBytes) {
 d.processed_remain = d.backend->getPlayedBytes();
- const int next = d.frame_infos.front().data_size;
+ const int next = fi.data.size();
 // TODO: avoid always 0
- // TODO: compare processed_remain with d.data.size because input chuncks can be in different sizes
+ // TODO: compare processed_remain with fi.data.size because input chuncks can be in different sizes
 while (!no_wait && d.processed_remain < next) {
 const qint64 us = d.format.durationForBytes(next - d.processed_remain);
 if (us < 1000LL)
@@ -689,7 +686,7 @@
 qint64 us = 0;
 while (!no_wait && c < 1) {
 if (us <= 0)
- us = d.format.durationForBytes(d.frame_infos.front().data_size);
+ us = fi.duration;
 #if AO_USE_TIMER
 elapsed = d.timer.restart();
 if (elapsed > 0 && us > elapsed*1000LL)
@@ -709,9 +706,9 @@
 if (processed < 0)
 processed += bufferSizeTotal();
 d.play_pos = s;
- const int next = d.frame_infos.front().data_size;
+ const int next = fi.data.size();
 int writable_size = d.processed_remain + processed;
- while (!no_wait && (/*processed < next ||*/ writable_size < d.data.size()) && next > 0) {
+ while (!no_wait && (/*processed < next ||*/ writable_size < fi.data.size()) && next > 0) {
 const qint64 us = d.format.durationForBytes(next - writable_size);
 d.uwait(us);
 s = d.backend->getOffsetByBytes();
@@ -722,7 +719,7 @@
 d.play_pos = s;
 }
 d.processed_remain += processed;
- d.processed_remain -= d.data.size(); //ensure d.processed_remain later is greater
+ d.processed_remain -= fi.data.size(); //ensure d.processed_remain later is greater
 remove = -processed;
 } else if (f & AudioOutputBackend::OffsetIndex) {
 int n = d.backend->getOffset();
@@ -733,7 +730,7 @@
 // TODO: timer
 // TODO: avoid always 0
 while (!no_wait && processed < 1) {
- d.uwait(d.format.durationForBytes(d.frame_infos.front().data_size));
+ d.uwait(fi.duration);
 n = d.backend->getOffset();
 processed = n - d.play_pos;
 if (processed < 0)
@@ -746,7 +743,7 @@
 return false;
 }
 if (remove < 0) {
- int next = d.frame_infos.front().data_size;
+ int next = fi.data.size();
 int free_bytes = -remove;//d.processed_remain;
 while (free_bytes >= next && next > 0) {
 free_bytes -= next;
@@ -755,7 +752,7 @@
 break;
 }
 d.frame_infos.pop_front();
- next = d.frame_infos.front().data_size;
+ next = d.frame_infos.front().data.size();
 }
 //qDebug("remove: %d, unremoved bytes < %d, writable_bytes: %d", remove, free_bytes, d.processed_remain);
 return true;

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputAudioToolbox.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputAudioToolbox.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV (from 2016-02-11)
 
@@ -18,7 +18,7 @@
 License along with this library; if not, write to the Free Software
 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 ******************************************************************************/
-
+// FIXME: pause=>resume error
 #include "QtAV/private/AudioOutputBackend.h"
 #include <QtCore/QQueue>
 #include <QtCore/QSemaphore>
@@ -45,6 +45,7 @@
 void onCallback() Q_DECL_OVERRIDE;
 bool write(const QByteArray& data) Q_DECL_OVERRIDE;
 bool play() Q_DECL_OVERRIDE;
+ bool setVolume(qreal value) override;
 private:
 static void outCallback(void* inUserData, AudioQueueRef inAQ, AudioQueueBufferRef inBuffer);
 void tryPauseTimeline();
@@ -64,20 +65,14 @@
 static const AudioOutputBackendId AudioOutputBackendId_AudioToolbox = mkid::id32base36_2<'A', 'T'>::value;
 FACTORY_REGISTER(AudioOutputBackend, AudioToolbox, kName)
 
-#define AT_ENSURE(FUNC, ...) \
- do { \
- OSStatus ret = FUNC; \
- if (ret != noErr) { \
- qWarning("AudioOutputAudioToolbox Error>>> " #FUNC " (%d)", (int)ret); \
- return __VA_ARGS__; \
- } \
- } while(0)
-
-#define AT_WARN(FUNC, ...) \
+#define AT_ENSURE(FUNC, ...) AQ_RUN_CHECK(FUNC, return __VA_ARGS__)
+#define AT_WARN(FUNC, ...) AQ_RUN_CHECK(FUNC)
+#define AQ_RUN_CHECK(FUNC, ...) \
 do { \
 OSStatus ret = FUNC; \
 if (ret != noErr) { \
- qWarning("AudioOutputAudioToolbox Error>>> " #FUNC " (%d)", ret); \
+ qWarning("AudioBackendAudioQueue Error>>> " #FUNC ": %#x", ret); \
+ __VA_ARGS__; \
 } \
 } while(0)
 
@@ -123,6 +118,7 @@
 
 AudioOutputAudioToolbox::AudioOutputAudioToolbox(QObject *parent)
 : AudioOutputBackend(AudioOutput::DeviceFeatures()
+ |AudioOutput::SetVolume
 , parent)
 , m_queue(NULL)
 , m_waiting(false)
@@ -155,7 +151,7 @@
 
 bool AudioOutputAudioToolbox::isSupported(AudioFormat::SampleFormat smpfmt) const
 {
- return !AudioFormat::isPlanar(smpfmt);
+ return !IsPlanar(smpfmt);
 }
 
 bool AudioOutputAudioToolbox::open()
@@ -220,8 +216,24 @@
 
 bool AudioOutputAudioToolbox::play()
 {
- // no running check is fine
- AT_ENSURE(AudioQueueStart(m_queue, NULL), false);
+ OSType err = AudioQueueStart(m_queue, nullptr);
+ if (err == '!pla') { //AVAudioSessionErrorCodeCannotStartPlaying
+ qWarning("AudioQueueStart error: AVAudioSessionErrorCodeCannotStartPlaying. May play in background");
+ close();
+ open();
+ return false;
+ }
+ if (err != noErr) {
+ qWarning("AudioQueueStart error: %#x", noErr);
+ return false;
+ }
+ return true;
+}
+
+bool AudioOutputAudioToolbox::setVolume(qreal value)
+{
+ // iOS document says the range is [0,1]. But >1.0 works on macOS. So no manually check range here
+ AT_ENSURE(AudioQueueSetParameter(m_queue, kAudioQueueParam_Volume, value), false);
 return true;
 }
 } //namespace QtAV

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputBackend.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputBackend.cpp Changed

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputDSound.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputDSound.cpp Changed

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputOpenAL.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputOpenAL.cpp Changed

@@ -57,8 +57,6 @@
 bool isSupported(const AudioFormat& format) const Q_DECL_FINAL;
 bool isSupported(AudioFormat::SampleFormat sampleFormat) const Q_DECL_FINAL;
 bool isSupported(AudioFormat::ChannelLayout channelLayout) const Q_DECL_FINAL;
- AudioFormat::SampleFormat preferredSampleFormat() const Q_DECL_FINAL;
- AudioFormat::ChannelLayout preferredChannelLayout() const Q_DECL_FINAL;
 protected:
 BufferControl bufferControl() const Q_DECL_FINAL;
 bool write(const QByteArray& data) Q_DECL_FINAL;
@@ -101,7 +99,7 @@
 static const AudioOutputBackendId AudioOutputBackendId_OpenAL = mkid::id32base36_6<'O', 'p', 'e', 'n', 'A', 'L'>::value;
 FACTORY_REGISTER(AudioOutputBackend, OpenAL, kName)
 
-#define AL_ENSURE_OK(expr, ...) \
+#define AL_ENSURE(expr, ...) \
 do { \
 expr; \
 const ALenum err = alGetError(); \
@@ -165,28 +163,20 @@
 format = alGetEnumValue(s16fmt[c-1].ext);
 }
 } else if (ctx) {
- if (AudioFormat::SampleFormat_Signed32 == spfmt) {
- if (c > 3 && c <= 8) {
- if (alIsExtensionPresent("AL_EXT_MCFORMATS")) {
- static const al_fmt_t s32fmt[] = {
- {"AL_FORMAT_QUAD32"},
- {"AL_FORMAT_REAR32"},
- {"AL_FORMAT_51CHN32"},
- {"AL_FORMAT_61CHN32"},
- {"AL_FORMAT_71CHN32"}
- };
- format = alGetEnumValue(s32fmt[c-4].ext);
- }
- }
- } else if (AudioFormat::SampleFormat_Float == spfmt) {
- if (c < 3) {
- if (alIsExtensionPresent("AL_EXT_float32")) {
- static const al_fmt_t f32fmt[] = {
- {"AL_FORMAT_MONO_FLOAT32"},
- {"AL_FORMAT_STEREO_FLOAT32"}
- };
- format = alGetEnumValue(f32fmt[c-1].ext);
- }
+ if (AudioFormat::SampleFormat_Float == spfmt) {
+ static const al_fmt_t f32fmt[] = {
+ {"AL_FORMAT_MONO_FLOAT32"},
+ {"AL_FORMAT_STEREO_FLOAT32"},
+ {0},
+ // AL_EXT_MCFORMATS
+ {"AL_FORMAT_QUAD32"},
+ {"AL_FORMAT_REAR32"},
+ {"AL_FORMAT_51CHN32"},
+ {"AL_FORMAT_61CHN32"},
+ {"AL_FORMAT_71CHN32"}
+ };
+ if (c <=8 && f32fmt[c-1].ext) {
+ format = alGetEnumValue(f32fmt[c-1].ext);
 }
 } else if (AudioFormat::SampleFormat_Double == spfmt) {
 if (c < 3) {
@@ -202,7 +192,10 @@
 }
 ALCenum err = alGetError();
 if (err != AL_NO_ERROR) {
- qWarning("OpenAL audioFormatToAL error: %s", alGetString(err));
+ if (ctx)
+ qWarning("OpenAL audioFormatToAL error: %s", alGetString(err));
+ else
+ qWarning("OpenAL audioFormatToAL error (null context): %#x", err);
 }
 if (format == 0) {
 qWarning("AudioOutputOpenAL Error: No OpenAL format available for audio data format %s %s."
@@ -347,9 +340,7 @@
 {
 if (sampleFormat == AudioFormat::SampleFormat_Unsigned8 || sampleFormat == AudioFormat::SampleFormat_Signed16)
 return true;
- if (AudioFormat::isPlanar(sampleFormat))
- return false;
- if (!context)
+ if (IsPlanar(sampleFormat))
 return false;
 SCOPE_LOCK_CONTEXT();
 if (sampleFormat == AudioFormat::SampleFormat_Float)
@@ -360,21 +351,11 @@
 return false;
 }
 
-bool AudioOutputOpenAL::isSupported(AudioFormat::ChannelLayout channelLayout) const
+bool AudioOutputOpenAL::isSupported(AudioFormat::ChannelLayout channelLayout) const // FIXME: check
 {
 return channelLayout == AudioFormat::ChannelLayout_Mono || channelLayout == AudioFormat::ChannelLayout_Stereo;
 }
 
-AudioFormat::SampleFormat AudioOutputOpenAL::preferredSampleFormat() const
-{
- return AudioFormat::SampleFormat_Signed16;
-}
-
-AudioFormat::ChannelLayout AudioOutputOpenAL::preferredChannelLayout() const
-{
- return AudioFormat::ChannelLayout_Stereo;
-}
-
 QString AudioOutputOpenAL::deviceName() const
 {
 if (!device)
@@ -399,10 +380,10 @@
 buf = buffer[(-state)%buffer_count];
 --state;
 } else {
- AL_ENSURE_OK(alSourceUnqueueBuffers(source, 1, &buf), false);
+ AL_ENSURE(alSourceUnqueueBuffers(source, 1, &buf), false);
 }
- AL_ENSURE_OK(alBufferData(buf, format_al, data.constData(), data.size(), format.sampleRate()), false);
- AL_ENSURE_OK(alSourceQueueBuffers(source, 1, &buf), false);
+ AL_ENSURE(alBufferData(buf, format_al, data.constData(), data.size(), format.sampleRate()), false);
+ AL_ENSURE(alSourceQueueBuffers(source, 1, &buf), false);
 return true;
 }
 
@@ -428,7 +409,7 @@
 bool AudioOutputOpenAL::setVolume(qreal value)
 {
 SCOPE_LOCK_CONTEXT();
- AL_ENSURE_OK(alListenerf(AL_GAIN, value), false);
+ AL_ENSURE(alListenerf(AL_GAIN, value), false);
 return true;
 }

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputOpenSL.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputOpenSL.cpp Changed

@@ -26,13 +26,26 @@
 #ifdef Q_OS_ANDROID
 #include <SLES/OpenSLES_Android.h>
 #include <SLES/OpenSLES_AndroidConfiguration.h>
+#include <sys/system_properties.h>
 #endif
 #include "QtAV/private/mkid.h"
 #include "QtAV/private/factory.h"
 #include "utils/Logger.h"
 
+// TODO: native sample rate, so AUDIO_OUTPUT_FLAG_FAST is enabled
 namespace QtAV {
 
+// OpenSL 1.1, or __ANDROID_API__ >= 21
+#ifndef SL_DATAFORMAT_PCM_EX
+#define SL_PCM_REPRESENTATION_SIGNED_INT ((SLuint32) 0x00000001)
+#define SL_PCM_REPRESENTATION_UNSIGNED_INT ((SLuint32) 0x00000002)
+#define SL_PCM_REPRESENTATION_FLOAT ((SLuint32) 0x00000003)
+#define SL_DATAFORMAT_PCM_EX ((SLuint32) 0x00000004)
+struct SLDataFormat_PCM_EX : SLDataFormat_PCM {
+ SLuint32 representation;
+};
+#endif
+
 static const char kName[] = "OpenSL";
 class AudioOutputOpenSL Q_DECL_FINAL: public AudioOutputBackend
 {
@@ -40,6 +53,7 @@
 AudioOutputOpenSL(QObject *parent = 0);
 ~AudioOutputOpenSL();
 
+ int engineVersion() const { return m_sl_major*100+m_sl_minor*10+m_sl_step;}
 QString name() const Q_DECL_OVERRIDE { return QLatin1String(kName);}
 bool isSupported(const AudioFormat& format) const Q_DECL_OVERRIDE;
 bool isSupported(AudioFormat::SampleFormat sampleFormat) const Q_DECL_OVERRIDE;
@@ -48,6 +62,7 @@
 bool close() Q_DECL_OVERRIDE;
 BufferControl bufferControl() const Q_DECL_OVERRIDE;
 void onCallback() Q_DECL_OVERRIDE;
+ void acquireNextBuffer() Q_DECL_OVERRIDE;
 bool write(const QByteArray& data) Q_DECL_OVERRIDE;
 bool play() Q_DECL_OVERRIDE;
 //default return -1. means not the control
@@ -62,17 +77,22 @@
 static void bufferQueueCallback(SLBufferQueueItf bufferQueue, void *context);
 static void playCallback(SLPlayItf player, void *ctx, SLuint32 event);
 private:
+ SLDataFormat_PCM_EX audioFormatToSL(const AudioFormat &format);
+
 SLObjectItf engineObject;
 SLEngineItf engine;
+ SLEngineCapabilitiesItf m_cap;
 SLObjectItf m_outputMixObject;
 SLObjectItf m_playerObject;
 SLPlayItf m_playItf;
 SLVolumeItf m_volumeItf;
 SLBufferQueueItf m_bufferQueueItf;
 #ifdef Q_OS_ANDROID
- SLAndroidSimpleBufferQueueItf m_bufferQueueItf_android;
+ SLAndroidSimpleBufferQueueItf m_bufferQueueItf_android; // supports decoding, recording
 #endif
 bool m_android;
+ int m_android_api_level;
+ SLint16 m_sl_major, m_sl_minor, m_sl_step;
 SLint32 m_streamType;
 quint32 buffers_queued;
 QSemaphore sem;
@@ -95,13 +115,21 @@
 } \
 } while(0)
 
-static SLDataFormat_PCM audioFormatToSL(const AudioFormat &format)
+SLDataFormat_PCM_EX AudioOutputOpenSL::audioFormatToSL(const AudioFormat &format)
 {
- SLDataFormat_PCM format_pcm;
- format_pcm.formatType = SL_DATAFORMAT_PCM;
+ SLDataFormat_PCM_EX format_pcm;
+ if (format.isFloat()) {
+ if (format.sampleSize() == sizeof(float))
+ format_pcm.representation = SL_PCM_REPRESENTATION_FLOAT;
+ } else if (format.isUnsigned()) {
+ format_pcm.representation = SL_PCM_REPRESENTATION_UNSIGNED_INT;
+ } else {
+ format_pcm.representation = SL_PCM_REPRESENTATION_SIGNED_INT;
+ }
+ format_pcm.formatType = m_android_api_level >= 21 || engineVersion() >= 110 ? SL_DATAFORMAT_PCM_EX : SL_DATAFORMAT_PCM;
 format_pcm.numChannels = format.channels();
 format_pcm.samplesPerSec = format.sampleRate() * 1000;
- format_pcm.bitsPerSample = format.bytesPerSample()*8;
+ format_pcm.bitsPerSample = format.bytesPerSample()*8; //raw sample size, e.g. s24 is 24. currently we do not support such formats
 format_pcm.containerSize = format_pcm.bitsPerSample;
 // TODO: more layouts
 format_pcm.channelMask = format.channels() == 1 ? SL_SPEAKER_FRONT_CENTER : SL_SPEAKER_FRONT_LEFT | SL_SPEAKER_FRONT_RIGHT;
@@ -161,15 +189,31 @@
 , m_bufferQueueItf(0)
 , m_bufferQueueItf_android(0)
 , m_android(false)
+ , m_android_api_level(0)
+ , m_sl_major(0)
+ , m_sl_minor(0)
+ , m_sl_step(0)
 , m_streamType(-1)
 , buffers_queued(0)
 , queue_data_write(0)
 {
+#ifdef Q_OS_ANDROID
+ char v[PROP_VALUE_MAX+1];
+ __system_property_get("ro.build.version.sdk", v);
+ m_android_api_level = atoi(v);
+#endif
 available = false;
- SL_ENSURE(slCreateEngine(&engineObject, 0, 0, 0, 0, 0));
+ SLEngineOption opt[] = {(SLuint32) SL_ENGINEOPTION_THREADSAFE, (SLuint32) SL_BOOLEAN_TRUE};
+ SL_ENSURE(slCreateEngine(&engineObject, 1, opt, 0, NULL, NULL)); // SLEngineOption is ignored by android
 SL_ENSURE((*engineObject)->Realize(engineObject, SL_BOOLEAN_FALSE));
 SL_ENSURE((*engineObject)->GetInterface(engineObject, SL_IID_ENGINE, &engine));
 available = true;
+
+ if ((*engineObject)->GetInterface(engineObject, SL_IID_ENGINECAPABILITIES, &m_cap) == SL_RESULT_SUCCESS) { // SL_RESULT_FEATURE_UNSUPPORTED
+ if ((*m_cap)->QueryAPIVersion(m_cap, &m_sl_major, &m_sl_minor, &m_sl_step) == SL_RESULT_SUCCESS) {
+ printf("OpenSL version: %d.%d.%d\n", m_sl_major, m_sl_minor, m_sl_step);
+ }
+ }
 }
 
 AudioOutputOpenSL::~AudioOutputOpenSL()
@@ -185,7 +229,13 @@
 
 bool AudioOutputOpenSL::isSupported(AudioFormat::SampleFormat sampleFormat) const
 {
- return sampleFormat == AudioFormat::SampleFormat_Unsigned8 || sampleFormat == AudioFormat::SampleFormat_Signed16;
+ if (sampleFormat == AudioFormat::SampleFormat_Unsigned8 || sampleFormat == AudioFormat::SampleFormat_Signed16) // TODO: android api 21 supports s32?
+ return true;
+ if (m_android_api_level < 21 || (engineVersion() > 0 && engineVersion() < 110))
+ return false;
+ if (!IsFloat(sampleFormat) || IsPlanar(sampleFormat))
+ return false;
+ return RawSampleSize(sampleFormat) == sizeof(float); // TODO: test s32 etc
 }
 
 bool AudioOutputOpenSL::isSupported(AudioFormat::ChannelLayout channelLayout) const
@@ -204,11 +254,17 @@
 sem.release();
 }
 
+void AudioOutputOpenSL::acquireNextBuffer()
+{
+ if (bufferControl() & CountCallback)
+ sem.acquire();
+}
+
 bool AudioOutputOpenSL::open()
 {
 queue_data.resize(buffer_size*buffer_count);
 SLDataLocator_BufferQueue bufferQueueLocator = { SL_DATALOCATOR_BUFFERQUEUE, (SLuint32)buffer_count };
- SLDataFormat_PCM pcmFormat = audioFormatToSL(format);
+ SLDataFormat_PCM_EX pcmFormat = audioFormatToSL(format);
 SLDataSource audioSrc = { &bufferQueueLocator, &pcmFormat };
 #ifdef Q_OS_ANDROID
 SLDataLocator_AndroidSimpleBufferQueue bufferQueueLocator_android = { SL_DATALOCATOR_ANDROIDSIMPLEBUFFERQUEUE, (SLuint32)buffer_count };
@@ -222,9 +278,9 @@
 SLDataSink audioSink = { &outputMixLocator, NULL };
 
 const SLInterfaceID ids[] = { SL_IID_BUFFERQUEUE, SL_IID_VOLUME
- #ifdef Q_OS_ANDROID
+#ifdef Q_OS_ANDROID
 , SL_IID_ANDROIDCONFIGURATION
- #endif
+#endif
 };
 const SLboolean req[] = { SL_BOOLEAN_TRUE, SL_BOOLEAN_TRUE
 #ifdef Q_OS_ANDROID
@@ -248,14 +304,12 @@
 if (m_android) {
 SL_ENSURE((*m_playerObject)->GetInterface(m_playerObject, SL_IID_ANDROIDSIMPLEBUFFERQUEUE, &m_bufferQueueItf_android), false);
 SL_ENSURE((*m_bufferQueueItf_android)->RegisterCallback(m_bufferQueueItf_android, AudioOutputOpenSL::bufferQueueCallbackAndroid, this), false);
- } else {
+ } else
+#endif
+ {
 SL_ENSURE((*m_playerObject)->GetInterface(m_playerObject, SL_IID_BUFFERQUEUE, &m_bufferQueueItf), false);
 SL_ENSURE((*m_bufferQueueItf)->RegisterCallback(m_bufferQueueItf, AudioOutputOpenSL::bufferQueueCallback, this), false);
 }
-#else
- SL_ENSURE((*m_playerObject)->GetInterface(m_playerObject, SL_IID_BUFFERQUEUE, &m_bufferQueueItf), false);
- SL_ENSURE((*m_bufferQueueItf)->RegisterCallback(m_bufferQueueItf, AudioOutputOpenSL::bufferQueueCallback, this), false);
-#endif
 // Play interface
 SL_ENSURE((*m_playerObject)->GetInterface(m_playerObject, SL_IID_PLAY, &m_playItf), false);
 // call when SL_PLAYSTATE_STOPPED
@@ -308,22 +362,19 @@
 
 bool AudioOutputOpenSL::write(const QByteArray& data)
 {
- if (bufferControl() & CountCallback)
- sem.acquire();
+ // assume data.size() <= buffer_size. It's true in QtAV
 const int s = qMin(queue_data.size() - queue_data_write, data.size());
 // assume data.size() <= buffer_size. It's true in QtAV
 if (s < data.size())
 queue_data_write = 0;
 memcpy((char*)queue_data.constData() + queue_data_write, data.constData(), data.size());
- //qDebug("enqueue %p, queue_data_write: %d", data.constData(), queue_data_write);
+ //qDebug("enqueue %p, queue_data_write: %d/%d available:%d", data.constData(), queue_data_write, queue_data.size(), sem.available());
 #ifdef Q_OS_ANDROID
 if (m_android)
 SL_ENSURE((*m_bufferQueueItf_android)->Enqueue(m_bufferQueueItf_android, queue_data.constData() + queue_data_write, data.size()), false);
 else
- SL_ENSURE((*m_bufferQueueItf)->Enqueue(m_bufferQueueItf, queue_data.constData() + queue_data_write, data.size()), false);
-#else
- SL_ENSURE((*m_bufferQueueItf)->Enqueue(m_bufferQueueItf, queue_data.constData() + queue_data_write, data.size()), false);
 #endif
+ SL_ENSURE((*m_bufferQueueItf)->Enqueue(m_bufferQueueItf, queue_data.constData() + queue_data_write, data.size()), false);
 buffers_queued++;
 queue_data_write += data.size();
 if (queue_data_write == queue_data.size())
@@ -350,16 +401,13 @@
 SLAndroidSimpleBufferQueueState state;
 (*m_bufferQueueItf_android)->GetState(m_bufferQueueItf_android, &state);
 count = state.count;
- } else {
+ } else
+#endif
+ {
 SLBufferQueueState state;
 (*m_bufferQueueItf)->GetState(m_bufferQueueItf, &state);
 count = state.count;
 }
-#else
- SLBufferQueueState state;
- (*m_bufferQueueItf)->GetState(m_bufferQueueItf, &state);
- count = state.count;
-#endif
 buffers_queued = count;
 processed -= count;
 return processed;

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputPulse.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputPulse.cpp Changed

QtAV-1.11.0.tar.gz/src/output/audio/AudioOutputXAudio2.cpp -> QtAV-1.12.0.tar.gz/src/output/audio/AudioOutputXAudio2.cpp Changed

QtAV-1.11.0.tar.gz/src/output/video/OpenGLRendererBase.cpp -> QtAV-1.12.0.tar.gz/src/output/video/OpenGLRendererBase.cpp Changed

QtAV-1.11.0.tar.gz/src/output/video/OpenGLWindowRenderer.cpp -> QtAV-1.12.0.tar.gz/src/output/video/OpenGLWindowRenderer.cpp Changed

QtAV-1.11.0.tar.gz/src/shaders/packed.f.glsl -> QtAV-1.12.0.tar.gz/src/shaders/packed.f.glsl Changed

QtAV-1.11.0.tar.gz/src/shaders/planar.f.glsl -> QtAV-1.12.0.tar.gz/src/shaders/planar.f.glsl Changed

@@ -62,16 +62,10 @@
                              dot(sample2d(u_Texture0, v_TexCoords0, 0).rg, u_to8),
                              dot(sample2d(u_Texture1, v_TexCoords1, 1).rg, u_to8),
                              dot(sample2d(u_Texture2, v_TexCoords2, 2).rg, u_to8),
-#ifdef HAS_ALPHA
-                             dot(sample2d(u_Texture3, v_TexCoords3, 3).rg, u_to8)
-#endif //HAS_ALPHA
 #else
                              dot(sample2d(u_Texture0, v_TexCoords0, 0).ra, u_to8),
                              dot(sample2d(u_Texture1, v_TexCoords1, 1).ra, u_to8),
                              dot(sample2d(u_Texture2, v_TexCoords2, 2).ra, u_to8),
-#ifdef HAS_ALPHA
-                             dot(sample2d(u_Texture3, v_TexCoords3, 3).ra, u_to8)
-#endif //HAS_ALPHA
 #endif //USE_RG
 #else
 #ifdef USE_RG
@@ -82,24 +76,33 @@
 #else
                              sample2d(u_Texture2, v_TexCoords2, 2).r,
 #endif //IS_BIPLANE
-#ifdef HAS_ALPHA
-                             sample2d(u_Texture3, v_TexCoords3, 3).r
-
-#endif //HAS_ALPHA
 #else
 // use r, g, a to work for both yv12 and nv12. idea from xbmc
                              sample2d(u_Texture0, v_TexCoords0, 0).r,
                              sample2d(u_Texture1, v_TexCoords1, 1).g,
                              sample2d(u_Texture2, v_TexCoords2, 2).a,
-#ifdef HAS_ALPHA
-                             sample2d(u_Texture3, v_TexCoords3, 3).a
-#endif //HAS_ALPHA
 #endif //USE_RG
 #endif //CHANNEL16_TO8
-#ifndef HAS_ALPHA
-                             1
-#endif //HAS_ALPHA
+                             1.0
                             )
                          , 0.0, 1.0) * u_opacity;
+#ifdef HAS_ALPHA
+    float a =
+#ifdef CHANNEL16_TO8
+#ifdef USE_RG
+    dot(sample2d(u_Texture3, v_TexCoords3, 3).rg, u_to8);
+#else
+    dot(sample2d(u_Texture3, v_TexCoords3, 3).ra, u_to8);
+#endif
+#else
+#ifdef USE_RG
+    sample2d(u_Texture3, v_TexCoords3, 3).r;
+#else
+    sample2d(u_Texture3, v_TexCoords3, 3).a;
+#endif
+#endif
+    gl_FragColor.rgb = gl_FragColor.rgb*a;
+    gl_FragColor.a = a;
+#endif //HAS_ALPHA
 /***User post processing here***%userPostProcess%***/
 }

QtAV-1.11.0.tar.gz/src/utils/BlockingQueue.h -> QtAV-1.12.0.tar.gz/src/utils/BlockingQueue.h Changed

QtAV-1.11.0.tar.gz/src/utils/CopyFrame_SSE2.cpp -> QtAV-1.12.0.tar.gz/src/utils/CopyFrame_SSE2.cpp Changed

QtAV-1.11.0.tar.gz/src/utils/CopyFrame_SSE4.cpp -> QtAV-1.12.0.tar.gz/src/utils/CopyFrame_SSE4.cpp Changed

QtAV-1.11.0.tar.gz/src/utils/GPUMemCopy.cpp -> QtAV-1.12.0.tar.gz/src/utils/GPUMemCopy.cpp Changed

@@ -1,6 +1,6 @@
 /******************************************************************************
 QtAV: Multimedia framework based on Qt and FFmpeg
- Copyright (C) 2012-2016 Wang Bin <wbsecg1@gmail.com>
+ Copyright (C) 2012-2017 Wang Bin <wbsecg1@gmail.com>
 
 * This file is part of QtAV
 
@@ -26,6 +26,12 @@
 extern "C" {
 #include <libavutil/cpu.h>
 }
+
+#ifndef Q_PROCESSOR_X86 // qt4
+#if defined(__SSE__) || defined(_M_IX86) || defined(_M_X64)
+#define Q_PROCESSOR_X86
+#endif
+#endif
 // read qsimd_p.h
 #define UINT unsigned int
 void CopyFrame_SSE2(void *pSrc, void *pDest, void *pCacheBlock, UINT width, UINT height, UINT pitch);
@@ -47,11 +53,11 @@
 
 bool GPUMemCopy::isAvailable()
 {
-#if QTAV_HAVE(SSE4_1)
+#if QTAV_HAVE(SSE4_1) && defined(Q_PROCESSOR_X86)
 if (detect_sse4())
 return true;
 #endif
-#if QTAV_HAVE(SSE2)
+#if QTAV_HAVE(SSE2) && defined(Q_PROCESSOR_X86)
 if (detect_sse2())
 return true;
 #endif
@@ -61,7 +67,7 @@
 GPUMemCopy::GPUMemCopy()
 : mInitialized(false)
 {
-#if QTAV_HAVE(SSE2)
+#if QTAV_HAVE(SSE2) && defined(Q_PROCESSOR_X86)
 mCache.buffer = 0;
 mCache.size = 0;
 #endif
@@ -81,7 +87,7 @@
 bool GPUMemCopy::initCache(unsigned width)
 {
 mInitialized = false;
-#if QTAV_HAVE(SSE2)
+#if QTAV_HAVE(SSE2) && defined(Q_PROCESSOR_X86)
 mCache.size = std::max<size_t>((width + 0x0f) & ~ 0x0f, CACHED_BUFFER_SIZE);
 mCache.buffer = (unsigned char*)qMallocAligned(mCache.size, 16);
 mInitialized = !!mCache.buffer;
@@ -96,7 +102,7 @@
 void GPUMemCopy::cleanCache()
 {
 mInitialized = false;
-#if QTAV_HAVE(SSE2)
+#if QTAV_HAVE(SSE2) && defined(Q_PROCESSOR_X86)
 if (mCache.buffer) {
 qFreeAligned(mCache.buffer);
 }
@@ -107,10 +113,10 @@
 
 void GPUMemCopy::copyFrame(void *pSrc, void *pDest, unsigned width, unsigned height, unsigned pitch)
 {
-#if QTAV_HAVE(SSE4_1)
+#if QTAV_HAVE(SSE4_1) && defined(Q_PROCESSOR_X86)
 if (detect_sse4())
 CopyFrame_SSE4(pSrc, pDest, mCache.buffer, width, height, pitch);
-#elif QTAV_HAVE(SSE2)
+#elif QTAV_HAVE(SSE2) && defined(Q_PROCESSOR_X86)
 if (detect_sse2())
 CopyFrame_SSE2(pSrc, pDest, mCache.buffer, width, height, pitch);
 #else
@@ -124,10 +130,10 @@
 
 void* gpu_memcpy(void *dst, const void *src, size_t size)
 {
-#if QTAV_HAVE(SSE4_1)
+#if QTAV_HAVE(SSE4_1) && defined(Q_PROCESSOR_X86)
 if (detect_sse4())
 return memcpy_sse4(dst, src, size);
-#elif QTAV_HAVE(SSE2)
+#elif QTAV_HAVE(SSE2) && defined(Q_PROCESSOR_X86)
 if (detect_sse2())
 return memcpy_sse2(dst, src, size);
 #endif

QtAV-1.11.0.tar.gz/src/utils/Logger.cpp -> QtAV-1.12.0.tar.gz/src/utils/Logger.cpp Changed

QtAV-1.11.0.tar.gz/src/utils/internal.cpp -> QtAV-1.12.0.tar.gz/src/utils/internal.cpp Changed

@@ -228,11 +228,11 @@
             qDebug("%s=>%s", i.key().toUtf8().constData(), i.value().toByteArray().constData());
             if (vt == QVariant::Int || vt == QVariant::UInt || vt == QVariant::Bool) {
                 // QVariant.toByteArray(): "true" or "false", can not recognized by avcodec
-                av_opt_set_int(obj, key.constData(), i.value().toInt(), 0);
+                av_opt_set_int(obj, key.constData(), i.value().toInt(), AV_OPT_SEARCH_CHILDREN);
             } else if (vt == QVariant::LongLong || vt == QVariant::ULongLong) {
-                av_opt_set_int(obj, key.constData(), i.value().toLongLong(), 0);
+                av_opt_set_int(obj, key.constData(), i.value().toLongLong(), AV_OPT_SEARCH_CHILDREN);
             } else if (vt == QVariant::Double) {
-                av_opt_set_double(obj, key.constData(), i.value().toDouble(), 0);
+                av_opt_set_double(obj, key.constData(), i.value().toDouble(), AV_OPT_SEARCH_CHILDREN);
             }
         }
         return;
@@ -249,9 +249,9 @@
         const QByteArray key(i.key().toUtf8());
         qDebug("%s=>%s", i.key().toUtf8().constData(), i.value().toByteArray().constData());
         if (vt == QVariant::Int || vt == QVariant::UInt || vt == QVariant::Bool) {
-            av_opt_set_int(obj, key.constData(), i.value().toInt(), 0);
+            av_opt_set_int(obj, key.constData(), i.value().toInt(), AV_OPT_SEARCH_CHILDREN);
         } else if (vt == QVariant::LongLong || vt == QVariant::ULongLong) {
-            av_opt_set_int(obj, key.constData(), i.value().toLongLong(), 0);
+            av_opt_set_int(obj, key.constData(), i.value().toLongLong(), AV_OPT_SEARCH_CHILDREN);
         }
     }
 }

QtAV-1.11.0.tar.gz/tests/qiodevice/qiodevice.pro -> QtAV-1.12.0.tar.gz/tests/qiodevice/qiodevice.pro Changed

QtAV-1.11.0.tar.gz/tools/ci/osx/after_success.sh -> QtAV-1.12.0.tar.gz/tools/ci/osx/after_success.sh Changed

@@ -1,12 +1,16 @@
-exit 0
-cd tools
-git clone https://github.com/andreyvit/create-dmg.git
-
-./deploy_osx.sh $TRAVIS_BUILD_DIR/$QTAV_OUT
-
-
-PKG=$TRAVIS_BUILD_DIR/${QTAV_OUT}-QMLPlayer.dmg
-mv QtAV-QMLPlayer.dmg $PKG
+PKG=$TRAVIS_BUILD_DIR/${QTAV_OUT}-Player.dmg
+set -ev
+cd $QTAV_OUT
+chmod +x *.sh
+./sdk_install.sh
+mkdir -p bin/Player.app/Contents/Resources/qml/QtAV
+cp -avf lib_*/*.dylib bin/Player.app/Contents/Resources/qml/QtAV
+cp -avf $TRAVIS_BUILD_DIR/qml/{plugins.qmltypes,Video.qml,qmldir} bin/Player.app/Contents/Resources/qml/QtAV
+cp -avf $TRAVIS_BUILD_DIR/tools/sdk_osx.sh bin/Player.app/
+cd bin
+macdeployqt Player.app -dmg
+hdiutil convert -format UDBZ Player.dmg -o $PKG
+cd -
 
 wget http://sourceforge.net/projects/sshpass/files/sshpass/1.05/sshpass-1.05.tar.gz/download -O sshpass.tar.gz
 tar zxf sshpass.tar.gz
@@ -19,3 +23,5 @@
 type -a sshpass
 # ignore known hosts: -o StrictHostKeyChecking=no
 sshpass -p $SF_PWD scp -o StrictHostKeyChecking=no $PKG $SF_USER,qtav@frs.sourceforge.net:/home/frs/project/q/qt/qtav/ci/
+
+exit 0

QtAV-1.11.0.tar.gz/tools/ci/win/build.bat -> QtAV-1.12.0.tar.gz/tools/ci/win/build.bat Changed

QtAV-1.11.0.tar.gz/tools/deploy_osx.sh -> QtAV-1.12.0.tar.gz/tools/deploy_osx.sh Changed

QtAV-1.11.0.tar.gz/tools/install_sdk/install_sdk.pro -> QtAV-1.12.0.tar.gz/tools/install_sdk/install_sdk.pro Changed

@@ -54,20 +54,25 @@
 mac: DEBUG_SUF=_debug
 win32: DEBUG_SUF=d
 NAME_SUF=
-iphonesimulator: NAME_SUF=_iphonesimulator
+iphonesimulator:!device: NAME_SUF=_iphonesimulator
 defineTest(createForModule) {
   MODULE_NAME = $$1
   MODULE_FULL_NAME = Qt$$MODULE_NAME
   MODULE = $$lower($$MODULE_NAME)
   MODULE_DEPENDS = $$eval($${MODULE}.depends)
   MODULE_DEFINES = QT_$$upper($${MODULE})_LIB
-ORIG_LIB = $${LIBPREFIX}$$qtLibName($$MODULE_FULL_NAME, $$QTAV_MAJOR_VERSION).$${LIBSUFFIX}
-ORIG_LIB_D = $${LIBPREFIX}$$qtLibName($$MODULE_FULL_NAME$${DEBUG_SUF}, $$QTAV_MAJOR_VERSION).$${LIBSUFFIX}
+  static {
+    ORIG_LIB = $${LIBPREFIX}$${MODULE_FULL_NAME}.$${LIBSUFFIX}
+    ORIG_LIB_D = $${LIBPREFIX}$${MODULE_FULL_NAME}.$${LIBSUFFIX}
+  } else {
+    ORIG_LIB = $${LIBPREFIX}$$qtLibName($$MODULE_FULL_NAME, $$QTAV_MAJOR_VERSION).$${LIBSUFFIX}
+    ORIG_LIB_D = $${LIBPREFIX}$$qtLibName($$MODULE_FULL_NAME$${DEBUG_SUF}, $$QTAV_MAJOR_VERSION).$${LIBSUFFIX}
+  }
 greaterThan(QT_MAJOR_VERSION, 4) {
   MODULE_PRF_FILE = $$OUT_PWD/mkspecs/features/$${MODULE}.prf
   NEW_LIB = $${LIBPREFIX}Qt$${QT_MAJOR_VERSION}$${MODULE_NAME}$${NAME_SUF}.$${LIBSUFFIX}
   NEW_LIB_D = $${LIBPREFIX}Qt$${QT_MAJOR_VERSION}$${MODULE_NAME}$${NAME_SUF}$${DEBUG_SUF}.$${LIBSUFFIX}
-  MKSPECS_DIR = $$[QT_INSTALL_BINS]/../mkspecs
+  MKSPECS_DIR = $$[QT_HOST_DATA]/mkspecs
 } else {
   MODULE_PRF_FILE = $$PWD/qt4/$${MODULE}.prf
   NEW_LIB = $${ORIG_LIB}
@@ -78,6 +83,7 @@
 # copy files to a dir need '/' at the end
 mac_framework {
   sdk_install.commands = $$quote($$COPY_DIR $$system_path($$PROJECT_LIBDIR/$${MODULE_FULL_NAME}.framework) $$system_path($$[QT_INSTALL_LIBS]))
+  sdk_install.commands += $$quote($$RM $$system_path($$[QT_INSTALL_LIBS])/$${MODULE_FULL_NAME}.framework/*.prl)
 } else {
   sdk_install.commands = $$quote($$MKDIR $$system_path($$[QT_INSTALL_HEADERS]/$${MODULE_FULL_NAME}/))
   sdk_install.commands += $$quote($$COPY $$system_path($$PROJECT_LIBDIR/*Qt*AV*.$$LIBSUFFIX*) $$system_path($$[QT_INSTALL_LIBS]/))
@@ -117,6 +123,7 @@
 AV_PRF_CONT += "QTAV_MINOR_VERSION=$$QTAV_MINOR_VERSION"
 AV_PRF_CONT += "QTAV_PATCH_VERSION=$$QTAV_PATCH_VERSION"
 AV_PRF_CONT += "android: QMAKE_LFLAGS += -lOpenSLES"
+AV_PRF_CONT += "static: DEFINES += BUILD_QT$$upper($${MODULE})_STATIC"
 #AV_PRF_CONT += "QMAKE_LFLAGS += -lavutil -lavcodec -lavformat -lswscale"
 #config_avresample: AV_PRF_CONT += "QMAKE_LFLAGS += -lavresample"
 #config_swresample: AV_PRF_CONT += "QMAKE_LFLAGS += -lswresample"

QtAV-1.12.0.tar.gz/tools/qtav_app_template.pro Added

QtAV-1.12.0.tar.gz/widgets/CMakeLists.txt Added

@@ -0,0 +1,102 @@
+set(MODULE QtAVWidgets)
+set(EXTRA_DEFS -DBUILD_QTAVWIDGETS_LIB)
+list(APPEND EXTRA_DEFS -DQTAV_HAVE_GL=1)
+
+set(HAVE_QT5OPENGL 0)
+if(BUILD_QT5OPENGL)
+ find_package(Qt5OpenGL)
+ if(Qt5OpenGL_FOUND)
+ set(HAVE_QT5OPENGL 1)
+ endif()
+endif()
+
+set(SDK_HEADERS
+ QtAVWidgets/global.h
+ QtAVWidgets/GraphicsItemRenderer.h
+ QtAVWidgets/OpenGLWidgetRenderer.h
+ QtAVWidgets/QtAVWidgets
+ QtAVWidgets/QtAVWidgets.h
+ QtAVWidgets/version.h
+ QtAVWidgets/VideoPreviewWidget.h
+ QtAVWidgets/WidgetRenderer.h
+)
+file(GLOB SDK_PRIVATE_HEADERS QtAVWidgets/*.h)
+
+set(SOURCES
+ global.cpp
+ GraphicsItemRenderer.cpp
+ OpenGLWidgetRenderer.cpp
+ VideoPreviewWidget.cpp
+ WidgetRenderer.cpp
+)
+if(HAVE_QT5OPENGL)
+ list(APPEND SDK_HEADERS QtAVWidgets/GLWidgetRenderer2.h)
+ list(APPEND SOURCES GLWidgetRenderer2.cpp)
+endif()
+
+# TODO: Qt5Gui_OPENGL_IMPLEMENTATION?
+if(Qt5Gui_VERSION VERSION_LESS 5.4.0)
+ list(APPEND SDK_HEADERS QtAVWidgets/QOpenGLWidget.h)
+ list(APPEND SOURCES QOpenGLWidget.cpp)
+endif()
+
+set(HEADERS ${SDK_HEADERS})
+if(WIN32)
+ set(RC_FILE ${CMAKE_CURRENT_BINARY_DIR}/${MODULE}.rc)
+ configure_file(${CMAKE_SOURCE_DIR}/cmake/QtAV.rc.in ${RC_FILE})
+endif()
+# add HEADERS for moc
+add_library(${MODULE} SHARED ${SOURCES} ${RESOURCES_SOURCES} ${HEADERS} ${RC_FILE})
+target_link_libraries(${MODULE}
+ LINK_PRIVATE ${EXTRA_LIBS}
+ LINK_PUBLIC QtAV Qt5::Widgets
+)
+if(HAVE_QT5OPENGL)
+ target_link_libraries(${MODULE} LINK_PUBLIC Qt5::OpenGL)
+endif()
+set_target_properties(${MODULE} PROPERTIES
+ MACOSX_RPATH ON
+ FRAMEWORK ON
+ VERSION ${PROJECT_VERSION}
+ SOVERSION ${SO_VERSION}
+ OUTPUT_NAME ${MODULE}
+ CLEAN_DIRECT_OUTPUT 1
+ #LINK_SEARCH_START_STATIC 1
+ LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib
+)
+
+
+#http://stackoverflow.com/questions/19866424/cmake-and-qt5-automoc-error
+#http://doc.qt.io/qt-5/cmake-manual.html
+set(CMAKE_INCLUDE_CURRENT_DIR ON) # for .moc
+target_include_directories(${MODULE}
+ PUBLIC $<INSTALL_INTERFACE:include>
+ PUBLIC $<INSTALL_INTERFACE:include/${MODULE}>
+ PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}>
+ PUBLIC $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/${MODULE}>
+ PRIVATE ${EXTRA_INCLUDE}
+ )
+target_compile_definitions(${MODULE} PRIVATE ${EXTRA_DEFS})
+
+
+install(FILES
+ ${SDK_HEADERS}
+ DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}
+)
+install(FILES
+ ${SDK_PRIVATE_HEADERS}
+ DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}/private
+)
+install(TARGETS ${MODULE}
+ EXPORT ${MODULE}-targets
+ #PUBLIC_HEADER DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}
+ #PRIVATE_HEADER DESTINATION ${QTAV_INSTALL_HEADERS}/${MODULE}/private
+ RUNTIME DESTINATION ${QTAV_INSTALL_BINS}
+ LIBRARY DESTINATION ${QTAV_INSTALL_LIBS}
+ ARCHIVE DESTINATION ${QTAV_INSTALL_LIBS}
+ FRAMEWORK DESTINATION ${QTAV_INSTALL_LIBS}
+)
+install(EXPORT ${MODULE}-targets
+ DESTINATION ${QTAV_INSTALL_LIBS}/cmake/${MODULE}
+ FILE ${MODULE}-config.cmake
+)

QtAV-1.11.0.tar.gz/widgets/Direct2DRenderer.cpp -> QtAV-1.12.0.tar.gz/widgets/Direct2DRenderer.cpp Changed

@@ -25,7 +25,6 @@
 #include <QtCore/QLibrary>
 #include "QtAV/private/VideoRenderer_p.h"
 #include "QtAV/private/factory.h"
-
 //#define CINTERFACE //http://rxlib.ru/faqs/faqc_en/15596.html
 #include <sal.h>
 #ifndef _Out_writes_bytes_opt_
@@ -226,8 +225,10 @@
 bitmap_width = w;
 bitmap_height = h;
 qDebug("Resize bitmap to %d x %d", w, h);
- D2D1_SIZE_U s = {(UINT32)w, (UINT32)h};
 SafeRelease(&bitmap);
+ if (w ==0 || h == 0)
+ return true;
+ D2D1_SIZE_U s = {(UINT32)w, (UINT32)h};
 HRESULT hr = render_target->CreateBitmap(s
 , NULL
 , 0
@@ -296,9 +297,11 @@
 
 bool Direct2DRenderer::receiveFrame(const VideoFrame& frame)
 {
- if (!frame.isValid())
- return false;
 DPTR_D(Direct2DRenderer);
+ if (!frame.isValid()) {
+ //d.prepareBitmap(0, 0);
+ return false;
+ }
 if (!d.prepareBitmap(frame.width(), frame.height()))
 return false;
 HRESULT hr = S_OK;
@@ -344,18 +347,20 @@
 void Direct2DRenderer::drawFrame()
 {
 DPTR_D(Direct2DRenderer);
+ if (!d.bitmap || d.out_rect.isEmpty())
+ return;
 D2D1_RECT_F out_rect = {
- (FLOAT)d.out_rect.left(),
- (FLOAT)d.out_rect.top(),
- (FLOAT)d.out_rect.right(),
- (FLOAT)d.out_rect.bottom()
+ (FLOAT)d.out_rect.x(),
+ (FLOAT)d.out_rect.y(),
+ (FLOAT)(d.out_rect.x() + d.out_rect.width()), // QRect.right() is x+width-1 for historical reason
+ (FLOAT)(d.out_rect.y() + d.out_rect.height())
 };
 QRect roi = realROI();
 D2D1_RECT_F roi_d2d = {
- (FLOAT)roi.left(),
- (FLOAT)roi.top(),
- (FLOAT)roi.right(),
- (FLOAT)roi.bottom()
+ (FLOAT)roi.x(),
+ (FLOAT)roi.y(),
+ (FLOAT)(roi.x() + roi.width()),
+ (FLOAT)(roi.y() + roi.height())
 };
 //d.render_target->SetTransform
 d.render_target->DrawBitmap(d.bitmap

QtAV-1.11.0.tar.gz/widgets/GLWidgetRenderer2.cpp -> QtAV-1.12.0.tar.gz/widgets/GLWidgetRenderer2.cpp Changed

QtAV-1.11.0.tar.gz/widgets/OpenGLWidgetRenderer.cpp -> QtAV-1.12.0.tar.gz/widgets/OpenGLWidgetRenderer.cpp Changed

@@ -21,7 +21,9 @@
 
 #include "QtAVWidgets/OpenGLWidgetRenderer.h"
 #include "QtAV/private/OpenGLRendererBase_p.h"
-#include <QResizeEvent>
+#include <QtGui/QGuiApplication>
+#include <QtGui/QResizeEvent>
+#include <QtGui/QScreen>
 
 namespace QtAV {
 
@@ -58,7 +60,19 @@
 
 void OpenGLWidgetRenderer::resizeGL(int w, int h)
 {
- onResizeGL(w, h);
+ // QGLWidget uses window()->windowHandle()->devicePixelRatio() for resizeGL(), while QOpenGLWidget does not, so scale here
+#if QT_VERSION >= QT_VERSION_CHECK(5, 5, 0)
+ if (!context())
+ return;
+ const qreal dpr = context()->screen()->devicePixelRatio();
+#elif QT_VERSION >= QT_VERSION_CHECK(5, 1, 0)
+ // qApp->devicePixelRatio() is global, window()->windowHandle()->devicePixelRatio() depends on screen, check window() and windowHandle() is required.
+ // QWidget.devicePixelRatio() is int, but float value is not implemented in old qt, so just use int is fine.
+ const qreal dpr = devicePixelRatio();
+#else
+ const qreal dpr = qApp->devicePixelRatio();
+#endif
+ onResizeGL(w*dpr, h*dpr);
 }
 
 void OpenGLWidgetRenderer::resizeEvent(QResizeEvent *e)
@@ -67,9 +81,9 @@
 QOpenGLWidget::resizeEvent(e); //will call resizeGL(). TODO:will call paintEvent()?
 }
 
-void OpenGLWidgetRenderer::showEvent(QShowEvent *)
+void OpenGLWidgetRenderer::showEvent(QShowEvent *e)
 {
- onShowEvent();
+ onShowEvent(); // TODO: onShowEvent(w, h)?
+ resizeGL(width(), height());
 }
-
 } //namespace QtAV

QtAV-1.11.0.tar.gz/widgets/global.cpp -> QtAV-1.12.0.tar.gz/widgets/global.cpp Changed

QtAV-1.11.0.tar.gz/widgets/libQtAVWidgets.pri -> QtAV-1.12.0.tar.gz/widgets/libQtAVWidgets.pri Changed

QtAV-1.11.0.tar.gz/widgets/libQtAVWidgets.pro -> QtAV-1.12.0.tar.gz/widgets/libQtAVWidgets.pro Changed

@@ -13,7 +13,6 @@
   }
 }
 CONFIG *= qtavwidgets-buildlib
-staticlib: DEFINES += BUILD_QTAVWIDGETS_STATIC
 
 INCLUDEPATH += $$[QT_INSTALL_HEADERS]
 #release: DEFINES += QT_NO_DEBUG_OUTPUT
@@ -27,7 +26,7 @@
     RC_ICONS = $$PROJECTROOT/src/QtAV.ico
     QMAKE_TARGET_COMPANY = "Shanghai University->S3 Graphics->Deepin | wbsecg1@gmail.com"
     QMAKE_TARGET_DESCRIPTION = "QtAVWidgets module. QtAV Multimedia framework. http://qtav.org"
-    QMAKE_TARGET_COPYRIGHT = "Copyright (C) 2012-2016 WangBin, wbsecg1@gmail.com"
+    QMAKE_TARGET_COPYRIGHT = "Copyright (C) 2012-2017 WangBin, wbsecg1@gmail.com"
     QMAKE_TARGET_PRODUCT = "QtAV Widgets"
 } else:win32 {
     RC_FILE = QtAVWidgets.rc
@@ -151,7 +150,8 @@
 
 DEB_INSTALL_LIST = $$join(SDK_HEADERS, \\n.$$[QT_INSTALL_HEADERS]/, .$$[QT_INSTALL_HEADERS]/)
 DEB_INSTALL_LIST += .$$[QT_INSTALL_LIBS]/libQt*AVWidgets.prl .$$[QT_INSTALL_LIBS]/libQt*AVWidgets.so
-DEB_INSTALL_LIST += .$$[QT_INSTALL_BINS]/../mkspecs/features/avwidgets.prf .$$[QT_INSTALL_BINS]/../mkspecs/modules/qt_lib_avwidgets.pri
+MKSPECS_DIR=$$[QT_HOST_DATA]/mkspecs
+DEB_INSTALL_LIST += .$${MKSPECS_DIR}/features/avwidgets.prf .$${MKSPECS_DIR}/modules/qt_lib_avwidgets.pri
 qtavwidgets_dev.target = qtav-dev.install #like qtmultimedia5-dev, contains widgets headers
 qtavwidgets_dev.commands = echo \"$$join(DEB_INSTALL_LIST, \\n)\" >>$$PROJECTROOT/debian/$${qtavwidgets_dev.target}
 QMAKE_EXTRA_TARGETS += qtavwidgets_dev

Overview

Request 3848 (accepted)

Request History