Packman Build Service PMBS

x265.changes Changed

@@ -1,35 +1,4 @@
 -------------------------------------------------------------------
-Thu Mar  1 23:14:47 UTC 2018 - zaitor@opensuse.org
-
-- Update to version 2.7:
-  * New features:
-    - option:`--gop-lookahead` can be used to extend the gop
-      boundary(set by `--keyint`). The GOP will be extended, if a
-      scene-cut frame is found within this many number of frames.
-    - Support for RADL pictures added in x265.
-    - option:`--radl` can be used to decide number of RADL pictures
-      preceding the IDR picture.
-  * Encoder enhancements:
-    - Moved from YASM to NASM assembler. Supports NASM assembler
-      version 2.13 and greater.
-    - Enable analysis save and load in a single run. Introduces two
-      new cli options `--analysis-save <filename>` and
-      `--analysis-load <filename>`.
-    - Comply to HDR10+ LLC specification.
-    - Reduced x265 build time by more than 50% by re-factoring
-      ipfilter.asm.
-  * Bug fixes:
-    - Fixed inconsistent output issue in deblock filter and
-      --const-vbv.
-    - Fixed Mac OS build warnings.
-    - Fixed inconsistency in pass-2 when weightp and cutree are
-      enabled.
-    - Fixed deadlock issue due to dropping of BREF frames, while
-      forcing slice types through qp file.
-- Bump soname to 151, also in baselibs.conf following upstream
-  changes.
-
--------------------------------------------------------------------
 Fri Dec 01 16:40:13 UTC 2017 - joerg.lorenzen@ki.tng.de
 
 - Update to version 2.6

x265.spec Changed

baselibs.conf Changed

x265_2.7.tar.gz/.hg_archival.txt -> x265_2.6.tar.gz/.hg_archival.txt Changed

x265_2.7.tar.gz/.hgtags -> x265_2.6.tar.gz/.hgtags Changed

x265_2.7.tar.gz/build/README.txt -> x265_2.6.tar.gz/build/README.txt Changed

@@ -9,8 +9,7 @@
 
 = Optional Prerequisites =
 
-1. To compile assembly primitives (performance) 
-   a) If you are using release 2.6 or older, download and install Yasm 1.2.0 or later, 
+1. Yasm 1.2.0 or later, to compile assembly primitives (performance)
 
    For Windows, download the latest yasm executable
    http://yasm.tortall.net/Download.html and copy the EXE into
@@ -34,24 +33,6 @@
    If cpu capabilities line says 'none!', then the encoder was built
    without yasm.
 
-   b) If you are building from the default branch after release 2.6, download and install nasm 2.13 or newer
-   
-   For windows and linux, you can download the nasm installer from http://www.nasm.us/pub/nasm/releasebuilds/?C=M;O=D.
-   Make sure that it is in your PATH environment variable (%PATH% in windows, and $PATH in linux) so that cmake
-   can find it.
-
-   Once NASM is properly installed, run cmake to regenerate projects. If you
-   do not see the below line in the cmake output, NASM is not in the PATH.
-
-   -- Found Nasm 2.13 to build assembly primitives
-
-   Now build the encoder and run x265 -V:
-
-   x265 [info]: using cpu capabilities: MMX, SSE2, ...
-
-   If cpu capabilities line says 'none!', then the encoder was built
-   without nasm and will be considerably slower for performance.
-
 2. VisualLeakDetector (Windows Only)
 
    Download from https://vld.codeplex.com/releases and install. May need

x265_2.7.tar.gz/doc/reST/api.rst -> x265_2.6.tar.gz/doc/reST/api.rst Changed

x265_2.7.tar.gz/doc/reST/cli.rst -> x265_2.6.tar.gz/doc/reST/cli.rst Changed

@@ -863,22 +863,21 @@
 sequence multiple times (presumably at varying bitrates). The encoder
 will not reuse analysis if slice type parameters do not match.
 
-.. option:: --analysis-save <filename>
+.. option:: --analysis-reuse-mode <string|int>
 
-	Encoder outputs analysis information of each frame. Analysis data from save mode is
-	written to the file specified. Requires cutree, pmode to be off. Default disabled.
-	
-.. option:: --analysis-load <filename>
-
-	Encoder reuses analysis information from the file specified. By reading the analysis data writen by
-	an earlier encode of the same sequence, substantial redundant work may be avoided. Requires cutree, pmode
-	to be off. Default disabled.
+	This option allows reuse of analysis information from first pass to second pass.
+	:option:`--analysis-reuse-mode save` specifies that encoder outputs analysis information of each frame.
+	:option:`--analysis-reuse-mode load` specifies that encoder reuses analysis information from first pass.
+	There is no benefit using load mode without running encoder in save mode. Analysis data from save mode is
+	written to a file specified by :option:`--analysis-reuse-file`. The amount of analysis data stored/reused
+	is determined by :option:`--analysis-reuse-level`. By reading the analysis data writen by an earlier encode
+	of the same sequence, substantial redundant work may be avoided. Requires cutree, pmode to be off. Default 0.
 
-	The amount of analysis data stored/reused is determined by :option:`--analysis-reuse-level`.
+	**Values:** off(0), save(1): dump analysis data, load(2): read analysis data
 
 .. option:: --analysis-reuse-file <filename>
 
-	Specify a filename for `multi-pass-opt-analysis` and `multi-pass-opt-distortion`.
+	Specify a filename for analysis data (see :option:`--analysis-reuse-mode`)
 	If no filename is specified, x265_analysis.dat is used.
 
 .. option:: --analysis-reuse-level <1..10>
@@ -1029,13 +1028,7 @@
 	Level 4 - uses the depth of the neighbouring/ co-located CUs TU depth 
 	to limit the 1st subTU depth. The 1st subTU depth is taken as the 
 	limiting depth for the other subTUs.
-	
-	Enabling levels 3 or 4 may cause a mismatch in the output bitstreams 
-	between option:`--analysis-save` and option:`--analysis-load`
-	as all neighbouring CUs TU depth may not be available in the 
-	option:`--analysis-load` run as only the best mode's information is 
-	available to it.
-	
+
 	Default: 0
 
 .. option:: --nr-intra <integer>, --nr-inter <integer>
@@ -1351,14 +1344,7 @@
 	This value represents the percentage difference between the inter cost and
 	intra cost of a frame used in scenecut detection. For example, a value of 5 indicates,
 	if the inter cost of a frame is greater than or equal to 95 percent of the intra cost of the frame,
-	then detect this frame as scenecut. Values between 5 and 15 are recommended. Default 5.
-	
-.. option:: --radl <integer>
-	
-	Number of RADL pictures allowed infront of IDR. Requires fixed keyframe interval.
-	Recommended value is 2-3. Default 0 (disabled).
-	
-	**Range of values: Between 0 and `--bframes`
+	then detect this frame as scenecut. Values between 5 and 15 are recommended. Default 5.	
 
 .. option:: --ctu-info <0, 1, 2, 4, 6>
 
@@ -1387,16 +1373,6 @@
 	Default 20
 
 	**Range of values:** Between the maximum consecutive bframe count (:option:`--bframes`) and 250
-.. option:: --gop-lookahead <integer>
-
-        Number of frames for GOP boundary decision lookahead. If a scenecut frame is found
-        within this from the gop boundary set by `--keyint`, the GOP will be extented until such a point,
-        otherwise the GOP will be terminated as set by `--keyint`. Default 0.
-
-        **Range of values:** Between 0 and (`--rc-lookahead` - mini-GOP length)
-
-        It is recommended to have `--gop-lookahaed` less than `--min-keyint` as scenecuts beyond
-        `--min-keyint` are already being coded as keyframes.
 
 .. option:: --lookahead-slices <0..16>
 
@@ -2064,7 +2040,7 @@
 	Example for MaxCLL=1000 candela per square meter, MaxFALL=400
 	candela per square meter:
 
-		--max-cll "1000,400"
+		--max-cll 1000,400
 
 	Note that this string value will need to be escaped or quoted to
 	protect against shell expansion on many platforms. No default.

x265_2.7.tar.gz/doc/reST/releasenotes.rst -> x265_2.6.tar.gz/doc/reST/releasenotes.rst Changed

@@ -2,32 +2,6 @@
 Release Notes
 *************
 
-Version 2.7
-===========
-
-Release date - 21st Feb, 2018.
-
-New features
-------------
-1. :option:`--gop-lookahead` can be used to extend the gop boundary(set by `--keyint`). The GOP will be extended, if a scene-cut frame is found within this many number of frames. 
-2. Support for RADL pictures added in x265.
-   :option:`--radl` can be used to decide number of RADL pictures preceding the IDR picture.
-
-Encoder enhancements
---------------------
-1. Moved from YASM to NASM assembler. Supports NASM assembler version 2.13 and greater.
-2. Enable analysis save and load in a single run. Introduces two new cli options `--analysis-save <filename>` and `--analysis-load <filename>`.
-3. Comply to HDR10+ LLC specification.
-4. Reduced x265 build time by more than 50% by re-factoring ipfilter.asm.  
-
-Bug fixes
----------
-1. Fixed inconsistent output issue in deblock filter and --const-vbv.
-2. Fixed Mac OS build warnings.
-3. Fixed inconsistency in pass-2 when weightp and cutree are enabled.
-4. Fixed deadlock issue due to dropping of BREF frames, while forcing slice types through qp file.
-
-
 Version 2.6
 ===========

x265_2.7.tar.gz/source/CMakeLists.txt -> x265_2.6.tar.gz/source/CMakeLists.txt Changed

@@ -29,7 +29,7 @@
 option(STATIC_LINK_CRT "Statically link C runtime for release builds" OFF)
 mark_as_advanced(FPROFILE_USE FPROFILE_GENERATE NATIVE_BUILD)
 # X265_BUILD must be incremented each time the public API is changed
-set(X265_BUILD 151)
+set(X265_BUILD 146)
 configure_file("${PROJECT_SOURCE_DIR}/x265.def.in"
                "${PROJECT_BINARY_DIR}/x265.def")
 configure_file("${PROJECT_SOURCE_DIR}/x265_config.h.in"
@@ -323,15 +323,15 @@
     execute_process(COMMAND ${CMAKE_CXX_COMPILER} -dumpversion OUTPUT_VARIABLE CC_VERSION)
 endif(GCC)
 
-find_package(Nasm)
+find_package(Yasm)
 if(ARM OR CROSS_COMPILE_ARM)
     option(ENABLE_ASSEMBLY "Enable use of assembly coded primitives" ON)
-elseif(NASM_FOUND AND X86)
-    if (NASM_VERSION_STRING VERSION_LESS "2.13.0")
-        message(STATUS "Nasm version ${NASM_VERSION_STRING} is too old. 2.13.0 or later required")
+elseif(YASM_FOUND AND X86)
+    if (YASM_VERSION_STRING VERSION_LESS "1.2.0")
+        message(STATUS "Yasm version ${YASM_VERSION_STRING} is too old. 1.2.0 or later required")
         option(ENABLE_ASSEMBLY "Enable use of assembly coded primitives" OFF)
     else()
-        message(STATUS "Found Nasm ${NASM_VERSION_STRING} to build assembly primitives")
+        message(STATUS "Found Yasm ${YASM_VERSION_STRING} to build assembly primitives")
         option(ENABLE_ASSEMBLY "Enable use of assembly coded primitives" ON)
     endif()
 else()
@@ -517,18 +517,18 @@
             list(APPEND ASM_OBJS ${ASM}.${SUFFIX})
             add_custom_command(
                 OUTPUT ${ASM}.${SUFFIX}
-                COMMAND ${NASM_EXECUTABLE} ARGS ${NASM_FLAGS} ${ASM_SRC} -o ${ASM}.${SUFFIX}
+                COMMAND ${YASM_EXECUTABLE} ARGS ${YASM_FLAGS} ${ASM_SRC} -o ${ASM}.${SUFFIX}
                 DEPENDS ${ASM_SRC})
         endforeach()
     endif()
 endif()
 source_group(ASM FILES ${ASM_SRCS})
 if(ENABLE_HDR10_PLUS)
-    add_library(x265-static STATIC $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> $<TARGET_OBJECTS:dynamicHDR10> ${ASM_OBJS})
+    add_library(x265-static STATIC $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> $<TARGET_OBJECTS:dynamicHDR10> ${ASM_OBJS} ${ASM_SRCS})
     add_library(hdr10plus-static STATIC $<TARGET_OBJECTS:dynamicHDR10>)
     set_target_properties(hdr10plus-static PROPERTIES OUTPUT_NAME hdr10plus)
 else()
-    add_library(x265-static STATIC $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> ${ASM_OBJS})
+    add_library(x265-static STATIC $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> ${ASM_OBJS} ${ASM_SRCS})
 endif()
 if(NOT MSVC)
     set_target_properties(x265-static PROPERTIES OUTPUT_NAME x265)
@@ -546,19 +546,14 @@
         ARCHIVE DESTINATION ${LIB_INSTALL_DIR})
 endif()
 install(FILES x265.h "${PROJECT_BINARY_DIR}/x265_config.h" DESTINATION include)
+
 if(WIN32)
-    if(MSVC_IDE)
-        install(FILES "${PROJECT_BINARY_DIR}/Debug/x265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS Debug)
-        install(FILES "${PROJECT_BINARY_DIR}/RelWithDebInfo/x265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS RelWithDebInfo)
-        install(FILES "${PROJECT_BINARY_DIR}/Debug/libx265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS Debug OPTIONAL NAMELINK_ONLY)
-        install(FILES "${PROJECT_BINARY_DIR}/RelWithDebInfo/libx265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS RelWithDebInfo OPTIONAL NAMELINK_ONLY)
-    else()
-        install(FILES "${PROJECT_BINARY_DIR}/x265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS Debug)
-        install(FILES "${PROJECT_BINARY_DIR}/x265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS RelWithDebInfo)
-        install(FILES "${PROJECT_BINARY_DIR}/libx265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS Debug OPTIONAL NAMELINK_ONLY)
-        install(FILES "${PROJECT_BINARY_DIR}/libx265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS RelWithDebInfo OPTIONAL NAMELINK_ONLY)
-    endif()
+    install(FILES "${PROJECT_BINARY_DIR}/Debug/x265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS Debug)
+    install(FILES "${PROJECT_BINARY_DIR}/RelWithDebInfo/x265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS RelWithDebInfo)
+    install(FILES "${PROJECT_BINARY_DIR}/Debug/libx265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS Debug OPTIONAL NAMELINK_ONLY)
+    install(FILES "${PROJECT_BINARY_DIR}/RelWithDebInfo/libx265.pdb" DESTINATION ${BIN_INSTALL_DIR} CONFIGURATIONS RelWithDebInfo OPTIONAL NAMELINK_ONLY)
 endif()
+
 if(CMAKE_RC_COMPILER)
     # The resource compiler does not need CFLAGS or macro defines. It
     # often breaks them
@@ -647,9 +642,7 @@
     endforeach()
     if(PLIBLIST)
         # blacklist of libraries that should not be in Libs.private
-        list(REMOVE_ITEM PLIBLIST "-lc" "-lpthread" "-lmingwex" "-lmingwthrd"
-            "-lmingw32" "-lmoldname" "-lmsvcrt" "-ladvapi32" "-lshell32"
-            "-luser32" "-lkernel32")
+        list(REMOVE_ITEM PLIBLIST "-lc" "-lpthread")
         string(REPLACE ";" " " PRIVATE_LIBS "${PLIBLIST}")
     else()
         set(PRIVATE_LIBS "")
@@ -693,11 +686,11 @@
         if(ENABLE_HDR10_PLUS)
         add_executable(cli ../COPYING ${InputFiles} ${OutputFiles} ${GETOPT}
                         x265.cpp x265.h x265cli.h
-                        $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> $<TARGET_OBJECTS:dynamicHDR10> ${ASM_OBJS})
+                        $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> $<TARGET_OBJECTS:dynamicHDR10> ${ASM_OBJS} ${ASM_SRCS})
         else()
             add_executable(cli ../COPYING ${InputFiles} ${OutputFiles} ${GETOPT}
                         x265.cpp x265.h x265cli.h
-                        $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> ${ASM_OBJS})
+                        $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> ${ASM_OBJS} ${ASM_SRCS})
         endif()
     else()
         add_executable(cli ../COPYING ${InputFiles} ${OutputFiles} ${GETOPT} ${X265_RC_FILE}

x265_2.6.tar.gz/source/cmake/CMakeASM_YASMInformation.cmake Added

@@ -0,0 +1,68 @@
+set(ASM_DIALECT "_YASM")
+set(CMAKE_ASM${ASM_DIALECT}_SOURCE_FILE_EXTENSIONS asm)
+
+if(X64)
+    list(APPEND ASM_FLAGS -DARCH_X86_64=1)
+    if(ENABLE_PIC)
+        list(APPEND ASM_FLAGS -DPIC)
+    endif()
+    if(APPLE)
+        set(ARGS -f macho64 -m amd64 -DPREFIX)
+    elseif(UNIX AND NOT CYGWIN)
+        set(ARGS -f elf64 -m amd64)
+    else()
+        set(ARGS -f win64 -m amd64)
+    endif()
+else()
+    list(APPEND ASM_FLAGS -DARCH_X86_64=0)
+    if(APPLE)
+        set(ARGS -f macho -DPREFIX)
+    elseif(UNIX AND NOT CYGWIN)
+        set(ARGS -f elf32)
+    else()
+        set(ARGS -f win32 -DPREFIX)
+    endif()
+endif()
+
+if(GCC)
+    list(APPEND ASM_FLAGS -DHAVE_ALIGNED_STACK=1)
+else()
+    list(APPEND ASM_FLAGS -DHAVE_ALIGNED_STACK=0)
+endif()
+
+if(HIGH_BIT_DEPTH)
+    if(MAIN12)
+        list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=1 -DBIT_DEPTH=12 -DX265_NS=${X265_NS})
+    else()
+        list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=1 -DBIT_DEPTH=10 -DX265_NS=${X265_NS})
+    endif()
+else()
+    list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=0 -DBIT_DEPTH=8 -DX265_NS=${X265_NS})
+endif()
+
+list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS}")
+
+if(CMAKE_BUILD_TYPE MATCHES Release)
+    list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_RELEASE}")
+elseif(CMAKE_BUILD_TYPE MATCHES Debug)
+    list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_DEBUG}")
+elseif(CMAKE_BUILD_TYPE MATCHES MinSizeRel)
+    list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_MINSIZEREL}")
+elseif(CMAKE_BUILD_TYPE MATCHES RelWithDebInfo)
+    list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_RELWITHDEBINFO}")
+endif()
+
+set(YASM_FLAGS ${ARGS} ${ASM_FLAGS} PARENT_SCOPE)
+string(REPLACE ";" " " CMAKE_ASM_YASM_COMPILER_ARG1 "${ARGS}")
+
+# This section exists to override the one in CMakeASMInformation.cmake
+# (the default Information file). This removes the <FLAGS>
+# thing so that your C compiler flags that have been set via
+# set_target_properties don't get passed to yasm and confuse it.
+if(NOT CMAKE_ASM${ASM_DIALECT}_COMPILE_OBJECT)
+    string(REPLACE ";" " " STR_ASM_FLAGS "${ASM_FLAGS}")
+    set(CMAKE_ASM${ASM_DIALECT}_COMPILE_OBJECT "<CMAKE_ASM${ASM_DIALECT}_COMPILER> ${STR_ASM_FLAGS} -o <OBJECT> <SOURCE>")
+endif()
+
+include(CMakeASMInformation)
+set(ASM_DIALECT)

x265_2.6.tar.gz/source/cmake/CMakeDetermineASM_YASMCompiler.cmake Added

x265_2.6.tar.gz/source/cmake/CMakeTestASM_YASMCompiler.cmake Added

x265_2.6.tar.gz/source/cmake/FindYasm.cmake Added

x265_2.7.tar.gz/source/cmake/version.cmake -> x265_2.6.tar.gz/source/cmake/version.cmake Changed

x265_2.7.tar.gz/source/common/CMakeLists.txt -> x265_2.6.tar.gz/source/common/CMakeLists.txt Changed

@@ -56,26 +56,28 @@
     endif()
     set(VEC_PRIMITIVES vec/vec-primitives.cpp ${PRIMITIVES})
     source_group(Intrinsics FILES ${VEC_PRIMITIVES})
+
     set(C_SRCS asm-primitives.cpp pixel.h mc.h ipfilter8.h blockcopy8.h dct8.h loopfilter.h seaintegral.h)
     set(A_SRCS pixel-a.asm const-a.asm cpu-a.asm ssd-a.asm mc-a.asm
                mc-a2.asm pixel-util8.asm blockcopy8.asm
                pixeladd8.asm dct8.asm seaintegral.asm)
     if(HIGH_BIT_DEPTH)
-        set(A_SRCS ${A_SRCS} sad16-a.asm intrapred16.asm v4-ipfilter16.asm h4-ipfilter16.asm h-ipfilter16.asm ipfilter16.asm loopfilter.asm)
+        set(A_SRCS ${A_SRCS} sad16-a.asm intrapred16.asm ipfilter16.asm loopfilter.asm)
     else()
-        set(A_SRCS ${A_SRCS} sad-a.asm intrapred8.asm intrapred8_allangs.asm v4-ipfilter8.asm h-ipfilter8.asm ipfilter8.asm loopfilter.asm)
+        set(A_SRCS ${A_SRCS} sad-a.asm intrapred8.asm intrapred8_allangs.asm ipfilter8.asm loopfilter.asm)
     endif()
+
     if(NOT X64)
         set(A_SRCS ${A_SRCS} pixel-32.asm)
     endif()
 
     if(MSVC_IDE OR XCODE)
-        # MSVC requires custom build rules in the main cmake script for nasm
-        set(MSVC_ASMS "${A_SRCS}" CACHE INTERNAL "nasm sources")
+        # MSVC requires custom build rules in the main cmake script for yasm
+        set(MSVC_ASMS "${A_SRCS}" CACHE INTERNAL "yasm sources")
         set(A_SRCS)
     endif()
 
-    enable_language(ASM_NASM)
+    enable_language(ASM_YASM)
 
     foreach(SRC ${A_SRCS} ${C_SRCS})
         set(ASM_PRIMITIVES ${ASM_PRIMITIVES} x86/${SRC})

x265_2.7.tar.gz/source/common/common.h -> x265_2.6.tar.gz/source/common/common.h Changed

x265_2.7.tar.gz/source/common/cudata.cpp -> x265_2.6.tar.gz/source/common/cudata.cpp Changed

@@ -1626,7 +1626,7 @@
                 dir |= (1 << list);
                 candMvField[count][list].mv = colmv;
                 candMvField[count][list].refIdx = refIdx;
-                if (m_encData->m_param->scaleFactor && m_encData->m_param->analysisSave && m_log2CUSize[0] < 4)
+                if (m_encData->m_param->scaleFactor && m_encData->m_param->analysisReuseMode == X265_ANALYSIS_SAVE && m_log2CUSize[0] < 4)
                 {
                     MV dist(MAX_MV, MAX_MV);
                     candMvField[count][list].mv = dist;
@@ -1791,7 +1791,7 @@
             int curRefPOC = m_slice->m_refPOCList[picList][refIdx];
             int curPOC = m_slice->m_poc;
 
-            if (m_encData->m_param->scaleFactor && m_encData->m_param->analysisSave && (m_log2CUSize[0] < 4))
+            if (m_encData->m_param->scaleFactor && m_encData->m_param->analysisReuseMode == X265_ANALYSIS_SAVE && (m_log2CUSize[0] < 4))
             {
                 MV dist(MAX_MV, MAX_MV);
                 pmv[numMvc++] = amvpCand[num++] = dist;

x265_2.7.tar.gz/source/common/deblock.cpp -> x265_2.6.tar.gz/source/common/deblock.cpp Changed

@@ -207,18 +207,21 @@
     static const MV zeroMv(0, 0);
     const Slice* const sliceQ = cuQ->m_slice;
     const Slice* const sliceP = cuP->m_slice;
-    const Frame* refP0 = (cuP->m_refIdx[0][partP] >= 0) ? sliceP->m_refFrameList[0][cuP->m_refIdx[0][partP]] : NULL;
-    const Frame* refQ0 = (cuQ->m_refIdx[0][partQ] >= 0) ? sliceQ->m_refFrameList[0][cuQ->m_refIdx[0][partQ]] : NULL;
+
+    const Frame* refP0 = sliceP->m_refFrameList[0][cuP->m_refIdx[0][partP]];
+    const Frame* refQ0 = sliceQ->m_refFrameList[0][cuQ->m_refIdx[0][partQ]];
     const MV& mvP0 = refP0 ? cuP->m_mv[0][partP] : zeroMv;
     const MV& mvQ0 = refQ0 ? cuQ->m_mv[0][partQ] : zeroMv;
+
     if (sliceQ->isInterP() && sliceP->isInterP())
     {
         return ((refP0 != refQ0) ||
                 (abs(mvQ0.x - mvP0.x) >= 4) || (abs(mvQ0.y - mvP0.y) >= 4)) ? 1 : 0;
     }
+
     // (sliceQ->isInterB() || sliceP->isInterB())
-    const Frame* refP1 = (cuP->m_refIdx[1][partP] >= 0) ? sliceP->m_refFrameList[1][cuP->m_refIdx[1][partP]] : NULL;
-    const Frame* refQ1 = (cuQ->m_refIdx[1][partQ] >= 0) ? sliceQ->m_refFrameList[1][cuQ->m_refIdx[1][partQ]] : NULL;
+    const Frame* refP1 = sliceP->m_refFrameList[1][cuP->m_refIdx[1][partP]];
+    const Frame* refQ1 = sliceQ->m_refFrameList[1][cuQ->m_refIdx[1][partQ]];
     const MV& mvP1 = refP1 ? cuP->m_mv[1][partP] : zeroMv;
     const MV& mvQ1 = refQ1 ? cuQ->m_mv[1][partQ] : zeroMv;

x265_2.7.tar.gz/source/common/frame.h -> x265_2.6.tar.gz/source/common/frame.h Changed

x265_2.7.tar.gz/source/common/framedata.cpp -> x265_2.6.tar.gz/source/common/framedata.cpp Changed

@@ -40,12 +40,11 @@
     m_spsrpsIdx = -1;
     if (param.rc.bStatWrite)
         m_spsrps = const_cast<RPS*>(sps.spsrps);
-    bool isallocated = m_cuMemPool.create(0, param.internalCsp, sps.numCUsInFrame, param);
-    if (isallocated)
-        for (uint32_t ctuAddr = 0; ctuAddr < sps.numCUsInFrame; ctuAddr++)
-            m_picCTU[ctuAddr].initialize(m_cuMemPool, 0, param, ctuAddr);
-    else
-        return false;
+
+    m_cuMemPool.create(0, param.internalCsp, sps.numCUsInFrame, param);
+    for (uint32_t ctuAddr = 0; ctuAddr < sps.numCUsInFrame; ctuAddr++)
+        m_picCTU[ctuAddr].initialize(m_cuMemPool, 0, param, ctuAddr);
+
     CHECKED_MALLOC_ZERO(m_cuStat, RCStatCU, sps.numCUsInFrame);
     CHECKED_MALLOC(m_rowStat, RCStatRow, sps.numCuInHeight);
     reinit(sps);
@@ -77,12 +76,16 @@
 
     X265_FREE(m_cuStat);
     X265_FREE(m_rowStat);
-    for (int i = 0; i < INTEGRAL_PLANE_NUM; i++)
+
+    if (m_meBuffer)
     {
-        if (m_meBuffer[i] != NULL)
+        for (int i = 0; i < INTEGRAL_PLANE_NUM; i++)
         {
-            X265_FREE(m_meBuffer[i]);
-            m_meBuffer[i] = NULL;
+            if (m_meBuffer[i] != NULL)
+            {
+                X265_FREE(m_meBuffer[i]);
+                m_meBuffer[i] = NULL;
+            }
         }
     }
 }

x265_2.7.tar.gz/source/common/lowres.cpp -> x265_2.6.tar.gz/source/common/lowres.cpp Changed

x265_2.7.tar.gz/source/common/lowres.h -> x265_2.6.tar.gz/source/common/lowres.h Changed

x265_2.7.tar.gz/source/common/param.cpp -> x265_2.6.tar.gz/source/common/param.cpp Changed

@@ -144,7 +144,6 @@
     /* Coding Structure */
     param->keyframeMin = 0;
     param->keyframeMax = 250;
-    param->gopLookahead = 0;
     param->bOpenGOP = 1;
     param->bframes = 4;
     param->lookaheadDepth = 20;
@@ -154,7 +153,6 @@
     param->lookaheadSlices = 8;
     param->lookaheadThreads = 0;
     param->scenecutBias = 5.0;
-    param->radl = 0;
     /* Intra Coding Tools */
     param->bEnableConstrainedIntra = 0;
     param->bEnableStrongIntraSmoothing = 1;
@@ -198,12 +196,10 @@
     param->rdPenalty = 0;
     param->psyRd = 2.0;
     param->psyRdoq = 0.0;
-    param->analysisReuseMode = 0; /*DEPRECATED*/
+    param->analysisReuseMode = 0;
     param->analysisMultiPassRefine = 0;
     param->analysisMultiPassDistortion = 0;
     param->analysisReuseFileName = NULL;
-    param->analysisSave = NULL;
-    param->analysisLoad = NULL;
     param->bIntraInBFrames = 0;
     param->bLossless = 0;
     param->bCULossless = 0;
@@ -853,7 +849,7 @@
         p->rc.bStrictCbr = atobool(value);
         p->rc.pbFactor = 1.0;
     }
-    OPT("analysis-reuse-mode") p->analysisReuseMode = parseName(value, x265_analysis_names, bError); /*DEPRECATED*/
+    OPT("analysis-reuse-mode") p->analysisReuseMode = parseName(value, x265_analysis_names, bError);
     OPT("sar")
     {
         p->vui.aspectRatioIdc = parseName(value, x265_sar_names, bError);
@@ -1008,10 +1004,6 @@
                 bError = true;
             }
          }
-        OPT("gop-lookahead") p->gopLookahead = atoi(value);
-        OPT("analysis-save") p->analysisSave = strdup(value);
-        OPT("analysis-load") p->analysisLoad = strdup(value);
-        OPT("radl") p->radl = atoi(value);
         else
             return X265_PARAM_BAD_NAME;
     }
@@ -1318,14 +1310,10 @@
           "scenecutThreshold must be greater than 0");
     CHECK(param->scenecutBias < 0 || 100 < param->scenecutBias,
            "scenecut-bias must be between 0 and 100");
-    CHECK(param->radl < 0 || param->radl > param->bframes,
-          "radl must be between 0 and bframes");
     CHECK(param->rdPenalty < 0 || param->rdPenalty > 2,
           "Valid penalty for 32x32 intra TU in non-I slices. 0:disabled 1:RD-penalty 2:maximum");
     CHECK(param->keyframeMax < -1,
           "Invalid max IDR period in frames. value should be greater than -1");
-    CHECK(param->gopLookahead < -1,
-          "GOP lookahead must be greater than -1");
     CHECK(param->decodedPictureHashSEI < 0 || param->decodedPictureHashSEI > 3,
           "Invalid hash option. Decoded Picture Hash SEI 0: disabled, 1: MD5, 2: CRC, 3: Checksum");
     CHECK(param->rc.vbvBufferSize < 0,
@@ -1352,7 +1340,9 @@
           "Constant QP is incompatible with 2pass");
     CHECK(param->rc.bStrictCbr && (param->rc.bitrate <= 0 || param->rc.vbvBufferSize <=0),
           "Strict-cbr cannot be applied without specifying target bitrate or vbv bufsize");
-    CHECK((param->analysisSave || param->analysisLoad) && (param->analysisReuseLevel < 1 || param->analysisReuseLevel > 10),
+    CHECK(param->analysisReuseMode && (param->analysisReuseMode < X265_ANALYSIS_OFF || param->analysisReuseMode > X265_ANALYSIS_LOAD),
+        "Invalid analysis mode. Analysis mode 0: OFF 1: SAVE : 2 LOAD");
+    CHECK(param->analysisReuseMode && (param->analysisReuseLevel < 1 || param->analysisReuseLevel > 10),
         "Invalid analysis refine level. Value must be between 1 and 10 (inclusive)");
     CHECK(param->scaleFactor > 2, "Invalid scale-factor. Supports factor <= 2");
     CHECK(param->rc.qpMax < QP_MIN || param->rc.qpMax > QP_MAX_MAX,
@@ -1530,15 +1520,11 @@
 char *x265_param2string(x265_param* p, int padx, int pady)
 {
     char *buf, *s;
-    size_t bufSize = 4000 + p->rc.zoneCount * 64;
-    if (p->numaPools)
-        bufSize += strlen(p->numaPools);
-    if (p->masteringDisplayColorVolume)
-        bufSize += strlen(p->masteringDisplayColorVolume);
 
-    buf = s = X265_MALLOC(char, bufSize);
+    buf = s = X265_MALLOC(char, MAXPARAMSIZE);
     if (!buf)
         return NULL;
+
 #define BOOL(param, cliopt) \
     s += sprintf(s, " %s", (param) ? cliopt : "no-" cliopt);
 
@@ -1553,7 +1539,7 @@
     BOOL(p->bEnableSsim, "ssim");
     s += sprintf(s, " log-level=%d", p->logLevel);
     if (p->csvfn)
-        s += sprintf(s, " csv csv-log-level=%d", p->csvLogLevel);
+        s += sprintf(s, " csvfn=%s csv-log-level=%d", p->csvfn, p->csvLogLevel);
     s += sprintf(s, " bitdepth=%d", p->internalBitDepth);
     s += sprintf(s, " input-csp=%d", p->internalCsp);
     s += sprintf(s, " fps=%u/%u", p->fpsNum, p->fpsDenom);
@@ -1575,7 +1561,6 @@
     BOOL(p->bOpenGOP, "open-gop");
     s += sprintf(s, " min-keyint=%d", p->keyframeMin);
     s += sprintf(s, " keyint=%d", p->keyframeMax);
-    s += sprintf(s, " gop-lookahead=%d", p->gopLookahead);
     s += sprintf(s, " bframes=%d", p->bframes);
     s += sprintf(s, " b-adapt=%d", p->bFrameAdaptive);
     BOOL(p->bBPyramid, "b-pyramid");
@@ -1583,7 +1568,6 @@
     s += sprintf(s, " rc-lookahead=%d", p->lookaheadDepth);
     s += sprintf(s, " lookahead-slices=%d", p->lookaheadSlices);
     s += sprintf(s, " scenecut=%d", p->scenecutThreshold);
-    s += sprintf(s, " radl=%d", p->radl);
     BOOL(p->bIntraRefresh, "intra-refresh");
     s += sprintf(s, " ctu=%d", p->maxCUSize);
     s += sprintf(s, " min-cu-size=%d", p->minCUSize);
@@ -1629,6 +1613,7 @@
     s += sprintf(s, " psy-rd=%.2f", p->psyRd);
     s += sprintf(s, " psy-rdoq=%.2f", p->psyRdoq);
     BOOL(p->bEnableRdRefine, "rd-refine");
+    s += sprintf(s, " analysis-reuse-mode=%d", p->analysisReuseMode);
     BOOL(p->bLossless, "lossless");
     s += sprintf(s, " cbqpoffs=%d", p->cbQpOffset);
     s += sprintf(s, " crqpoffs=%d", p->crQpOffset);
@@ -1726,10 +1711,6 @@
     BOOL(p->bEmitHDRSEI, "hdr");
     BOOL(p->bHDROpt, "hdr-opt");
     BOOL(p->bDhdr10opt, "dhdr10-opt");
-    if (p->analysisSave)
-        s += sprintf(s, " analysis-save");
-    if (p->analysisLoad)
-        s += sprintf(s, " analysis-load");
     s += sprintf(s, " analysis-reuse-level=%d", p->analysisReuseLevel);
     s += sprintf(s, " scale-factor=%d", p->scaleFactor);
     s += sprintf(s, " refine-intra=%d", p->intraRefine);

x265_2.7.tar.gz/source/common/param.h -> x265_2.6.tar.gz/source/common/param.h Changed

x265_2.7.tar.gz/source/common/picyuv.cpp -> x265_2.6.tar.gz/source/common/picyuv.cpp Changed

@@ -358,20 +358,18 @@
     pixel *uPic = m_picOrg[1];
     pixel *vPic = m_picOrg[2];
 
-    if (param.csvLogLevel >= 2 || param.maxCLL || param.maxFALL)
+    for (int r = 0; r < height; r++)
     {
-        for (int r = 0; r < height; r++)
+        for (int c = 0; c < width; c++)
         {
-            for (int c = 0; c < width; c++)
-            {
-                m_maxLumaLevel = X265_MAX(yPic[c], m_maxLumaLevel);
-                m_minLumaLevel = X265_MIN(yPic[c], m_minLumaLevel);
-                lumaSum += yPic[c];
-            }
-            yPic += m_stride;
+            m_maxLumaLevel = X265_MAX(yPic[c], m_maxLumaLevel);
+            m_minLumaLevel = X265_MIN(yPic[c], m_minLumaLevel);
+            lumaSum += yPic[c];
         }
-        m_avgLumaLevel = (double)lumaSum / (m_picHeight * m_picWidth);
+        yPic += m_stride;
     }
+    m_avgLumaLevel = (double)lumaSum / (m_picHeight * m_picWidth);
+
     if (param.csvLogLevel >= 2)
     {
         if (param.internalCsp != X265_CSP_I400)

x265_2.7.tar.gz/source/common/x86/asm-primitives.cpp -> x265_2.6.tar.gz/source/common/x86/asm-primitives.cpp Changed

x265_2.7.tar.gz/source/common/x86/blockcopy8.asm -> x265_2.6.tar.gz/source/common/x86/blockcopy8.asm Changed

x265_2.7.tar.gz/source/common/x86/intrapred8.asm -> x265_2.6.tar.gz/source/common/x86/intrapred8.asm Changed

x265_2.7.tar.gz/source/common/x86/ipfilter16.asm -> x265_2.6.tar.gz/source/common/x86/ipfilter16.asm Changed

@@ -47,10 +47,75 @@
 
 SECTION_RODATA 32
 
+tab_c_32:         times 8 dd 32
 tab_c_524800:     times 4 dd 524800
 tab_c_n8192:      times 8 dw -8192
 pd_524800:        times 8 dd 524800
 
+tab_Tm16:         db 0, 1, 2, 3, 4,  5,  6, 7, 2, 3, 4,  5, 6, 7, 8, 9
+
+tab_ChromaCoeff:  dw  0, 64,  0,  0
+                  dw -2, 58, 10, -2
+                  dw -4, 54, 16, -2
+                  dw -6, 46, 28, -4
+                  dw -4, 36, 36, -4
+                  dw -4, 28, 46, -6
+                  dw -2, 16, 54, -4
+                  dw -2, 10, 58, -2
+
+const tab_ChromaCoeffV,  times 8 dw 0, 64
+                         times 8 dw 0, 0
+
+                         times 8 dw -2, 58
+                         times 8 dw 10, -2
+
+                         times 8 dw -4, 54
+                         times 8 dw 16, -2
+
+                         times 8 dw -6, 46
+                         times 8 dw 28, -4
+
+                         times 8 dw -4, 36
+                         times 8 dw 36, -4
+
+                         times 8 dw -4, 28
+                         times 8 dw 46, -6
+
+                         times 8 dw -2, 16
+                         times 8 dw 54, -4
+
+                         times 8 dw -2, 10
+                         times 8 dw 58, -2
+
+tab_ChromaCoeffVer: times 8 dw 0, 64
+                    times 8 dw 0, 0
+
+                    times 8 dw -2, 58
+                    times 8 dw 10, -2
+
+                    times 8 dw -4, 54
+                    times 8 dw 16, -2
+
+                    times 8 dw -6, 46
+                    times 8 dw 28, -4
+
+                    times 8 dw -4, 36
+                    times 8 dw 36, -4
+
+                    times 8 dw -4, 28
+                    times 8 dw 46, -6
+
+                    times 8 dw -2, 16
+                    times 8 dw 54, -4
+
+                    times 8 dw -2, 10
+                    times 8 dw 58, -2
+
+tab_LumaCoeff:    dw   0, 0,  0,  64,  0,   0,  0,  0
+                  dw  -1, 4, -10, 58,  17, -5,  1,  0
+                  dw  -1, 4, -11, 40,  40, -11, 4, -1
+                  dw   0, 1, -5,  17,  58, -10, 4, -1
+
 ALIGN 32
 tab_LumaCoeffV:   times 4 dw 0, 0
                   times 4 dw 0, 64
@@ -92,6 +157,14 @@
                   times 8 dw 58, -10
                   times 8 dw 4, -1
 
+const interp8_hps_shuf,     dd 0, 4, 1, 5, 2, 6, 3, 7
+
+const interp8_hpp_shuf,     db 0, 1, 2, 3, 4, 5, 6, 7, 2, 3, 4, 5, 6, 7, 8, 9
+                            db 4, 5, 6, 7, 8, 9, 10, 11, 6, 7, 8, 9, 10, 11, 12, 13
+
+const interp8_hpp_shuf_new, db 0, 1, 2, 3, 2, 3, 4, 5, 4, 5, 6, 7, 6, 7, 8, 9
+                            db 4, 5, 6, 7, 6, 7, 8, 9, 8, 9, 10, 11, 10, 11, 12, 13
+
 SECTION .text
 cextern pd_8
 cextern pd_32
@@ -102,6 +175,255 @@
 cextern pw_2000
 cextern idct8_shuf2
 
+%macro FILTER_LUMA_HOR_4_sse2 1
+    movu        m4,     [r0 + %1]       ; m4 = src[0-7]
+    movu        m5,     [r0 + %1 + 2]   ; m5 = src[1-8]
+    pmaddwd     m4,     m0
+    pmaddwd     m5,     m0
+    pshufd      m2,     m4,     q2301
+    paddd       m4,     m2
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m4,     m4,     q3120
+    pshufd      m5,     m5,     q3120
+    punpcklqdq  m4,     m5
+
+    movu        m5,     [r0 + %1 + 4]   ; m5 = src[2-9]
+    movu        m3,     [r0 + %1 + 6]   ; m3 = src[3-10]
+    pmaddwd     m5,     m0
+    pmaddwd     m3,     m0
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m2,     m3,     q2301
+    paddd       m3,     m2
+    pshufd      m5,     m5,     q3120
+    pshufd      m3,     m3,     q3120
+    punpcklqdq  m5,     m3
+
+    pshufd      m2,     m4,     q2301
+    paddd       m4,     m2
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m4,     m4,     q3120
+    pshufd      m5,     m5,     q3120
+    punpcklqdq  m4,     m5
+    paddd       m4,     m1
+%endmacro
+
+%macro FILTER_LUMA_HOR_8_sse2 1
+    movu        m4,     [r0 + %1]       ; m4 = src[0-7]
+    movu        m5,     [r0 + %1 + 2]   ; m5 = src[1-8]
+    pmaddwd     m4,     m0
+    pmaddwd     m5,     m0
+    pshufd      m2,     m4,     q2301
+    paddd       m4,     m2
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m4,     m4,     q3120
+    pshufd      m5,     m5,     q3120
+    punpcklqdq  m4,     m5
+
+    movu        m5,     [r0 + %1 + 4]   ; m5 = src[2-9]
+    movu        m3,     [r0 + %1 + 6]   ; m3 = src[3-10]
+    pmaddwd     m5,     m0
+    pmaddwd     m3,     m0
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m2,     m3,     q2301
+    paddd       m3,     m2
+    pshufd      m5,     m5,     q3120
+    pshufd      m3,     m3,     q3120
+    punpcklqdq  m5,     m3
+
+    pshufd      m2,     m4,     q2301
+    paddd       m4,     m2
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m4,     m4,     q3120
+    pshufd      m5,     m5,     q3120
+    punpcklqdq  m4,     m5
+    paddd       m4,     m1
+
+    movu        m5,     [r0 + %1 + 8]   ; m5 = src[4-11]
+    movu        m6,     [r0 + %1 + 10]  ; m6 = src[5-12]
+    pmaddwd     m5,     m0
+    pmaddwd     m6,     m0
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m2,     m6,     q2301
+    paddd       m6,     m2
+    pshufd      m5,     m5,     q3120
+    pshufd      m6,     m6,     q3120
+    punpcklqdq  m5,     m6
+
+    movu        m6,     [r0 + %1 + 12]  ; m6 = src[6-13]
+    movu        m3,     [r0 + %1 + 14]  ; m3 = src[7-14]
+    pmaddwd     m6,     m0
+    pmaddwd     m3,     m0
+    pshufd      m2,     m6,     q2301
+    paddd       m6,     m2
+    pshufd      m2,     m3,     q2301
+    paddd       m3,     m2
+    pshufd      m6,     m6,     q3120
+    pshufd      m3,     m3,     q3120
+    punpcklqdq  m6,     m3
+
+    pshufd      m2,     m5,     q2301
+    paddd       m5,     m2
+    pshufd      m2,     m6,     q2301
+    paddd       m6,     m2
+    pshufd      m5,     m5,     q3120
+    pshufd      m6,     m6,     q3120
+    punpcklqdq  m5,     m6
+    paddd       m5,     m1
+%endmacro
+
+;------------------------------------------------------------------------------------------------------------
+; void interp_8tap_horiz_p%3_%1x%2(pixel *src, intptr_t srcStride, pixel *dst, intptr_t dstStride, int coeffIdx)

x265_2.7.tar.gz/source/common/x86/ipfilter8.asm -> x265_2.6.tar.gz/source/common/x86/ipfilter8.asm Changed

@@ -33,16 +33,119 @@
 
 const interp4_vpp_shuf, times 2 db 0, 4, 1, 5, 2, 6, 3, 7, 8, 12, 9, 13, 10, 14, 11, 15
 
+const interp_vert_shuf, times 2 db 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 7, 6, 8, 7, 9
+                        times 2 db 4, 6, 5, 7, 6, 8, 7, 9, 8, 10, 9, 11, 10, 12, 11, 13
+
 const interp4_vpp_shuf1, dd 0, 1, 1, 2, 2, 3, 3, 4
                          dd 2, 3, 3, 4, 4, 5, 5, 6
 
+const pb_8tap_hps_0, times 2 db 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8
+                     times 2 db 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9,10
+                     times 2 db 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9,10,10,11,11,12
+                     times 2 db 6, 7, 7, 8, 8, 9, 9,10,10,11,11,12,12,13,13,14
+
 const tab_Lm,    db 0, 1, 2, 3, 4,  5,  6,  7,  1, 2, 3, 4,  5,  6,  7,  8
                  db 2, 3, 4, 5, 6,  7,  8,  9,  3, 4, 5, 6,  7,  8,  9,  10
                  db 4, 5, 6, 7, 8,  9,  10, 11, 5, 6, 7, 8,  9,  10, 11, 12
                  db 6, 7, 8, 9, 10, 11, 12, 13, 7, 8, 9, 10, 11, 12, 13, 14
 
+const tab_Vm,    db 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
+                 db 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3
+
+const tab_Cm,    db 0, 2, 1, 3, 0, 2, 1, 3, 0, 2, 1, 3, 0, 2, 1, 3
+
 const pd_526336, times 8 dd 8192*64+2048
 
+const tab_ChromaCoeff, db  0, 64,  0,  0
+                       db -2, 58, 10, -2
+                       db -4, 54, 16, -2
+                       db -6, 46, 28, -4
+                       db -4, 36, 36, -4
+                       db -4, 28, 46, -6
+                       db -2, 16, 54, -4
+                       db -2, 10, 58, -2
+
+const tabw_ChromaCoeff, dw  0, 64,  0,  0
+                        dw -2, 58, 10, -2
+                        dw -4, 54, 16, -2
+                        dw -6, 46, 28, -4
+                        dw -4, 36, 36, -4
+                        dw -4, 28, 46, -6
+                        dw -2, 16, 54, -4
+                        dw -2, 10, 58, -2
+
+const tab_ChromaCoeff_V, times 8 db 0, 64
+                         times 8 db 0,  0
+
+                         times 8 db -2, 58
+                         times 8 db 10, -2
+
+                         times 8 db -4, 54
+                         times 8 db 16, -2
+
+                         times 8 db -6, 46
+                         times 8 db 28, -4
+
+                         times 8 db -4, 36
+                         times 8 db 36, -4
+
+                         times 8 db -4, 28
+                         times 8 db 46, -6
+
+                         times 8 db -2, 16
+                         times 8 db 54, -4
+
+                         times 8 db -2, 10
+                         times 8 db 58, -2
+
+const tab_ChromaCoeffV, times 4 dw 0, 64
+                        times 4 dw 0, 0
+
+                        times 4 dw -2, 58
+                        times 4 dw 10, -2
+
+                        times 4 dw -4, 54
+                        times 4 dw 16, -2
+
+                        times 4 dw -6, 46
+                        times 4 dw 28, -4
+
+                        times 4 dw -4, 36
+                        times 4 dw 36, -4
+
+                        times 4 dw -4, 28
+                        times 4 dw 46, -6
+
+                        times 4 dw -2, 16
+                        times 4 dw 54, -4
+
+                        times 4 dw -2, 10
+                        times 4 dw 58, -2
+
+const pw_ChromaCoeffV,  times 8 dw 0, 64
+                        times 8 dw 0, 0
+
+                        times 8 dw -2, 58
+                        times 8 dw 10, -2
+
+                        times 8 dw -4, 54
+                        times 8 dw 16, -2
+
+                        times 8 dw -6, 46
+                        times 8 dw 28, -4
+
+                        times 8 dw -4, 36
+                        times 8 dw 36, -4
+
+                        times 8 dw -4, 28
+                        times 8 dw 46, -6
+
+                        times 8 dw -2, 16
+                        times 8 dw 54, -4
+
+                        times 8 dw -2, 10
+                        times 8 dw 58, -2
+
 const tab_LumaCoeff,   db   0, 0,  0,  64,  0,   0,  0,  0
                        db  -1, 4, -10, 58,  17, -5,  1,  0
                        db  -1, 4, -11, 40,  40, -11, 4, -1
@@ -93,6 +196,26 @@
                         times 8 dw 58, -10
                         times 8 dw 4, -1
 
+const pb_LumaCoeffVer,  times 16 db 0, 0
+                        times 16 db 0, 64
+                        times 16 db 0, 0
+                        times 16 db 0, 0
+
+                        times 16 db -1, 4
+                        times 16 db -10, 58
+                        times 16 db 17, -5
+                        times 16 db 1, 0
+
+                        times 16 db -1, 4
+                        times 16 db -11, 40
+                        times 16 db 40, -11
+                        times 16 db 4, -1
+
+                        times 16 db 0, 1
+                        times 16 db -5, 17
+                        times 16 db 58, -10
+                        times 16 db 4, -1
+
 const tab_LumaCoeffVer, times 8 db 0, 0
                         times 8 db 0, 64
                         times 8 db 0, 0
@@ -133,10 +256,44 @@
                             times 16 db 58, -10
                             times 16 db 4, -1
 
+const tab_ChromaCoeffVer_32,    times 16 db 0, 64
+                                times 16 db 0, 0
+
+                                times 16 db -2, 58
+                                times 16 db 10, -2
+
+                                times 16 db -4, 54
+                                times 16 db 16, -2
+
+                                times 16 db -6, 46
+                                times 16 db 28, -4
+
+                                times 16 db -4, 36
+                                times 16 db 36, -4
+
+                                times 16 db -4, 28
+                                times 16 db 46, -6
+
+                                times 16 db -2, 16
+                                times 16 db 54, -4
+
+                                times 16 db -2, 10
+                                times 16 db 58, -2
+
 const tab_c_64_n64, times 8 db 64, -64
 
+const interp4_shuf, times 2 db 0, 1, 8, 9, 4, 5, 12, 13, 2, 3, 10, 11, 6, 7, 14, 15
+
+const interp4_horiz_shuf1,  db 0, 1, 2, 3, 1, 2, 3, 4, 2, 3, 4, 5, 3, 4, 5, 6
+                            db 8, 9, 10, 11, 9, 10, 11, 12, 10, 11, 12, 13, 11, 12, 13, 14
+
+const interp4_hpp_shuf,     times 2 db 0, 1, 2, 3, 1, 2, 3, 4, 8, 9, 10, 11, 9, 10, 11, 12
+
 const interp8_hps_shuf,     dd 0, 4, 1, 5, 2, 6, 3, 7
 
+ALIGN 32
+interp4_hps_shuf: times 2 db 0, 1, 2, 3, 1, 2, 3, 4, 8, 9, 10, 11, 9, 10, 11, 12
+
 SECTION .text
 
 cextern pb_128
@@ -146,6 +303,462 @@
 cextern pw_2000
 cextern pw_8192
 
+%macro FILTER_H4_w2_2_sse2 0
+    pxor        m3, m3
+    movd        m0, [srcq - 1]
+    movd        m2, [srcq]

x265_2.7.tar.gz/source/common/x86/loopfilter.asm -> x265_2.6.tar.gz/source/common/x86/loopfilter.asm Changed

@@ -374,7 +374,7 @@
     pxor        m0, m0                      ; m0 = 0
     mova        m6, [pb_2]                  ; m6 = [2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]
     shr         r4d, 4
-.loop:
+.loop
     movu        m7, [r0]
     movu        m5, [r0 + 16]
     movu        m3, [r0 + r3]
@@ -430,7 +430,7 @@
     mova        m6,    [pb_2]                  ; m6 = [2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]
     mova        m7,    [pb_128]
     shr         r4d,   4
-.loop:
+.loop
     movu        m1,    [r0]                    ; m1 = pRec[x]
     movu        m2,    [r0 + r3]               ; m2 = pRec[x + iStride]
 
@@ -478,7 +478,7 @@
     mova        m4, [pb_2]
     shr         r4d, 4
     mova        m0, [pw_pixel_max]
-.loop:
+.loop
     movu        m5, [r0]
     movu        m3, [r0 + r3]
 
@@ -523,7 +523,7 @@
     mova          xm6,    [pb_2]                  ; xm6 = [2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]
     mova          xm7,    [pb_128]
     shr           r4d,    4
-.loop:
+.loop
     movu          xm1,    [r0]                    ; xm1 = pRec[x]
     movu          xm2,    [r0 + r3]               ; xm2 = pRec[x + iStride]
 
@@ -572,7 +572,7 @@
     mov         r5d, r4d
     shr         r4d, 4
     mov         r6, r0
-.loop:
+.loop
     movu        m7, [r0]
     movu        m5, [r0 + 16]
     movu        m3, [r0 + r3]
@@ -674,7 +674,7 @@
     pxor        m0,         m0                      ; m0 = 0
     mova        m7,         [pb_128]
     shr         r4d,        4
-.loop:
+.loop
     movu        m1,         [r0]                    ; m1 = pRec[x]
     movu        m2,         [r0 + r3]               ; m2 = pRec[x + iStride]
 
@@ -748,7 +748,7 @@
     mova            m4, [pw_pixel_max]
     vbroadcasti128  m6, [r2]                ; m6 = m_iOffsetEo
     shr             r4d, 4
-.loop:
+.loop
     movu            m7, [r0]
     movu            m5, [r0 + r3]
     movu            m1, [r0 + r3 * 2]
@@ -804,7 +804,7 @@
     vbroadcasti128  m5,         [pb_128]
     vbroadcasti128  m6,         [r2]                         ; m6 = m_iOffsetEo
     shr             r4d,        4
-.loop:
+.loop
     movu            xm1,        [r0]                         ; m1 = pRec[x]
     movu            xm2,        [r0 + r3]                    ; m2 = pRec[x + iStride]
     vinserti128     m1,         m1,       xm2,            1
@@ -859,7 +859,7 @@
     movh        m6, [r0 + r4 * 2]
     movhps      m6, [r1 + r4]
 
-.loop:
+.loop
     movu        m7, [r0]
     movu        m5, [r0 + 16]
     movu        m3, [r0 + r5 + 2]
@@ -918,7 +918,7 @@
     movh        m5,    [r0 + r4]
     movhps      m5,    [r1 + r4]
 
-.loop:
+.loop
     movu        m1,    [r0]                    ; m1 = rec[x]
     movu        m2,    [r0 + r5 + 1]           ; m2 = rec[x + stride + 1]
     pxor        m3,    m1,    m7
@@ -970,7 +970,7 @@
     movhps          xm4, [r1 + r4]
     vbroadcasti128  m5, [r3]
     mova            m6, [pw_pixel_max]
-.loop:
+.loop
     movu            m1, [r0]
     movu            m3, [r0 + r5 + 2]
 
@@ -1061,7 +1061,7 @@
     movhps          xm4, [r1 + r4]
     vbroadcasti128  m5, [r3]
 
-.loop:
+.loop
     movu            m1, [r0]
     movu            m7, [r0 + 32]
     movu            m3, [r0 + r5 + 2]
@@ -1567,11 +1567,11 @@
     movu        m4, [r1 + 16]       ; offset[16-31]
     pxor        m7, m7
 
-.loopH:
+.loopH
     mov         r5d, r2d
     xor         r6,  r6
 
-.loopW:
+.loopW
     movu        m2, [r0 + r6]
     movu        m5, [r0 + r6 + 16]
     psrlw       m0, m2, (BIT_DEPTH - 5)
@@ -1617,11 +1617,11 @@
     movu        m3, [r1 + 0]      ; offset[0-15]
     movu        m4, [r1 + 16]     ; offset[16-31]
     pxor        m7, m7            ; m7 =[0]
-.loopH:
+.loopH
     mov         r5d, r2d
     xor         r6,  r6
 
-.loopW:
+.loopW
     movu        m2, [r0 + r6]     ; m0 = [rec]
     psrlw       m1, m2, 3
     pand        m1, [pb_31]       ; m1 = [index]
@@ -1670,9 +1670,9 @@
     mov             r6d, r3d
     shr             r3d, 1
 
-.loopH:
+.loopH
     mov             r5d, r2d
-.loopW:
+.loopW
     movu            m2, [r0]
     movu            m5, [r0 + r4]
     psrlw           m0, m2, (BIT_DEPTH - 5)
@@ -1751,9 +1751,9 @@
     shr             r2d,        4
     mov             r1d,        r3d
     shr             r3d,        1
-.loopH:
+.loopH
     mov             r5d,        r2d
-.loopW:
+.loopW
     movu            xm2,        [r0]                ; m2 = [rec]
     vinserti128     m2,         m2,  [r0 + r4],  1
     psrlw           m1,         m2,  3
@@ -1789,7 +1789,7 @@
     test            r1b,        1
     jz              .end
     mov             r5d,        r2d
-.loopW1:
+.loopW1
     movu            xm2,        [r0]                ; m2 = [rec]
     psrlw           xm1,        xm2, 3
     pand            xm1,        xm7                 ; m1 = [index]
@@ -1811,7 +1811,7 @@
     add             r0,         16
     dec             r5d
     jnz             .loopW1
-.end:
+.end
     RET
 %endif
 
@@ -1827,7 +1827,7 @@
     add             r3d, 1
     mov             r5, r0
     movu            m4, [r0 + r4]
-.loop:
+.loop
     movu            m1, [r1]        ; m2 = pRec[x]
     movu            m2, [r2]        ; m3 = pTmpU[x]
 
@@ -1921,7 +1921,7 @@
     mov             r5, r0
     movu            m4, [r0 + r4]
 
-.loop:
+.loop
     movu            m1, [r1]        ; m2 = pRec[x]
     movu            m2, [r2]        ; m3 = pTmpU[x]

x265_2.7.tar.gz/source/common/x86/mc-a.asm -> x265_2.6.tar.gz/source/common/x86/mc-a.asm Changed

@@ -4115,7 +4115,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 4
-.loop:
+.loop
     pixel_avg_W8
     dec     r9d
     jnz     .loop
@@ -4129,7 +4129,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 8
-.loop:
+.loop
     pixel_avg_W8
     dec     r9d
     jnz     .loop
@@ -4697,7 +4697,7 @@
     lea     r8, [r1 * 3]
     mov     r9d, 4
 
-.loop:
+.loop
     movu    m0, [r2]
     movu    m1, [r4]
     pavgw   m0, m1
@@ -4834,7 +4834,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 4
-.loop:
+.loop
     pixel_avg_H16
     dec r9d
     jnz .loop
@@ -4848,7 +4848,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 4
-.loop:
+.loop
     pixel_avg_H16
     pixel_avg_H16
     dec r9d
@@ -4863,7 +4863,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 4
-.loop:
+.loop
     pixel_avg_H16
     pixel_avg_H16
     pixel_avg_H16
@@ -4887,7 +4887,7 @@
     lea     r8, [r1 * 3]
     mov     r9d, 8
 
-.loop:
+.loop
     movu    m0, [r2]
     movu    m1, [r4]
     pavgw   m0, m1
@@ -4987,7 +4987,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 2
-.loop:
+.loop
     pixel_avg_W32
     dec     r9d
     jnz     .loop
@@ -5001,7 +5001,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 4
-.loop:
+.loop
     pixel_avg_W32
     dec     r9d
     jnz     .loop
@@ -5015,7 +5015,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 6
-.loop:
+.loop
     pixel_avg_W32
     dec     r9d
     jnz     .loop
@@ -5029,7 +5029,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 8
-.loop:
+.loop
     pixel_avg_W32
     dec     r9d
     jnz     .loop
@@ -5043,7 +5043,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 16
-.loop:
+.loop
     pixel_avg_W32
     dec     r9d
     jnz     .loop
@@ -5141,7 +5141,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 4
-.loop:
+.loop
     pixel_avg_W64
     dec     r9d
     jnz     .loop
@@ -5155,7 +5155,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 8
-.loop:
+.loop
     pixel_avg_W64
     dec     r9d
     jnz     .loop
@@ -5169,7 +5169,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 12
-.loop:
+.loop
     pixel_avg_W64
     dec     r9d
     jnz     .loop
@@ -5183,7 +5183,7 @@
     lea     r7, [r5 * 3]
     lea     r8, [r1 * 3]
     mov     r9d, 16
-.loop:
+.loop
     pixel_avg_W64
     dec     r9d
     jnz     .loop
@@ -5204,7 +5204,7 @@
     lea     r8, [r1 * 3]
     mov     r9d, 16
 
-.loop:
+.loop
     movu    m0, [r2]
     movu    m1, [r4]
     pavgw   m0, m1

x265_2.7.tar.gz/source/common/x86/pixel-util8.asm -> x265_2.6.tar.gz/source/common/x86/pixel-util8.asm Changed

x265_2.7.tar.gz/source/common/x86/sad-a.asm -> x265_2.6.tar.gz/source/common/x86/sad-a.asm Changed

@@ -5631,7 +5631,7 @@
     xorps           m5, m5
     mov             r4d, 4
 
-.loop:
+.loop
     movu           m1, [r0]               ; row 0 of pix0
     movu           m2, [r2]               ; row 0 of pix1
     movu           m3, [r0 + r1]          ; row 1 of pix0
@@ -5676,7 +5676,7 @@
     mov             r4d, 6
     lea             r5, [r1 * 3]
     lea             r6, [r3 * 3]
-.loop:
+.loop
     movu           m1, [r0]               ; row 0 of pix0
     movu           m2, [r2]               ; row 0 of pix1
     movu           m3, [r0 + r1]          ; row 1 of pix0
@@ -5718,7 +5718,7 @@
     lea             r5, [r1 * 3]
     lea             r6, [r3 * 3]
 
-.loop:
+.loop
     movu           m1, [r0]               ; row 0 of pix0
     movu           m2, [r2]               ; row 0 of pix1
     movu           m3, [r0 + r1]          ; row 1 of pix0
@@ -5759,7 +5759,7 @@
     lea             r5, [r1 * 3]
     lea             r6, [r3 * 3]
 
-.loop:
+.loop
     movu           m1, [r0]               ; row 0 of pix0
     movu           m2, [r2]               ; row 0 of pix1
     movu           m3, [r0 + r1]          ; row 1 of pix0
@@ -5822,7 +5822,7 @@
     mov             r4d, 64/4
     lea             r5, [r1 * 3]
     lea             r6, [r3 * 3]
-.loop:
+.loop
     movu           m1, [r0]               ; row 0 of pix0
     movu           m2, [r2]               ; row 0 of pix1
     movu           m3, [r0 + r1]          ; row 1 of pix0
@@ -5873,7 +5873,7 @@
     xorps           m0, m0
     xorps           m5, m5
     mov             r4d, 4
-.loop:
+.loop
     movu           m1, [r0]               ; first 32 of row 0 of pix0
     movu           m2, [r2]               ; first 32 of row 0 of pix1
     movu           m3, [r0 + 32]          ; second 32 of row 0 of pix0
@@ -5936,7 +5936,7 @@
     xorps           m0, m0
     xorps           m5, m5
     mov             r4d, 16
-.loop:
+.loop
     movu           m1, [r0]               ; first 32 of row 0 of pix0
     movu           m2, [r2]               ; first 32 of row 0 of pix1
     movu           m3, [r0 + 32]          ; second 32 of row 0 of pix0
@@ -5978,7 +5978,7 @@
     mov             r4d, 12
     lea             r5, [r1 * 3]
     lea             r6, [r3 * 3]
-.loop:
+.loop
     movu           m1, [r0]               ; first 32 of row 0 of pix0
     movu           m2, [r2]               ; first 32 of row 0 of pix1
     movu           m3, [r0 + 32]          ; second 32 of row 0 of pix0
@@ -6040,7 +6040,7 @@
     mov             r4d, 8
     lea             r5, [r1 * 3]
     lea             r6, [r3 * 3]
-.loop:
+.loop
     movu           m1, [r0]               ; first 32 of row 0 of pix0
     movu           m2, [r2]               ; first 32 of row 0 of pix1
     movu           m3, [r0 + 32]          ; second 32 of row 0 of pix0

x265_2.7.tar.gz/source/common/x86/seaintegral.asm -> x265_2.6.tar.gz/source/common/x86/seaintegral.asm Changed

@@ -36,7 +36,7 @@
     mov r2, r1
     shl r2, 4
 
-.loop:
+.loop
     movu    m0, [r0]
     movu    m1, [r0 + r2]
     psubd   m1, m0
@@ -54,7 +54,7 @@
     mov r2, r1
     shl r2, 5
 
-.loop:
+.loop
     movu    m0, [r0]
     movu    m1, [r0 + r2]
     psubd   m1, m0
@@ -75,7 +75,7 @@
     shl r3, 4
     add r2, r3
 
-.loop:
+.loop
     movu    m0, [r0]
     movu    m1, [r0 + r2]
     psubd   m1, m0
@@ -93,7 +93,7 @@
     mov r2, r1
     shl r2, 6
 
-.loop:
+.loop
     movu    m0, [r0]
     movu    m1, [r0 + r2]
     psubd   m1, m0
@@ -114,7 +114,7 @@
     shl r3, 5
     add r2, r3
 
-.loop:
+.loop
     movu    m0, [r0]
     movu    m1, [r0 + r2]
     psubd   m1, m0
@@ -132,7 +132,7 @@
     mov r2, r1
     shl r2, 7
 
-.loop:
+.loop
     movu    m0, [r0]
     movu    m1, [r0 + r2]
     psubd   m1, m0
@@ -264,7 +264,7 @@
     movu           [r0 + r3], xm0
     jmp            .end
 
-.end:
+.end
     RET
 %endif
 
@@ -379,7 +379,7 @@
     movu           [r0 + r3], m0
     jmp             .end
 
-.end:
+.end
     RET
 %endif
 
@@ -577,7 +577,7 @@
     movu           [r0 + r3], xm0
     jmp            .end
 
-.end:
+.end
     RET
 %endif
 
@@ -740,7 +740,7 @@
     movu           [r0 + r3], m0
     jmp             .end
 
-.end:
+.end
     RET
 %endif
 
@@ -883,7 +883,7 @@
     movu           [r0 + r3], m0
     jmp             .end
 
-.end:
+.end
     RET
 
 %macro INTEGRAL_THIRTYTWO_HORIZONTAL_16 0
@@ -1058,5 +1058,5 @@
     movu           [r0 + r3], m0
     jmp             .end
 
-.end:
+.end
     RET

x265_2.7.tar.gz/source/common/x86/x86inc.asm -> x265_2.6.tar.gz/source/common/x86/x86inc.asm Changed

@@ -66,15 +66,6 @@
     %endif
 %endif
 
-%define FORMAT_ELF 0
-%ifidn __OUTPUT_FORMAT__,elf
-    %define FORMAT_ELF 1
-%elifidn __OUTPUT_FORMAT__,elf32
-    %define FORMAT_ELF 1
-%elifidn __OUTPUT_FORMAT__,elf64
-    %define FORMAT_ELF 1
-%endif
-
 %ifdef PREFIX
     %define mangle(x) _ %+ x
 %else
@@ -97,10 +88,6 @@
     default rel
 %endif
 
-%ifdef __NASM_VER__
-    %use smartalign
-%endif
-
 ; Macros to eliminate most code duplication between x86_32 and x86_64:
 ; Currently this works only for leaf functions which load all their arguments
 ; into registers at the start, and make no other use of the stack. Luckily that
@@ -698,7 +685,7 @@
         CAT_XDEFINE cglobaled_, %2, 1
     %endif
     %xdefine current_function %2
-    %if FORMAT_ELF
+    %ifidn __OUTPUT_FORMAT__,elf
         global %2:function %%VISIBILITY
     %else
         global %2
@@ -724,16 +711,14 @@
 
 ; like cextern, but without the prefix
 %macro cextern_naked 1
-    %ifdef PREFIX
-        %xdefine %1 mangle(%1)
-    %endif
+    %xdefine %1 mangle(%1)
     CAT_XDEFINE cglobaled_, %1, 1
     extern %1
 %endmacro
 
 %macro const 1-2+
     %xdefine %1 mangle(private_prefix %+ _ %+ %1)
-    %if FORMAT_ELF
+    %ifidn __OUTPUT_FORMAT__,elf
         global %1:data hidden
     %else
         global %1
@@ -742,8 +727,9 @@
     %1: %2
 %endmacro
 
-; This is needed for ELF, otherwise the GNU linker assumes the stack is executable by default.
-%if FORMAT_ELF
+; This is needed for ELF, otherwise the GNU linker assumes the stack is
+; executable by default.
+%ifidn __OUTPUT_FORMAT__,elf
     [SECTION .note.GNU-stack noalloc noexec nowrite progbits]
 %endif
 
@@ -815,17 +801,9 @@
     %endif
 
     %if ARCH_X86_64 || cpuflag(sse2)
-        %ifdef __NASM_VER__
-            ALIGNMODE p6
-        %else
-            CPU amdnop
-        %endif
+        CPU amdnop
     %else
-        %ifdef __NASM_VER__
-            ALIGNMODE nop
-        %else
-            CPU basicnop
-        %endif
+        CPU basicnop
     %endif
 %endmacro
 
@@ -1489,7 +1467,7 @@
                 v%5%6 %1, %2, %3, %4
             %elifidn %1, %2
                 ; If %3 or %4 is a memory operand it needs to be encoded as the last operand.
-                %ifnum sizeof%3
+                %ifid %3
                     v%{5}213%6 %2, %3, %4
                 %else
                     v%{5}132%6 %2, %4, %3
@@ -1513,3 +1491,14 @@
 FMA4_INSTR fmsubadd, pd, ps
 FMA4_INSTR fnmadd,   pd, ps, sd, ss
 FMA4_INSTR fnmsub,   pd, ps, sd, ss
+
+; workaround: vpbroadcastq is broken in x86_32 due to a yasm bug (fixed in 1.3.0)
+%if __YASM_VERSION_ID__ < 0x01030000 && ARCH_X86_64 == 0
+    %macro vpbroadcastq 2
+        %if sizeof%1 == 16
+            movddup %1, %2
+        %else
+            vbroadcastsd %1, %2
+        %endif
+    %endmacro
+%endif

x265_2.7.tar.gz/source/dynamicHDR10/JsonHelper.cpp -> x265_2.6.tar.gz/source/dynamicHDR10/JsonHelper.cpp Changed

@@ -139,13 +139,21 @@
         return JsonObject();
     }
 
-    std::ifstream ifs(path);
-    const std::string json_str2((std::istreambuf_iterator<char>(ifs)),
-                                (std::istreambuf_iterator<char>()));
-
+    ifstream tfile;
+    string json_str;
+    string json_str2;
     string err = "";
+    tfile.open(path);
+    while(tfile)
+    {
+        std::getline(tfile, json_str);
+        json_str2.append(json_str);
+    }
 
-    return Json::parse(json_str2,err, JsonParse::COMMENTS).object_items();
+    tfile.close();
+    size_t beginning = json_str2.find_first_of("{");
+    int fixchar = json_str2[json_str2.size() - 2] == '}' ? 1 : 0;
+    return Json::parse(json_str2.substr(beginning,json_str2.size() - fixchar),err).object_items();
 }
 
 JsonArray JsonHelper::readJsonArray(const string &path)
@@ -166,13 +174,28 @@
         return JsonArray();
     }
 
-    std::ifstream ifs(path);
-    const std::string json_str2((std::istreambuf_iterator<char>(ifs)),
-                                (std::istreambuf_iterator<char>()));
-
+    ifstream tfile;
+    string json_str;
+    string json_str2;
     string err = "";
+    tfile.open(path);
+    while(tfile)
+    {
+        std::getline(tfile, json_str);
+        json_str2.append(json_str);
+    }
+
+    tfile.close();
 
-    return Json::parse(json_str2,err, JsonParse::COMMENTS).array_items();
+    vector<Json> data;
+    if (json_str2.size() != 0)
+    {
+        size_t beginning = json_str2.find_first_of("[");
+        int fixchar = json_str2[json_str2.size() - 2] == ']' ? 1 : 0;
+        return Json::parse(json_str2.substr(beginning, json_str2.size() - fixchar), err).array_items();
+    }
+    else
+        return data;
 }
 
 bool JsonHelper::validatePathExtension(string &path)

x265_2.7.tar.gz/source/dynamicHDR10/SeiMetadataDictionary.cpp -> x265_2.6.tar.gz/source/dynamicHDR10/SeiMetadataDictionary.cpp Changed

x265_2.7.tar.gz/source/dynamicHDR10/SeiMetadataDictionary.h -> x265_2.6.tar.gz/source/dynamicHDR10/SeiMetadataDictionary.h Changed

x265_2.7.tar.gz/source/dynamicHDR10/metadataFromJson.cpp -> x265_2.6.tar.gz/source/dynamicHDR10/metadataFromJson.cpp Changed

@@ -372,7 +372,7 @@
     const uint16_t terminalProviderCode = 0x003C;
     const uint16_t terminalProviderOrientedCode = 0x0001;
     const uint8_t applicationIdentifier = 4;
-    const uint8_t applicationVersion = 1;
+    const uint8_t applicationVersion = 0;
 
     mPimpl->appendBits(metadata, countryCode, 8);
     mPimpl->appendBits(metadata, terminalProviderCode, 16);
@@ -384,7 +384,9 @@
     //Note: Validated only add up to two local selections, ignore the rest
     JsonArray jsonArray = fileData[frame][JsonDataKeys::LocalParameters].array_items();
     int ellipsesNum = static_cast<int>(jsonArray.size() > 2 ? 2 : jsonArray.size());
-    uint16_t numWindows = (uint16_t)fileData[frame][JsonDataKeys::NumberOfWindows].int_value();
+
+    uint16_t numWindows = 1 + static_cast<uint16_t>(ellipsesNum);
+
     mPimpl->appendBits(metadata, numWindows, 2);
     for (int i = 0; i < ellipsesNum; ++i)
     {
@@ -424,15 +426,16 @@
 
         mPimpl->appendBits(metadata, semimajorExternalAxis, 16);
         mPimpl->appendBits(metadata, semiminorExternalAxis, 16);
-        uint8_t overlapProcessOption = static_cast<uint8_t>(ellipseJsonObject[EllipseNames::OverlapProcessOption].int_value());
+        /*bool*/ uint8_t overlapProcessOption = static_cast<uint8_t>(ellipseJsonObject[EllipseNames::OverlapProcessOption].int_value()); //1; 
         //TODO: Uses Layering method, the value is "1"
         mPimpl->appendBits(metadata, overlapProcessOption, 1);
     }
     /* Targeted System Display Data */
-    uint32_t monitorPeak = fileData[frame][JsonDataKeys::TargetDisplayLuminance].int_value();     //500;
-    mPimpl->appendBits(metadata, monitorPeak, 27);
+    uint32_t TEMPmonitorPeak = fileData[frame][JsonDataKeys::TargetDisplayLuminance].int_value();     //500;
+    mPimpl->appendBits(metadata, TEMPmonitorPeak, 27);
+
     //NOTE: Set as false for now, as requested
-    uint8_t targetedSystemDisplayActualPeakLuminanceFlag = 0;
+    /*bool*/uint8_t targetedSystemDisplayActualPeakLuminanceFlag = 0; /*false*/
     mPimpl->appendBits(metadata, targetedSystemDisplayActualPeakLuminanceFlag, 1);
     if (targetedSystemDisplayActualPeakLuminanceFlag)
     {
@@ -460,6 +463,7 @@
         mPimpl->appendBits(metadata, static_cast<uint16_t>((int)luminanceData.maxGLuminance & 0xFFFF), 16);
         mPimpl->appendBits(metadata, static_cast<uint8_t>(((int)luminanceData.maxBLuminance & 0x10000) >> 16), 1);
         mPimpl->appendBits(metadata, static_cast<uint16_t>((int)luminanceData.maxBLuminance & 0xFFFF), 16);
+        /* changed from maxRGBLuminance to average luminance to match stms implementation */
         mPimpl->appendBits(metadata, static_cast<uint8_t>(((int)luminanceData.averageLuminance & 0x10000) >> 16), 1);
         mPimpl->appendBits(metadata, static_cast<uint16_t>((int)luminanceData.averageLuminance & 0xFFFF), 16);
 
@@ -474,7 +478,7 @@
             uint8_t distributionMaxrgbPercentage = static_cast<uint8_t>(percentilPercentages.at(i));
             mPimpl->appendBits(metadata, distributionMaxrgbPercentage, 7);
 
-            /* 17bits: 1bit then 16 */
+            // 17bits: 1bit then 16
             unsigned int ithPercentile = luminanceData.percentiles.at(i);
             uint8_t highValue = static_cast<uint8_t>((ithPercentile & 0x10000) >> 16);
             uint16_t lowValue = static_cast<uint16_t>(ithPercentile & 0xFFFF);
@@ -495,32 +499,33 @@
     {
         //TODO
     }
-    /* Bezier Curve Data */
+    // BEZIER CURVE DATA
     for (int w = 0; w < numWindows; ++w)
     {
+        //TODO: 
         uint8_t toneMappingFlag = 1;
-		/* Check if the window contains tone mapping bezier curve data and set toneMappingFlag appropriately */
-		//Json bezierData = fileData[frame][BezierCurveNames::TagName];
-        BezierCurveData curveData;
-		/* Select curve data based on global window */
-        if (w == 0)
+        mPimpl->appendBits(metadata, toneMappingFlag, 1);
+        if (toneMappingFlag)
         {
-            if (!mPimpl->bezierCurveFromJson(fileData[frame][BezierCurveNames::TagName], curveData))
+            Json bezierData = fileData[frame][BezierCurveNames::TagName];
+            BezierCurveData curveData;
+
+            /* Select curve data based on global window or local window */
+            if (w == 0)
             {
-				toneMappingFlag = 0;
+                if (!mPimpl->bezierCurveFromJson(bezierData, curveData))
+                {
+                    std::cout << "error parsing bezierCurve frame: " << w << std::endl;
+                }
             }
-        }
-	    /* Select curve data based on local window */
-        else
-        {
-            if (!mPimpl->bezierCurveFromJson(jsonArray[w - 1][BezierCurveNames::TagName], curveData))
+            else
             {
-				toneMappingFlag = 0;
+                if (!mPimpl->bezierCurveFromJson(jsonArray[w - 1][BezierCurveNames::TagName], curveData))
+                {
+                    std::cout << "error parsing bezierCurve ellipse: " << w - 1 << std::endl;
+                }
             }
-        }		
-        mPimpl->appendBits(metadata, toneMappingFlag, 1);
-        if (toneMappingFlag)
-        {
+
             uint16_t kneePointX = static_cast<uint16_t>(curveData.sPx);
             mPimpl->appendBits(metadata, kneePointX, 12);
             uint16_t kneePointY = static_cast<uint16_t>(curveData.sPy);
@@ -536,7 +541,7 @@
                 mPimpl->appendBits(metadata, anchor, 10);
             }
         }
-	}
+    }
     /* Set to false as requested */
     bool colorSaturationMappingFlag = 0;
     mPimpl->appendBits(metadata, colorSaturationMappingFlag, 1);

x265_2.7.tar.gz/source/encoder/analysis.cpp -> x265_2.6.tar.gz/source/encoder/analysis.cpp Changed

@@ -100,17 +100,16 @@
     for (uint32_t depth = 0; depth <= m_param->maxCUDepth; depth++, cuSize >>= 1)
     {
         ModeDepth &md = m_modeDepth[depth];
-        ok &= md.cuMemPool.create(depth, csp, MAX_PRED_TYPES, *m_param);
+
+        md.cuMemPool.create(depth, csp, MAX_PRED_TYPES, *m_param);
         ok &= md.fencYuv.create(cuSize, csp);
-        if (ok)
+
+        for (int j = 0; j < MAX_PRED_TYPES; j++)
         {
-            for (int j = 0; j < MAX_PRED_TYPES; j++)
-            {
-                md.pred[j].cu.initialize(md.cuMemPool, depth, *m_param, j);
-                ok &= md.pred[j].predYuv.create(cuSize, csp);
-                ok &= md.pred[j].reconYuv.create(cuSize, csp);
-                md.pred[j].fencYuv = &md.fencYuv;
-            }
+            md.pred[j].cu.initialize(md.cuMemPool, depth, *m_param, j);
+            ok &= md.pred[j].predYuv.create(cuSize, csp);
+            ok &= md.pred[j].reconYuv.create(cuSize, csp);
+            md.pred[j].fencYuv = &md.fencYuv;
         }
     }
     if (m_param->sourceHeight >= 1080)
@@ -159,34 +158,38 @@
     if (m_param->bCTUInfo && (*m_frame->m_ctuInfo + ctu.m_cuAddr))
     {
         x265_ctu_info_t* ctuTemp = *m_frame->m_ctuInfo + ctu.m_cuAddr;
-        int32_t depthIdx = 0;
-        uint32_t maxNum8x8Partitions = 64;
-        uint8_t* depthInfoPtr = m_frame->m_addOnDepth[ctu.m_cuAddr];
-        uint8_t* contentInfoPtr = m_frame->m_addOnCtuInfo[ctu.m_cuAddr];
-        int* prevCtuInfoChangePtr = m_frame->m_addOnPrevChange[ctu.m_cuAddr];
-        do
-        {
-            uint8_t depth = (uint8_t)ctuTemp->ctuPartitions[depthIdx];
-            uint8_t content = (uint8_t)(*((int32_t *)ctuTemp->ctuInfo + depthIdx));
-            int prevCtuInfoChange = m_frame->m_prevCtuInfoChange[ctu.m_cuAddr * maxNum8x8Partitions + depthIdx];
-            memset(depthInfoPtr, depth, sizeof(uint8_t) * numPartition >> 2 * depth);
-            memset(contentInfoPtr, content, sizeof(uint8_t) * numPartition >> 2 * depth);
-            memset(prevCtuInfoChangePtr, 0, sizeof(int) * numPartition >> 2 * depth);
-            for (uint32_t l = 0; l < numPartition >> 2 * depth; l++)
-                prevCtuInfoChangePtr[l] = prevCtuInfoChange;
-            depthInfoPtr += ctu.m_numPartitions >> 2 * depth;
-            contentInfoPtr += ctu.m_numPartitions >> 2 * depth;
-            prevCtuInfoChangePtr += ctu.m_numPartitions >> 2 * depth;
-            depthIdx++;
-        } while (ctuTemp->ctuPartitions[depthIdx] != 0);
-
-        m_additionalCtuInfo = m_frame->m_addOnCtuInfo[ctu.m_cuAddr];
-        m_prevCtuInfoChange = m_frame->m_addOnPrevChange[ctu.m_cuAddr];
-        memcpy(ctu.m_cuDepth, m_frame->m_addOnDepth[ctu.m_cuAddr], sizeof(uint8_t) * numPartition);
-        //Calculate log2CUSize from depth
-        for (uint32_t i = 0; i < cuGeom.numPartitions; i++)
-            ctu.m_log2CUSize[i] = (uint8_t)m_param->maxLog2CUSize - ctu.m_cuDepth[i];
+        if (ctuTemp->ctuPartitions)
+        {
+            int32_t depthIdx = 0;
+            uint32_t maxNum8x8Partitions = 64;
+            uint8_t* depthInfoPtr = m_frame->m_addOnDepth[ctu.m_cuAddr];
+            uint8_t* contentInfoPtr = m_frame->m_addOnCtuInfo[ctu.m_cuAddr];
+            int* prevCtuInfoChangePtr = m_frame->m_addOnPrevChange[ctu.m_cuAddr];
+            do
+            {
+                uint8_t depth = (uint8_t)ctuTemp->ctuPartitions[depthIdx];
+                uint8_t content = (uint8_t)(*((int32_t *)ctuTemp->ctuInfo + depthIdx));
+                int prevCtuInfoChange = m_frame->m_prevCtuInfoChange[ctu.m_cuAddr * maxNum8x8Partitions + depthIdx];
+                memset(depthInfoPtr, depth, sizeof(uint8_t) * numPartition >> 2 * depth);
+                memset(contentInfoPtr, content, sizeof(uint8_t) * numPartition >> 2 * depth);
+                memset(prevCtuInfoChangePtr, 0, sizeof(int) * numPartition >> 2 * depth);
+                for (uint32_t l = 0; l < numPartition >> 2 * depth; l++)
+                    prevCtuInfoChangePtr[l] = prevCtuInfoChange;
+                depthInfoPtr += ctu.m_numPartitions >> 2 * depth;
+                contentInfoPtr += ctu.m_numPartitions >> 2 * depth;
+                prevCtuInfoChangePtr += ctu.m_numPartitions >> 2 * depth;
+                depthIdx++;
+            } while (ctuTemp->ctuPartitions[depthIdx] != 0);
+
+            m_additionalCtuInfo = m_frame->m_addOnCtuInfo[ctu.m_cuAddr];
+            m_prevCtuInfoChange = m_frame->m_addOnPrevChange[ctu.m_cuAddr];
+            memcpy(ctu.m_cuDepth, m_frame->m_addOnDepth[ctu.m_cuAddr], sizeof(uint8_t) * numPartition);
+            //Calculate log2CUSize from depth
+            for (uint32_t i = 0; i < cuGeom.numPartitions; i++)
+                ctu.m_log2CUSize[i] = (uint8_t)m_param->maxLog2CUSize - ctu.m_cuDepth[i];
+        }
     }
+
     if (m_param->analysisMultiPassRefine && m_param->rc.bStatRead)
     {
         m_multipassAnalysis = (analysis2PassFrameData*)m_frame->m_analysis2Pass.analysisFramedata;
@@ -204,11 +207,11 @@
         }
     }
 
-    if ((m_param->analysisSave || m_param->analysisLoad) && m_slice->m_sliceType != I_SLICE && m_param->analysisReuseLevel > 1 && m_param->analysisReuseLevel < 10)
+    if (m_param->analysisReuseMode && m_slice->m_sliceType != I_SLICE && m_param->analysisReuseLevel > 1 && m_param->analysisReuseLevel < 10)
     {
         int numPredDir = m_slice->isInterP() ? 1 : 2;
         m_reuseInterDataCTU = (analysis_inter_data*)m_frame->m_analysisData.interData;
-        m_reuseRef = &m_reuseInterDataCTU->ref [ctu.m_cuAddr * X265_MAX_PRED_MODE_PER_CTU * numPredDir];
+        m_reuseRef = &m_reuseInterDataCTU->ref[ctu.m_cuAddr * X265_MAX_PRED_MODE_PER_CTU * numPredDir];
         m_reuseDepth = &m_reuseInterDataCTU->depth[ctu.m_cuAddr * ctu.m_numPartitions];
         m_reuseModes = &m_reuseInterDataCTU->modes[ctu.m_cuAddr * ctu.m_numPartitions];
         if (m_param->analysisReuseLevel > 4)
@@ -216,7 +219,7 @@
             m_reusePartSize = &m_reuseInterDataCTU->partSize[ctu.m_cuAddr * ctu.m_numPartitions];
             m_reuseMergeFlag = &m_reuseInterDataCTU->mergeFlag[ctu.m_cuAddr * ctu.m_numPartitions];
         }
-        if (m_param->analysisSave && !m_param->analysisLoad)
+        if (m_param->analysisReuseMode == X265_ANALYSIS_SAVE)
             for (int i = 0; i < X265_MAX_PRED_MODE_PER_CTU * numPredDir; i++)
                 m_reuseRef[i] = -1;
     }
@@ -225,7 +228,7 @@
     if (m_slice->m_sliceType == I_SLICE)
     {
         analysis_intra_data* intraDataCTU = (analysis_intra_data*)m_frame->m_analysisData.intraData;
-        if (m_param->analysisLoad && m_param->analysisReuseLevel > 1)
+        if (m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->analysisReuseLevel > 1)
         {
             memcpy(ctu.m_cuDepth, &intraDataCTU->depth[ctu.m_cuAddr * numPartition], sizeof(uint8_t) * numPartition);
             memcpy(ctu.m_lumaIntraDir, &intraDataCTU->modes[ctu.m_cuAddr * numPartition], sizeof(uint8_t) * numPartition);
@@ -236,7 +239,7 @@
     }
     else
     {
-        bool bCopyAnalysis = ((m_param->analysisLoad && m_param->analysisReuseLevel == 10) || (m_param->bMVType && m_param->analysisReuseLevel >= 7 && ctu.m_numPartitions <= 16));
+        bool bCopyAnalysis = ((m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->analysisReuseLevel == 10) || (m_param->bMVType && m_param->analysisReuseLevel >= 7 && ctu.m_numPartitions <= 16));
         bool BCompressInterCUrd0_4 = (m_param->bMVType && m_param->analysisReuseLevel >= 7 && m_param->rdLevel <= 4);
         bool BCompressInterCUrd5_6 = (m_param->bMVType && m_param->analysisReuseLevel >= 7 && m_param->rdLevel >= 5 && m_param->rdLevel <= 6);
         bCopyAnalysis = bCopyAnalysis || BCompressInterCUrd0_4 || BCompressInterCUrd5_6;
@@ -277,7 +280,7 @@
             /* generate residual for entire CTU at once and copy to reconPic */
             encodeResidue(ctu, cuGeom);
         }
-        else if ((m_param->analysisLoad && m_param->analysisReuseLevel == 10) || ((m_param->bMVType == AVC_INFO) && m_param->analysisReuseLevel >= 7 && ctu.m_numPartitions <= 16))
+        else if ((m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->analysisReuseLevel == 10) || ((m_param->bMVType == AVC_INFO) && m_param->analysisReuseLevel >= 7))
         {
             analysis_inter_data* interDataCTU = (analysis_inter_data*)m_frame->m_analysisData.interData;
             int posCTU = ctu.m_cuAddr * numPartition;
@@ -456,9 +459,11 @@
 
     int bestCUQP = qp;
     int lambdaQP = lqp;
+
     bool doQPRefine = (bDecidedDepth && depth <= m_slice->m_pps->maxCuDQPDepth) || (!bDecidedDepth && depth == m_slice->m_pps->maxCuDQPDepth);
-    if (m_param->analysisReuseLevel >= 7)
+    if (m_param->analysisReuseLevel == 10)
         doQPRefine = false;
+
     if (doQPRefine)
     {
         uint64_t bestCUCost, origCUCost, cuCost, cuPrevCost;
@@ -647,12 +652,13 @@
         cacheCost[cuIdx] = md.bestMode->rdCost;
     }
 
-    if ((m_limitTU & X265_TU_LIMIT_NEIGH) && cuGeom.log2CUSize >= 4)
+    /* Save Intra CUs TU depth only when analysis mode is OFF */
+    if ((m_limitTU & X265_TU_LIMIT_NEIGH) && cuGeom.log2CUSize >= 4 && !m_param->analysisReuseMode)
     {
         CUData* ctu = md.bestMode->cu.m_encData->getPicCTU(parentCTU.m_cuAddr);
         int8_t maxTUDepth = -1;
         for (uint32_t i = 0; i < cuGeom.numPartitions; i++)
-            maxTUDepth = X265_MAX(maxTUDepth, md.bestMode->cu.m_tuDepth[i]);
+            maxTUDepth = X265_MAX(maxTUDepth, md.pred[PRED_INTRA].cu.m_tuDepth[i]);
         ctu->m_refTuDepth[cuGeom.geomRecurId] = maxTUDepth;
     }
 
@@ -1259,7 +1265,7 @@
                 mightSplit &= !bDecidedDepth;
             }
         }
-        if ((m_param->analysisLoad && m_param->analysisReuseLevel > 1 && m_param->analysisReuseLevel != 10))
+        if ((m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->analysisReuseLevel > 1 && m_param->analysisReuseLevel != 10))
         {
             if (mightNotSplit && depth == m_reuseDepth[cuGeom.absPartIdx])
             {
@@ -1299,8 +1305,9 @@
                 }
             }
         }
+
         /* Step 1. Evaluate Merge/Skip candidates for likely early-outs, if skip mode was not set above */
-        if ((mightNotSplit && depth >= minDepth && !md.bestMode && !bCtuInfoCheck) || (m_param->bMVType && m_param->analysisReuseLevel == 7 && (m_modeFlag[0] || m_modeFlag[1]))) /* TODO: Re-evaluate if analysis load/save still works */
+        if ((mightNotSplit && depth >= minDepth && !md.bestMode && !bCtuInfoCheck) || (m_param->bMVType && (m_modeFlag[0] || m_modeFlag[1]))) /* TODO: Re-evaluate if analysis load/save still works */
         {
             /* Compute Merge Cost */
             md.pred[PRED_MERGE].cu.initSubCU(parentCTU, cuGeom, qp);
@@ -1310,7 +1317,8 @@
                 skipModes = (m_param->bEnableEarlySkip || m_param->interRefine == 2)
                 && md.bestMode && md.bestMode->cu.isSkipped(0); // TODO: sa8d threshold per depth
         }
-        if (md.bestMode && m_param->bEnableRecursionSkip && !bCtuInfoCheck && !(m_param->bMVType && m_param->analysisReuseLevel == 7 && (m_modeFlag[0] || m_modeFlag[1])))
+
+        if (md.bestMode && m_param->bEnableRecursionSkip && !bCtuInfoCheck && !(m_param->bMVType && (m_modeFlag[0] || m_modeFlag[1])))
         {
             skipRecursion = md.bestMode->cu.isSkipped(0);

x265_2.7.tar.gz/source/encoder/api.cpp -> x265_2.6.tar.gz/source/encoder/api.cpp Changed

@@ -67,7 +67,9 @@
     "Y PSNR, U PSNR, V PSNR, Global PSNR, SSIM, SSIM (dB), "
     "I count, I ave-QP, I kbps, I-PSNR Y, I-PSNR U, I-PSNR V, I-SSIM (dB), "
     "P count, P ave-QP, P kbps, P-PSNR Y, P-PSNR U, P-PSNR V, P-SSIM (dB), "
-    "B count, B ave-QP, B kbps, B-PSNR Y, B-PSNR U, B-PSNR V, B-SSIM (dB), ";
+    "B count, B ave-QP, B kbps, B-PSNR Y, B-PSNR U, B-PSNR V, B-SSIM (dB), "
+    "MaxCLL, MaxFALL, Version\n";
+
 x265_encoder *x265_encoder_open(x265_param *p)
 {
     if (!p)
@@ -190,10 +192,9 @@
 {
     if (!enc || !param_in)
         return -1;
+
     x265_param save;
     Encoder* encoder = static_cast<Encoder*>(enc);
-    if (encoder->m_param->csvfn == NULL && param_in->csvfpt != NULL)
-         encoder->m_param->csvfpt = param_in->csvfpt;
     if (encoder->m_latestParam->forceFlush != param_in->forceFlush)
         return encoder->reconfigureParam(encoder->m_latestParam, param_in);
     bool isReconfigureRc = encoder->isReconfigureRc(encoder->m_latestParam, param_in);
@@ -310,9 +311,7 @@
         Encoder *encoder = static_cast<Encoder*>(enc);
         x265_stats stats;
         encoder->fetchStats(&stats, sizeof(stats));
-        int padx = encoder->m_sps.conformanceWindow.rightOffset;
-        int pady = encoder->m_sps.conformanceWindow.bottomOffset;
-        x265_csvlog_encode(encoder->m_param, &stats, padx, pady, argc, argv);
+        x265_csvlog_encode(enc, &stats, argc, argv);
     }
 }
 
@@ -357,13 +356,13 @@
     return -1;
 }
 
-int x265_get_ref_frame_list(x265_encoder *enc, x265_picyuv** l0, x265_picyuv** l1, int sliceType, int poc, int* pocL0, int* pocL1)
+int x265_get_ref_frame_list(x265_encoder *enc, x265_picyuv** l0, x265_picyuv** l1, int sliceType, int poc)
 {
     if (!enc)
         return -1;
 
     Encoder *encoder = static_cast<Encoder*>(enc);
-    return encoder->getRefFrameList((PicYuv**)l0, (PicYuv**)l1, sliceType, poc, pocL0, pocL1);
+    return encoder->getRefFrameList((PicYuv**)l0, (PicYuv**)l1, sliceType, poc);
 }
 
 int x265_set_analysis_data(x265_encoder *enc, x265_analysis_data *analysis_data, int poc, uint32_t cuBytes)
@@ -399,7 +398,7 @@
     pic->userSEI.payloads = NULL;
     pic->userSEI.numPayloads = 0;
 
-    if ((param->analysisSave || param->analysisLoad) || (param->bMVType == AVC_INFO))
+    if (param->analysisReuseMode || (param->bMVType == AVC_INFO))
     {
         uint32_t widthInCU = (param->sourceWidth + param->maxCUSize - 1) >> param->maxLog2CUSize;
         uint32_t heightInCU = (param->sourceHeight + param->maxCUSize - 1) >> param->maxLog2CUSize;
@@ -755,12 +754,7 @@
                 fprintf(csvfp, "\n");
             }
             else
-            {
                 fputs(summaryCSVHeader, csvfp);
-                if (param->csvLogLevel >= 2 || param->maxCLL || param->maxFALL)
-                    fputs("MaxCLL, MaxFALL,", csvfp);
-                fputs(" Version\n", csvfp);
-            }
         }
         return csvfp;
     }
@@ -873,40 +867,45 @@
     fflush(stderr);
 }
 
-void x265_csvlog_encode(const x265_param *p, const x265_stats *stats, int padx, int pady, int argc, char** argv)
+void x265_csvlog_encode(x265_encoder *enc, const x265_stats* stats, int argc, char** argv)
 {
-    if (p && p->csvfpt)
+    if (enc)
     {
+        Encoder *encoder = static_cast<Encoder*>(enc);
+        int padx = encoder->m_sps.conformanceWindow.rightOffset;
+        int pady = encoder->m_sps.conformanceWindow.bottomOffset;
         const x265_api * api = x265_api_get(0);
 
-        if (p->csvLogLevel)
+        if (!encoder->m_param->csvfpt)
+            return;
+
+        if (encoder->m_param->csvLogLevel)
         {
             // adding summary to a per-frame csv log file, so it needs a summary header
-            fprintf(p->csvfpt, "\nSummary\n");
-            fputs(summaryCSVHeader, p->csvfpt);
-            if (p->csvLogLevel >= 2 || p->maxCLL || p->maxFALL)
-                fputs("MaxCLL, MaxFALL,", p->csvfpt);
-            fputs(" Version\n",p->csvfpt);
+            fprintf(encoder->m_param->csvfpt, "\nSummary\n");
+            fputs(summaryCSVHeader, encoder->m_param->csvfpt);
         }
+
         // CLI arguments or other
         if (argc)
         {
-            fputc('"', p->csvfpt);
+            fputc('"', encoder->m_param->csvfpt);
             for (int i = 1; i < argc; i++)
             {
-                fputc(' ', p->csvfpt);
-                fputs(argv[i], p->csvfpt);
+                fputc(' ', encoder->m_param->csvfpt);
+                fputs(argv[i], encoder->m_param->csvfpt);
             }
-            fputc('"', p->csvfpt);
+            fputc('"', encoder->m_param->csvfpt);
         }
         else
         {
-            char *opts = x265_param2string((x265_param*)p, padx, pady);
+            const x265_param* paramTemp = encoder->m_param;
+            char *opts = x265_param2string((x265_param*)paramTemp, padx, pady);
             if (opts)
             {
-                fputc('"', p->csvfpt);
-                fputs(opts, p->csvfpt);
-                fputc('"', p->csvfpt);
+                fputc('"', encoder->m_param->csvfpt);
+                fputs(opts, encoder->m_param->csvfpt);
+                fputc('"', encoder->m_param->csvfpt);
             }
         }
 
@@ -917,70 +916,69 @@
         timeinfo = localtime(&now);
         char buffer[200];
         strftime(buffer, 128, "%c", timeinfo);
-        fprintf(p->csvfpt, ", %s, ", buffer);
+        fprintf(encoder->m_param->csvfpt, ", %s, ", buffer);
 
         // elapsed time, fps, bitrate
-        fprintf(p->csvfpt, "%.2f, %.2f, %.2f,",
+        fprintf(encoder->m_param->csvfpt, "%.2f, %.2f, %.2f,",
             stats->elapsedEncodeTime, stats->encodedPictureCount / stats->elapsedEncodeTime, stats->bitrate);
 
-        if (p->bEnablePsnr)
-            fprintf(p->csvfpt, " %.3lf, %.3lf, %.3lf, %.3lf,",
+        if (encoder->m_param->bEnablePsnr)
+            fprintf(encoder->m_param->csvfpt, " %.3lf, %.3lf, %.3lf, %.3lf,",
             stats->globalPsnrY / stats->encodedPictureCount, stats->globalPsnrU / stats->encodedPictureCount,
             stats->globalPsnrV / stats->encodedPictureCount, stats->globalPsnr);
         else
-            fprintf(p->csvfpt, " -, -, -, -,");
-        if (p->bEnableSsim)
-            fprintf(p->csvfpt, " %.6f, %6.3f,", stats->globalSsim, x265_ssim2dB(stats->globalSsim));
+            fprintf(encoder->m_param->csvfpt, " -, -, -, -,");
+        if (encoder->m_param->bEnableSsim)
+            fprintf(encoder->m_param->csvfpt, " %.6f, %6.3f,", stats->globalSsim, x265_ssim2dB(stats->globalSsim));
         else
-            fprintf(p->csvfpt, " -, -,");
+            fprintf(encoder->m_param->csvfpt, " -, -,");
 
         if (stats->statsI.numPics)
         {
-            fprintf(p->csvfpt, " %-6u, %2.2lf, %-8.2lf,", stats->statsI.numPics, stats->statsI.avgQp, stats->statsI.bitrate);
-            if (p->bEnablePsnr)
-                fprintf(p->csvfpt, " %.3lf, %.3lf, %.3lf,", stats->statsI.psnrY, stats->statsI.psnrU, stats->statsI.psnrV);
+            fprintf(encoder->m_param->csvfpt, " %-6u, %2.2lf, %-8.2lf,", stats->statsI.numPics, stats->statsI.avgQp, stats->statsI.bitrate);
+            if (encoder->m_param->bEnablePsnr)
+                fprintf(encoder->m_param->csvfpt, " %.3lf, %.3lf, %.3lf,", stats->statsI.psnrY, stats->statsI.psnrU, stats->statsI.psnrV);
             else
-                fprintf(p->csvfpt, " -, -, -,");
-            if (p->bEnableSsim)
-                fprintf(p->csvfpt, " %.3lf,", stats->statsI.ssim);
+                fprintf(encoder->m_param->csvfpt, " -, -, -,");
+            if (encoder->m_param->bEnableSsim)
+                fprintf(encoder->m_param->csvfpt, " %.3lf,", stats->statsI.ssim);
             else
-                fprintf(p->csvfpt, " -,");
+                fprintf(encoder->m_param->csvfpt, " -,");
         }
         else
-            fprintf(p->csvfpt, " -, -, -, -, -, -, -,");
+            fprintf(encoder->m_param->csvfpt, " -, -, -, -, -, -, -,");
 
         if (stats->statsP.numPics)
         {
-            fprintf(p->csvfpt, " %-6u, %2.2lf, %-8.2lf,", stats->statsP.numPics, stats->statsP.avgQp, stats->statsP.bitrate);
-            if (p->bEnablePsnr)
-                fprintf(p->csvfpt, " %.3lf, %.3lf, %.3lf,", stats->statsP.psnrY, stats->statsP.psnrU, stats->statsP.psnrV);
+            fprintf(encoder->m_param->csvfpt, " %-6u, %2.2lf, %-8.2lf,", stats->statsP.numPics, stats->statsP.avgQp, stats->statsP.bitrate);
+            if (encoder->m_param->bEnablePsnr)
+                fprintf(encoder->m_param->csvfpt, " %.3lf, %.3lf, %.3lf,", stats->statsP.psnrY, stats->statsP.psnrU, stats->statsP.psnrV);
             else
-                fprintf(p->csvfpt, " -, -, -,");
-            if (p->bEnableSsim)
-                fprintf(p->csvfpt, " %.3lf,", stats->statsP.ssim);
+                fprintf(encoder->m_param->csvfpt, " -, -, -,");
+            if (encoder->m_param->bEnableSsim)

x265_2.7.tar.gz/source/encoder/dpb.cpp -> x265_2.6.tar.gz/source/encoder/dpb.cpp Changed

@@ -92,14 +92,19 @@
             m_freeList.pushBack(*curFrame);
             curFrame->m_encData->m_freeListNext = m_frameDataFreeList;
             m_frameDataFreeList = curFrame->m_encData;
-            for (int i = 0; i < INTEGRAL_PLANE_NUM; i++)
+
+            if (curFrame->m_encData->m_meBuffer)
             {
-                if (curFrame->m_encData->m_meBuffer[i] != NULL)
+                for (int i = 0; i < INTEGRAL_PLANE_NUM; i++)
                 {
-                    X265_FREE(curFrame->m_encData->m_meBuffer[i]);
-                    curFrame->m_encData->m_meBuffer[i] = NULL;
+                    if (curFrame->m_encData->m_meBuffer[i] != NULL)
+                    {
+                        X265_FREE(curFrame->m_encData->m_meBuffer[i]);
+                        curFrame->m_encData->m_meBuffer[i] = NULL;
+                    }
                 }
             }
+
             if (curFrame->m_ctuInfo != NULL)
             {
                 uint32_t widthInCU = (curFrame->m_param->sourceWidth + curFrame->m_param->maxCUSize - 1) >> curFrame->m_param->maxLog2CUSize;
@@ -176,10 +181,7 @@
     // Mark pictures in m_piclist as unreferenced if they are not included in RPS
     applyReferencePictureSet(&slice->m_rps, pocCurr);
 
-    if (slice->m_sliceType != I_SLICE)
-        slice->m_numRefIdx[0] = x265_clip3(1, newFrame->m_param->maxNumReferences, slice->m_rps.numberOfNegativePictures);
-    else
-        slice->m_numRefIdx[0] = X265_MIN(newFrame->m_param->maxNumReferences, slice->m_rps.numberOfNegativePictures); // Ensuring L0 contains just the -ve POC
+    slice->m_numRefIdx[0] = X265_MIN(newFrame->m_param->maxNumReferences, slice->m_rps.numberOfNegativePictures); // Ensuring L0 contains just the -ve POC
     slice->m_numRefIdx[1] = X265_MIN(newFrame->m_param->bBPyramid ? 2 : 1, slice->m_rps.numberOfPositivePictures);
     slice->setRefPicList(m_picList);
 
@@ -228,14 +230,11 @@
     {
         if ((iterPic->m_poc != curPoc) && iterPic->m_encData->m_bHasReferences)
         {
-            if ((m_lastIDR >= curPoc) || (m_lastIDR <= iterPic->m_poc))
-            {
-                    rps->poc[poci] = iterPic->m_poc;
-                    rps->deltaPOC[poci] = rps->poc[poci] - curPoc;
-                    (rps->deltaPOC[poci] < 0) ? numNeg++ : numPos++;
-                    rps->bUsed[poci] = !isRAP;
-                    poci++;
-            }
+            rps->poc[poci] = iterPic->m_poc;
+            rps->deltaPOC[poci] = rps->poc[poci] - curPoc;
+            (rps->deltaPOC[poci] < 0) ? numNeg++ : numPos++;
+            rps->bUsed[poci] = !isRAP;
+            poci++;
         }
         iterPic = iterPic->m_next;
     }

x265_2.7.tar.gz/source/encoder/encoder.cpp -> x265_2.6.tar.gz/source/encoder/encoder.cpp Changed

@@ -50,8 +50,10 @@
 
 /* Threshold for motion vection, based on expermental result.
  * TODO: come up an algorithm for adoptive threshold */
-#define MVTHRESHOLD (10*10)
+
+#define MVTHRESHOLD 10
 #define PU_2Nx2N 1
+
 static const char* defaultAnalysisFileName = "x265_analysis.dat";
 
 using namespace X265_NS;
@@ -77,6 +79,7 @@
     m_param = NULL;
     m_latestParam = NULL;
     m_threadPool = NULL;
+    m_analysisFile = NULL;
     m_analysisFileIn = NULL;
     m_analysisFileOut = NULL;
     m_offsetEmergency = NULL;
@@ -341,29 +344,19 @@
         m_aborted = true;
     if (!m_lookahead->create())
         m_aborted = true;
+
     initRefIdx();
-    if (m_param->analysisSave && m_param->bUseAnalysisFile)
-    {
-        char* temp = strcatFilename(m_param->analysisSave, ".temp");
-        if (!temp)
-            m_aborted = true;
-        else
-        {
-            m_analysisFileOut = x265_fopen(temp, "wb");
-            X265_FREE(temp);
-        }
-        if (!m_analysisFileOut)
-        {
-            x265_log_file(NULL, X265_LOG_ERROR, "Analysis save: failed to open file %s.temp\n", m_param->analysisSave);
-            m_aborted = true;
-        }
-    }
-    if (m_param->analysisLoad && m_param->bUseAnalysisFile)
+
+    if (m_param->analysisReuseMode)
     {
-        m_analysisFileIn = x265_fopen(m_param->analysisLoad, "rb");
-        if (!m_analysisFileIn)
+        const char* name = m_param->analysisReuseFileName;
+        if (!name)
+            name = defaultAnalysisFileName;
+        const char* mode = m_param->analysisReuseMode == X265_ANALYSIS_LOAD ? "rb" : "wb";
+        m_analysisFile = x265_fopen(name, mode);
+        if (!m_analysisFile)
         {
-            x265_log_file(NULL, X265_LOG_ERROR, "Analysis load: failed to open file %s\n", m_param->analysisLoad);
+            x265_log_file(NULL, X265_LOG_ERROR, "Analysis load/save: failed to open file %s\n", name);
             m_aborted = true;
         }
     }
@@ -457,7 +450,7 @@
     return 0;
 }
 
-int Encoder::getRefFrameList(PicYuv** l0, PicYuv** l1, int sliceType, int poc, int* pocL0, int* pocL1)
+int Encoder::getRefFrameList(PicYuv** l0, PicYuv** l1, int sliceType, int poc)
 {
     if (!(IS_X265_TYPE_I(sliceType)))
     {
@@ -469,10 +462,9 @@
                 if (framePtr->m_encData->m_slice->m_refFrameList[0][j] && framePtr->m_encData->m_slice->m_refFrameList[0][j]->m_reconPic != NULL)
                 {
                     int l0POC = framePtr->m_encData->m_slice->m_refFrameList[0][j]->m_poc;
-                    pocL0[j] = l0POC;
                     Frame* l0Fp = m_dpb->m_picList.getPOC(l0POC);
-                    while (l0Fp->m_reconRowFlag[l0Fp->m_numRows - 1].get() == 0)
-                        l0Fp->m_reconRowFlag[l0Fp->m_numRows - 1].waitForChange(0); /* If recon is not ready, current frame encoder has to wait. */
+                    if (l0Fp->m_reconPic->m_picOrg[0] == NULL)
+                        l0Fp->m_reconEncoded.wait(); /* If recon is not ready, current frame encoder need to wait. */
                     l0[j] = l0Fp->m_reconPic;
                 }
             }
@@ -481,19 +473,15 @@
                 if (framePtr->m_encData->m_slice->m_refFrameList[1][j] && framePtr->m_encData->m_slice->m_refFrameList[1][j]->m_reconPic != NULL)
                 {
                     int l1POC = framePtr->m_encData->m_slice->m_refFrameList[1][j]->m_poc;
-                    pocL1[j] = l1POC;
                     Frame* l1Fp = m_dpb->m_picList.getPOC(l1POC);
-                    while (l1Fp->m_reconRowFlag[l1Fp->m_numRows - 1].get() == 0)
-                        l1Fp->m_reconRowFlag[l1Fp->m_numRows - 1].waitForChange(0); /* If recon is not ready, current frame encoder has to wait. */
+                    if (l1Fp->m_reconPic->m_picOrg[0] == NULL)
+                        l1Fp->m_reconEncoded.wait(); /* If recon is not ready, current frame encoder need to wait. */
                     l1[j] = l1Fp->m_reconPic;
                 }
             }
         }
         else
-        {
-            x265_log(NULL, X265_LOG_WARNING, "Current frame is not in DPB piclist.\n");
-            return 1;
-        }
+            x265_log(NULL, X265_LOG_WARNING, "Refrence List is not in piclist\n");
     }
     else
     {
@@ -576,19 +564,19 @@
                     {
                         int cuOffset = cuI * bytes + pu;
                         (interData)->mergeFlag[cuPos + cuOffset] = (srcInterData)->mergeFlag[(mbIndex * 16) + cuOffset];
-                        (interData)->sadCost[cuPos + cuOffset] = (srcInterData)->sadCost[(mbIndex * 16) + cuOffset];
+
                         (interData)->interDir[cuPos + cuOffset] = (srcInterData)->interDir[(mbIndex * 16) + cuOffset];
                         for (uint32_t k = 0; k < numDir; k++)
                         {
                             (interData)->mvpIdx[k][cuPos + cuOffset] = (srcInterData)->mvpIdx[k][(mbIndex * 16) + cuOffset];
                             (interData)->refIdx[k][cuPos + cuOffset] = (srcInterData)->refIdx[k][(mbIndex * 16) + cuOffset];
                             memcpy(&(interData)->mv[k][cuPos + cuOffset], &(srcInterData)->mv[k][(mbIndex * 16) + cuOffset], sizeof(MV));
-                            if (m_param->analysisReuseLevel == 7 && numPU == PU_2Nx2N &&
-                                ((interData)->depth[cuPos + cuOffset] == (m_param->maxCUSize >> 5)))
+                            if (m_param->analysisReuseLevel == 7)
                             {
-                                int mv_x = (interData)->mv[k][cuPos + cuOffset].x;
-                                int mv_y = (interData)->mv[k][cuPos + cuOffset].y;
-                                if ((mv_x*mv_x + mv_y*mv_y) <= MVTHRESHOLD)
+                                int mv_x = ((analysis_inter_data *)curFrame->m_analysisData.interData)->mv[k][(mbIndex * 16) + cuOffset].x;
+                                int mv_y = ((analysis_inter_data *)curFrame->m_analysisData.interData)->mv[k][(mbIndex * 16) + cuOffset].y;
+                                double mv = sqrt(mv_x*mv_x + mv_y*mv_y);
+                                if (numPU == PU_2Nx2N && ((srcInterData)->depth[cuPos + cuOffset] == (m_param->maxCUSize >> 5)) && mv <= MVTHRESHOLD)
                                     memset(&curFrame->m_analysisData.modeFlag[k][cuPos + cuOffset], 1, bytes);
                             }
                         }
@@ -654,10 +642,9 @@
                     if (m_param->analysisReuseLevel > 4)
                     {
                         memset(&(currInterData)->partSize[count], (interData)->partSize[d], bytes);
-                        int numPU = nbPartsTable[(interData)->partSize[d]];
-                        for (int pu = 0; pu < numPU; pu++)
+                        int numPU = nbPartsTable[(currInterData)->partSize[d]];
+                        for (int pu = 0; pu < numPU; pu++, d++)
                         {
-                            if (pu) d++;
                             (currInterData)->mergeFlag[count + pu] = (interData)->mergeFlag[d];
                             if (m_param->analysisReuseLevel >= 7)
                             {
@@ -667,11 +654,12 @@
                                     (currInterData)->mvpIdx[i][count + pu] = (interData)->mvpIdx[i][d];
                                     (currInterData)->refIdx[i][count + pu] = (interData)->refIdx[i][d];
                                     memcpy(&(currInterData)->mv[i][count + pu], &(interData)->mv[i][d], sizeof(MV));
-                                    if (m_param->analysisReuseLevel == 7 && numPU == PU_2Nx2N && m_param->num4x4Partitions <= 16)
+                                    if (m_param->analysisReuseLevel == 7)
                                     {
-                                        int mv_x = (currInterData)->mv[i][count + pu].x;
-                                        int mv_y = (currInterData)->mv[i][count + pu].y;
-                                        if ((mv_x*mv_x + mv_y*mv_y) <= MVTHRESHOLD)
+                                        int mv_x = ((analysis_inter_data *)curFrame->m_analysisData.interData)->mv[i][count + pu].x;
+                                        int mv_y = ((analysis_inter_data *)curFrame->m_analysisData.interData)->mv[i][count + pu].y;
+                                        double mv = sqrt(mv_x*mv_x + mv_y*mv_y);
+                                        if (numPU == PU_2Nx2N && m_param->num4x4Partitions <= 16 && mv <= MVTHRESHOLD)
                                             memset(&curFrame->m_analysisData.modeFlag[i][count + pu], 1, bytes);
                                     }
                                 }
@@ -732,6 +720,9 @@
 
     X265_FREE(m_offsetEmergency);
 
+    if (m_analysisFile)
+        fclose(m_analysisFile);
+
     if (m_latestParam != NULL && m_latestParam != m_param)
     {
         if (m_latestParam->scalingLists != m_param->scalingLists)
@@ -746,7 +737,7 @@
     {
         int bError = 1;
         fclose(m_analysisFileOut);
-        const char* name = m_param->analysisSave ? m_param->analysisSave : m_param->analysisReuseFileName;
+        const char* name = m_param->analysisReuseFileName;
         if (!name)
             name = defaultAnalysisFileName;
         char* temp = strcatFilename(name, ".temp");
@@ -774,8 +765,6 @@
         free((char*)m_param->numaPools);
         free((char*)m_param->masteringDisplayColorVolume);
         free((char*)m_param->toneMapFile);
-        free((char*)m_param->analysisSave);
-        free((char*)m_param->analysisLoad);
         PARAM_NS::x265_param_free(m_param);
     }
 }
@@ -862,7 +851,7 @@
 
     if (m_exportedPic)
     {
-        if (!m_param->bUseAnalysisFile && m_param->analysisSave)
+        if (!m_param->bUseAnalysisFile && m_param->analysisReuseMode == X265_ANALYSIS_SAVE)
             freeAnalysis(&m_exportedPic->m_analysisData);
         ATOMIC_DEC(&m_exportedPic->m_countRefEncoders);
         m_exportedPic = NULL;
@@ -1047,7 +1036,7 @@

x265_2.7.tar.gz/source/encoder/encoder.h -> x265_2.6.tar.gz/source/encoder/encoder.h Changed

x265_2.7.tar.gz/source/encoder/frameencoder.cpp -> x265_2.6.tar.gz/source/encoder/frameencoder.cpp Changed

@@ -335,13 +335,15 @@
             while (!m_frame->m_ctuInfo)
                 m_frame->m_copied.wait();
         }
-        if ((m_param->bMVType == AVC_INFO) && !m_param->analysisSave && !m_param->analysisLoad && !(IS_X265_TYPE_I(m_frame->m_lowres.sliceType)))
+        if ((m_param->bMVType == AVC_INFO) && !m_param->analysisReuseMode && !(IS_X265_TYPE_I(m_frame->m_lowres.sliceType)))
         {
             while (((m_frame->m_analysisData.interData == NULL && m_frame->m_analysisData.intraData == NULL) || (uint32_t)m_frame->m_poc != m_frame->m_analysisData.poc))
                 m_frame->m_copyMVType.wait();
         }
         compressFrame();
         m_done.trigger(); /* FrameEncoder::getEncodedPicture() blocks for this event */
+        if (m_frame != NULL)
+            m_frame->m_reconEncoded.trigger();
         m_enable.wait();
     }
 }
@@ -430,7 +432,7 @@
     bool bUseWeightB = slice->m_sliceType == B_SLICE && slice->m_pps->bUseWeightedBiPred;
 
     WeightParam* reuseWP = NULL;
-    if (m_param->analysisLoad && (bUseWeightP || bUseWeightB))
+    if (m_param->analysisReuseMode && (bUseWeightP || bUseWeightB))
         reuseWP = (WeightParam*)m_frame->m_analysisData.wt;
 
     if (bUseWeightP || bUseWeightB)
@@ -439,7 +441,7 @@
         m_cuStats.countWeightAnalyze++;
         ScopedElapsedTime time(m_cuStats.weightAnalyzeTime);
 #endif
-        if (m_param->analysisLoad)
+        if (m_param->analysisReuseMode == X265_ANALYSIS_LOAD)
         {
             for (int list = 0; list < slice->isInterB() + 1; list++) 
             {
@@ -466,8 +468,6 @@
     else
         slice->disableWeights();
 
-    if (m_param->analysisSave && (bUseWeightP || bUseWeightB))
-        reuseWP = (WeightParam*)m_frame->m_analysisData.wt;
     // Generate motion references
     int numPredDir = slice->isInterP() ? 1 : slice->isInterB() ? 2 : 0;
     for (int l = 0; l < numPredDir; l++)
@@ -480,7 +480,7 @@
             slice->m_refReconPicList[l][ref] = slice->m_refFrameList[l][ref]->m_reconPic;
             m_mref[l][ref].init(slice->m_refReconPicList[l][ref], w, *m_param);
         }
-        if (m_param->analysisSave && (bUseWeightP || bUseWeightB))
+        if (m_param->analysisReuseMode == X265_ANALYSIS_SAVE && (bUseWeightP || bUseWeightB))
         {
             for (int i = 0; i < (m_param->internalCsp != X265_CSP_I400 ? 3 : 1); i++)
                 *(reuseWP++) = slice->m_weightPredTable[l][0][i];
@@ -1413,7 +1413,7 @@
             /* TODO: use defines from slicetype.h for lowres block size */
             uint32_t block_y = (ctu->m_cuPelY >> m_param->maxLog2CUSize) * noOfBlocks;
             uint32_t block_x = (ctu->m_cuPelX >> m_param->maxLog2CUSize) * noOfBlocks;
-            if (!m_param->analysisLoad || !m_param->bDisableLookahead)
+            if (m_param->analysisReuseMode != X265_ANALYSIS_LOAD || !m_param->bDisableLookahead)
             {
                 cuStat.vbvCost = 0;
                 cuStat.intraVbvCost = 0;
@@ -1748,8 +1748,8 @@
         if (rowInSlice == rowCount)
         {
             m_rowSliceTotalBits[sliceId] = 0;
-            if (bIsVbv && !(m_param->rc.bEnableConstVbv && m_param->bEnableWavefront))
-            {          
+            if (bIsVbv)
+            {                
                 for (uint32_t i = m_sliceBaseRow[sliceId]; i < rowCount + m_sliceBaseRow[sliceId]; i++)
                     m_rowSliceTotalBits[sliceId] += curEncData.m_rowStat[i].encodedBits;
             }

x265_2.7.tar.gz/source/encoder/framefilter.cpp -> x265_2.6.tar.gz/source/encoder/framefilter.cpp Changed

x265_2.7.tar.gz/source/encoder/ratecontrol.cpp -> x265_2.6.tar.gz/source/encoder/ratecontrol.cpp Changed

x265_2.7.tar.gz/source/encoder/ratecontrol.h -> x265_2.6.tar.gz/source/encoder/ratecontrol.h Changed

x265_2.7.tar.gz/source/encoder/sao.h -> x265_2.6.tar.gz/source/encoder/sao.h Changed

x265_2.7.tar.gz/source/encoder/search.cpp -> x265_2.6.tar.gz/source/encoder/search.cpp Changed

@@ -1947,7 +1947,7 @@
         /* poc difference is out of range for lookahead */
         return 0;
 
-    MV* mvs = m_frame->m_lowres.lowresMvs[list][diffPoc];
+    MV* mvs = m_frame->m_lowres.lowresMvs[list][diffPoc - 1];
     if (mvs[0].x == 0x7FFF)
         /* this motion search was not estimated by lookahead */
         return 0;
@@ -2073,7 +2073,7 @@
     int mvpIdx = selectMVP(interMode.cu, pu, amvp, list, ref);
     MV mvmin, mvmax, outmv, mvp = amvp[mvpIdx];
 
-    if (!m_param->analysisSave && !m_param->analysisLoad) /* Prevents load/save outputs from diverging if lowresMV is not available */
+    if (!m_param->analysisReuseMode) /* Prevents load/save outputs from diverging if lowresMV is not available */
     {
         MV lmv = getLowresMV(interMode.cu, pu, list, ref);
         if (lmv.notZero())
@@ -2161,7 +2161,7 @@
         cu.getNeighbourMV(puIdx, pu.puAbsPartIdx, interMode.interNeighbours);
 
         /* Uni-directional prediction */
-        if ((m_param->analysisLoad && m_param->analysisReuseLevel > 1 && m_param->analysisReuseLevel != 10)
+        if ((m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->analysisReuseLevel > 1 && m_param->analysisReuseLevel != 10)
             || (m_param->analysisMultiPassRefine && m_param->rc.bStatRead) || (m_param->bMVType == AVC_INFO))
         {
             for (int list = 0; list < numPredDir; list++)
@@ -2297,7 +2297,7 @@
                     int mvpIdx = selectMVP(cu, pu, amvp, list, ref);
                     MV mvmin, mvmax, outmv, mvp = amvp[mvpIdx];
 
-                    if (!m_param->analysisSave && !m_param->analysisLoad) /* Prevents load/save outputs from diverging when lowresMV is not available */
+                    if (!m_param->analysisReuseMode) /* Prevents load/save outputs from diverging when lowresMV is not available */
                     {
                         MV lmv = getLowresMV(cu, pu, list, ref);
                         if (lmv.notZero())

x265_2.7.tar.gz/source/encoder/slicetype.cpp -> x265_2.6.tar.gz/source/encoder/slicetype.cpp Changed

@@ -154,7 +154,7 @@
     int blockXY = 0;
     int blockX = 0, blockY = 0;
     double strength = 0.f;
-    if ((param->rc.aqMode == X265_AQ_NONE || param->rc.aqStrength == 0) || (param->rc.bStatRead && param->rc.cuTree && IS_REFERENCED(curFrame)))
+    if (param->rc.aqMode == X265_AQ_NONE || param->rc.aqStrength == 0)
     {
         /* Need to init it anyways for CU tree */
         int cuCount = blockCount;
@@ -589,7 +589,7 @@
     m_outputSignalRequired = false;
     m_isActive = true;
     m_inputCount = 0;
-    m_extendGopBoundary = false;
+
     m_8x8Height = ((m_param->sourceHeight / 2) + X265_LOWRES_CU_SIZE - 1) >> X265_LOWRES_CU_BITS;
     m_8x8Width = ((m_param->sourceWidth / 2) + X265_LOWRES_CU_SIZE - 1) >> X265_LOWRES_CU_BITS;
     m_cuCount = m_8x8Width * m_8x8Height;
@@ -646,11 +646,7 @@
         m_numRowsPerSlice = m_8x8Height;
         m_numCoopSlices = 1;
     }
-    if (param->gopLookahead && (param->gopLookahead > (param->lookaheadDepth - param->bframes - 2)))
-    {
-        param->gopLookahead = X265_MAX(0, param->lookaheadDepth - param->bframes - 2);
-        x265_log(param, X265_LOG_WARNING, "Gop-lookahead cannot be greater than (rc-lookahead - length of the mini-gop); Clipping gop-lookahead to %d\n", param->gopLookahead);
-    }
+
 #if DETAILED_CU_STATS
     m_slicetypeDecideElapsedTime = 0;
     m_preLookaheadElapsedTime = 0;
@@ -746,7 +742,7 @@
 /* Called by API thread */
 void Lookahead::addPicture(Frame& curFrame, int sliceType)
 {
-    if (m_param->analysisLoad && m_param->bDisableLookahead)
+    if (m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->bDisableLookahead)
     {
         if (!m_filled)
             m_filled = true;
@@ -847,7 +843,7 @@
             return out;
         }
 
-        if (m_param->analysisLoad && m_param->bDisableLookahead)
+        if (m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->bDisableLookahead)
             return NULL;
 
         findJob(-1); /* run slicetypeDecide() if necessary */
@@ -879,7 +875,7 @@
     Slice *slice = curFrame->m_encData->m_slice;
     int p0 = 0, p1, b;
     int poc = slice->m_poc;
-    int l0poc = slice->m_rps.numberOfNegativePictures ? slice->m_refPOCList[0][0] : -1;
+    int l0poc = slice->m_refPOCList[0][0];
     int l1poc = slice->m_refPOCList[1][0];
 
     switch (slice->m_sliceType)
@@ -896,34 +892,23 @@
         break;
 
     case B_SLICE:
-        if (l0poc >= 0)
-        {
-            b = poc - l0poc;
-            p1 = b + l1poc - poc;
-            frames[p0] = &slice->m_refFrameList[0][0]->m_lowres;
-            frames[b] = &curFrame->m_lowres;
-            frames[p1] = &slice->m_refFrameList[1][0]->m_lowres;
-        }
-        else 
-        {
-            p0 = b = 0;
-            p1 = b + l1poc - poc;
-            frames[p0] = frames[b] = &curFrame->m_lowres;
-            frames[p1] = &slice->m_refFrameList[1][0]->m_lowres;
-        }
-        
+        b = poc - l0poc;
+        p1 = b + l1poc - poc;
+        frames[p0] = &slice->m_refFrameList[0][0]->m_lowres;
+        frames[b] = &curFrame->m_lowres;
+        frames[p1] = &slice->m_refFrameList[1][0]->m_lowres;
         break;
 
     default:
         return;
     }
-    if (!m_param->analysisLoad || !m_param->bDisableLookahead)
+    if (m_param->analysisReuseMode != X265_ANALYSIS_LOAD || !m_param->bDisableLookahead)
     {
         X265_CHECK(curFrame->m_lowres.costEst[b - p0][p1 - b] > 0, "Slice cost not estimated\n")
         if (m_param->rc.cuTree && !m_param->rc.bStatRead)
             /* update row satds based on cutree offsets */
             curFrame->m_lowres.satdCost = frameCostRecalculate(frames, p0, p1, b);
-        else if (!m_param->analysisLoad || m_param->scaleFactor)
+        else if (m_param->analysisReuseMode != X265_ANALYSIS_LOAD || m_param->scaleFactor)
         {
             if (m_param->rc.aqMode)
                 curFrame->m_lowres.satdCost = curFrame->m_lowres.costEstAq[b - p0][p1 - b];
@@ -997,8 +982,11 @@
         ProfileLookaheadTime(m_lookahead.m_preLookaheadElapsedTime, m_lookahead.m_countPreLookahead);
         ProfileScopeEvent(prelookahead);
         m_lock.release();
+
         preFrame->m_lowres.init(preFrame->m_fencPic, preFrame->m_poc);
-        if (m_lookahead.m_bAdaptiveQuant)
+        if (m_lookahead.m_param->rc.bStatRead && m_lookahead.m_param->rc.cuTree && IS_REFERENCED(preFrame))
+            /* cu-tree offsets were read from stats file */;
+        else if (m_lookahead.m_bAdaptiveQuant)
             tld.calcAdaptiveQuantFrame(preFrame, m_lookahead.m_param);
         tld.lowresIntraEstimate(preFrame->m_lowres, m_lookahead.m_param->rc.qgSize);
         preFrame->m_lowresInit = true;
@@ -1064,7 +1052,7 @@
     {
         slicetypeAnalyse(frames, false);
         bool bIsVbv = m_param->rc.vbvBufferSize > 0 && m_param->rc.vbvMaxBitrate > 0;
-        if (m_param->analysisLoad && m_param->scaleFactor && bIsVbv)
+        if (m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->scaleFactor && bIsVbv)
         {
             int numFrames;
             for (numFrames = 0; numFrames < maxSearch; numFrames++)
@@ -1098,8 +1086,7 @@
             x265_log(m_param, X265_LOG_WARNING, "B-ref at frame %d incompatible with B-pyramid and %d reference frames\n",
                      frm.sliceType, m_param->maxNumReferences);
         }
-        if ((!m_param->bIntraRefresh || frm.frameNum == 0) && frm.frameNum - m_lastKeyframe >= m_param->keyframeMax &&
-            (!m_extendGopBoundary || frm.frameNum - m_lastKeyframe >= m_param->keyframeMax + m_param->gopLookahead))
+        if ((!m_param->bIntraRefresh || frm.frameNum == 0) && frm.frameNum - m_lastKeyframe >= m_param->keyframeMax)
         {
             if (frm.sliceType == X265_TYPE_AUTO || frm.sliceType == X265_TYPE_I)
                 frm.sliceType = m_param->bOpenGOP && m_lastKeyframe >= 0 ? X265_TYPE_I : X265_TYPE_IDR;
@@ -1128,20 +1115,12 @@
             /* Closed GOP */
             m_lastKeyframe = frm.frameNum;
             frm.bKeyframe = true;
-            if (bframes > 0 && !m_param->radl)
+            if (bframes > 0)
             {
                 list[bframes - 1]->m_lowres.sliceType = X265_TYPE_P;
                 bframes--;
             }
         }
-        if (m_param->radl && !m_param->bOpenGOP && list[bframes + 1])
-        {
-            if ((frm.frameNum - m_lastKeyframe) >  (m_param->keyframeMax - m_param->radl - 1) && (frm.frameNum - m_lastKeyframe) <  m_param->keyframeMax)
-                frm.sliceType = X265_TYPE_B;
-            if ((frm.frameNum - m_lastKeyframe) == (m_param->keyframeMax - m_param->radl - 1))
-                frm.sliceType = X265_TYPE_P;
-        }
-
         if (bframes == m_param->bframes || !list[bframes + 1])
         {
             if (IS_X265_TYPE_B(frm.sliceType))
@@ -1191,13 +1170,8 @@
         if (bframes)
         {
             p0 = 0; // last nonb
-            bool isp0available = frames[bframes + 1]->sliceType == X265_TYPE_IDR ? false : true;
-
             for (b = 1; b <= bframes; b++)
             {
-                if (!isp0available)
-                    p0 = b;
-
                 if (frames[b]->sliceType == X265_TYPE_B)
                     for (p1 = b; frames[p1]->sliceType == X265_TYPE_B; p1++)
                         ; // find new nonb or bref
@@ -1207,10 +1181,7 @@
                 estGroup.singleCost(p0, p1, b);
 
                 if (frames[b]->sliceType == X265_TYPE_BREF)
-                {
                     p0 = b;
-                    isp0available = true;
-                }
             }
         }
     }
@@ -1234,8 +1205,9 @@
     int idx = 0;
     list[bframes]->m_reorderedPts = pts[idx++];
     m_outputQueue.pushBack(*list[bframes]);
+
     /* Add B-ref frame next to P frame in output queue, the B-ref encode before non B-ref frame */
-    if (brefs)
+    if (bframes > 1 && m_param->bBPyramid)
     {
         for (int i = 0; i < bframes; i++)
         {
@@ -1275,7 +1247,7 @@
         frames[j + 1] = NULL;
         slicetypeAnalyse(frames, true);
         bool bIsVbv = m_param->rc.vbvBufferSize > 0 && m_param->rc.vbvMaxBitrate > 0;
-        if (m_param->analysisLoad && m_param->scaleFactor && bIsVbv)
+        if (m_param->analysisReuseMode == X265_ANALYSIS_LOAD && m_param->scaleFactor && bIsVbv)
         {
             int numFrames;
             for (numFrames = 0; numFrames < maxSearch; numFrames++)
@@ -1405,14 +1377,12 @@

x265_2.7.tar.gz/source/encoder/slicetype.h -> x265_2.6.tar.gz/source/encoder/slicetype.h Changed

x265_2.7.tar.gz/source/encoder/weightPrediction.cpp -> x265_2.6.tar.gz/source/encoder/weightPrediction.cpp Changed

x265_2.7.tar.gz/source/input/y4m.cpp -> x265_2.6.tar.gz/source/input/y4m.cpp Changed

@@ -20,8 +20,7 @@
  * This program is also available under a commercial proprietary license.
  * For more information, contact us at license @ x265.com.
  *****************************************************************************/
-#define _FILE_OFFSET_BITS 64
-#define _LARGEFILE_SOURCE
+
 #include "y4m.h"
 #include "common.h"
 
@@ -39,7 +38,9 @@
 
 using namespace X265_NS;
 using namespace std;
-static const char header[] = {'F','R','A','M','E'};
+
+static const char header[] = "FRAME";
+
 Y4MInput::Y4MInput(InputFileInfo& info)
 {
     for (int i = 0; i < QUEUE_SIZE; i++)
@@ -59,14 +60,15 @@
     ifs = NULL;
     if (!strcmp(info.filename, "-"))
     {
-        ifs = stdin;
+        ifs = &cin;
 #if _WIN32
         setmode(fileno(stdin), O_BINARY);
 #endif
     }
     else
-        ifs = x265_fopen(info.filename, "rb");
-    if (ifs && !ferror(ifs) && parseHeader())
+        ifs = new ifstream(info.filename, ios::binary | ios::in);
+
+    if (ifs && ifs->good() && parseHeader())
     {
         int pixelbytes = depth > 8 ? 2 : 1;
         for (int i = 0; i < x265_cli_csps[colorSpace].planes; i++)
@@ -89,8 +91,8 @@
     }
     if (!threadActive)
     {
-        if (ifs && ifs != stdin)
-            fclose(ifs);
+        if (ifs && ifs != &cin)
+            delete ifs;
         ifs = NULL;
         return;
     }
@@ -104,34 +106,61 @@
     info.csp = colorSpace;
     info.depth = depth;
     info.frameCount = -1;
-    size_t estFrameSize = framesize + sizeof(header) + 1; /* assume basic FRAME\n headers */
+
+    size_t estFrameSize = framesize + strlen(header) + 1; /* assume basic FRAME\n headers */
+
     /* try to estimate frame count, if this is not stdin */
-    if (ifs != stdin)
+    if (ifs != &cin)
     {
-        int64_t cur = ftello(ifs);
+        istream::pos_type cur = ifs->tellg();
+
+#if defined(_MSC_VER) && _MSC_VER < 1700
+        /* Older MSVC versions cannot handle 64bit file sizes properly, so go native */
+        HANDLE hFile = CreateFileA(info.filename, GENERIC_READ,
+                                   FILE_SHARE_READ | FILE_SHARE_WRITE, NULL, OPEN_EXISTING,
+                                   FILE_ATTRIBUTE_NORMAL, NULL);
+        if (hFile != INVALID_HANDLE_VALUE)
+        {
+            LARGE_INTEGER size;
+            if (GetFileSizeEx(hFile, &size))
+                info.frameCount = (int)((size.QuadPart - (int64_t)cur) / estFrameSize);
+            CloseHandle(hFile);
+        }
+#else // if defined(_MSC_VER) && _MSC_VER < 1700
         if (cur >= 0)
         {
-            fseeko(ifs, 0, SEEK_END);
-            int64_t size = ftello(ifs);
-            fseeko(ifs, cur, SEEK_SET);
+            ifs->seekg(0, ios::end);
+            istream::pos_type size = ifs->tellg();
+            ifs->seekg(cur, ios::beg);
             if (size > 0)
                 info.frameCount = (int)((size - cur) / estFrameSize);
         }
+#endif // if defined(_MSC_VER) && _MSC_VER < 1700
     }
+
     if (info.skipFrames)
     {
-        if (ifs != stdin)
-            fseeko(ifs, (int64_t)estFrameSize * info.skipFrames, SEEK_CUR);
+#if X86_64
+        if (ifs != &cin)
+            ifs->seekg((uint64_t)estFrameSize * info.skipFrames, ios::cur);
         else
             for (int i = 0; i < info.skipFrames; i++)
-                if (fread(buf[0], estFrameSize - framesize, 1, ifs) + fread(buf[0], framesize, 1, ifs) != 2)
-                    break;
+            {
+                ifs->read(buf[0], estFrameSize - framesize);
+                ifs->read(buf[0], framesize);
+            }
+#else
+        for (int i = 0; i < info.skipFrames; i++)
+            ifs->ignore(estFrameSize);
+#endif
     }
 }
+
 Y4MInput::~Y4MInput()
 {
-    if (ifs && ifs != stdin)
-        fclose(ifs);
+    if (ifs && ifs != &cin)
+        delete ifs;
+
     for (int i = 0; i < QUEUE_SIZE; i++)
         X265_FREE(buf[i]);
 }
@@ -151,31 +180,37 @@
 
     int csp = 0;
     int d = 0;
-    int c;
-    while ((c = fgetc(ifs)) != EOF)
+
+    while (ifs->good())
     {
         // Skip Y4MPEG string
-        while ((c != EOF) && (c != ' ') && (c != '\n'))
-            c = fgetc(ifs);
-        while (c == ' ')
+        int c = ifs->get();
+        while (ifs->good() && (c != ' ') && (c != '\n'))
+            c = ifs->get();
+
+        while (c == ' ' && ifs->good())
         {
             // read parameter identifier
-            switch (fgetc(ifs))
+            switch (ifs->get())
             {
             case 'W':
                 width = 0;
-                while ((c = fgetc(ifs)) != EOF)
+                while (ifs->good())
                 {
+                    c = ifs->get();
+
                     if (c == ' ' || c == '\n')
                         break;
                     else
                         width = width * 10 + (c - '0');
                 }
                 break;
+
             case 'H':
                 height = 0;
-                while ((c = fgetc(ifs)) != EOF)
+                while (ifs->good())
                 {
+                    c = ifs->get();
                     if (c == ' ' || c == '\n')
                         break;
                     else
@@ -186,13 +221,15 @@
             case 'F':
                 rateNum = 0;
                 rateDenom = 0;
-                while ((c = fgetc(ifs)) != EOF)
+                while (ifs->good())
                 {
+                    c = ifs->get();
                     if (c == '.')
                     {
                         rateDenom = 1;
-                        while ((c = fgetc(ifs)) != EOF)
+                        while (ifs->good())
                         {
+                            c = ifs->get();
                             if (c == ' ' || c == '\n')
                                 break;
                             else
@@ -205,8 +242,9 @@
                     }
                     else if (c == ':')
                     {
-                        while ((c = fgetc(ifs)) != EOF)
+                        while (ifs->good())
                         {
+                            c = ifs->get();
                             if (c == ' ' || c == '\n')
                                 break;
                             else

x265_2.7.tar.gz/source/input/y4m.h -> x265_2.6.tar.gz/source/input/y4m.h Changed

x265_2.7.tar.gz/source/input/yuv.cpp -> x265_2.6.tar.gz/source/input/yuv.cpp Changed

@@ -20,8 +20,7 @@
  * This program is also available under a commercial proprietary license.
  * For more information, contact us at license @ x265.com.
  *****************************************************************************/
-#define _FILE_OFFSET_BITS 64
-#define _LARGEFILE_SOURCE
+
 #include "yuv.h"
 #include "common.h"
 
@@ -66,21 +65,23 @@
         x265_log(NULL, X265_LOG_ERROR, "yuv: width, height, and FPS must be specified\n");
         return;
     }
+
     if (!strcmp(info.filename, "-"))
     {
-        ifs = stdin;
+        ifs = &cin;
 #if _WIN32
         setmode(fileno(stdin), O_BINARY);
 #endif
     }
     else
-        ifs = x265_fopen(info.filename, "rb");
-    if (ifs && !ferror(ifs))
+        ifs = new ifstream(info.filename, ios::binary | ios::in);
+
+    if (ifs && ifs->good())
         threadActive = true;
     else
     {
-        if (ifs && ifs != stdin)
-            fclose(ifs);
+        if (ifs && ifs != &cin)
+            delete ifs;
         ifs = NULL;
         return;
     }
@@ -97,33 +98,55 @@
     }
 
     info.frameCount = -1;
+
     /* try to estimate frame count, if this is not stdin */
-    if (ifs != stdin)
+    if (ifs != &cin)
     {
-        int64_t cur = ftello(ifs);
+        istream::pos_type cur = ifs->tellg();
+
+#if defined(_MSC_VER) && _MSC_VER < 1700
+        /* Older MSVC versions cannot handle 64bit file sizes properly, so go native */
+        HANDLE hFile = CreateFileA(info.filename, GENERIC_READ,
+                                   FILE_SHARE_READ | FILE_SHARE_WRITE, NULL, OPEN_EXISTING,
+                                   FILE_ATTRIBUTE_NORMAL, NULL);
+        if (hFile != INVALID_HANDLE_VALUE)
+        {
+            LARGE_INTEGER size;
+            if (GetFileSizeEx(hFile, &size))
+                info.frameCount = (int)((size.QuadPart - (int64_t)cur) / framesize);
+            CloseHandle(hFile);
+        }
+#else // if defined(_MSC_VER) && _MSC_VER < 1700
         if (cur >= 0)
         {
-            fseeko(ifs, 0, SEEK_END);
-            int64_t size = ftello(ifs);
-            fseeko(ifs, cur, SEEK_SET);
+            ifs->seekg(0, ios::end);
+            istream::pos_type size = ifs->tellg();
+            ifs->seekg(cur, ios::beg);
             if (size > 0)
                 info.frameCount = (int)((size - cur) / framesize);
         }
+#endif // if defined(_MSC_VER) && _MSC_VER < 1700
     }
+
     if (info.skipFrames)
     {
-        if (ifs != stdin)
-            fseeko(ifs, (int64_t)framesize * info.skipFrames, SEEK_CUR);
+#if X86_64
+        if (ifs != &cin)
+            ifs->seekg((uint64_t)framesize * info.skipFrames, ios::cur);
         else
             for (int i = 0; i < info.skipFrames; i++)
-                if (fread(buf[0], framesize, 1, ifs) != 1)
-                    break;
+                ifs->read(buf[0], framesize);
+#else
+        for (int i = 0; i < info.skipFrames; i++)
+            ifs->ignore(framesize);
+#endif
     }
 }
+
 YUVInput::~YUVInput()
 {
-    if (ifs && ifs != stdin)
-        fclose(ifs);
+    if (ifs && ifs != &cin)
+        delete ifs;
     for (int i = 0; i < QUEUE_SIZE; i++)
         X265_FREE(buf[i]);
 }
@@ -156,10 +179,12 @@
     threadActive = false;
     writeCount.poke();
 }
+
 bool YUVInput::populateFrameQueue()
 {
-    if (!ifs || ferror(ifs))
+    if (!ifs || ifs->fail())
         return false;
+
     /* wait for room in the ring buffer */
     int written = writeCount.get();
     int read = readCount.get();
@@ -170,8 +195,10 @@
             // release() has been called
             return false;
     }
+
     ProfileScopeEvent(frameRead);
-    if (fread(buf[written % QUEUE_SIZE], framesize, 1, ifs) == 1)
+    ifs->read(buf[written % QUEUE_SIZE], framesize);
+    if (ifs->good())
     {
         writeCount.incr();
         return true;

x265_2.7.tar.gz/source/input/yuv.h -> x265_2.6.tar.gz/source/input/yuv.h Changed

x265_2.7.tar.gz/source/output/raw.cpp -> x265_2.6.tar.gz/source/output/raw.cpp Changed

x265_2.7.tar.gz/source/test/CMakeLists.txt -> x265_2.6.tar.gz/source/test/CMakeLists.txt Changed

@@ -7,37 +7,37 @@
 
 # add X86 assembly files
 if(X86)
-enable_language(ASM_NASM)
+enable_language(ASM_YASM)
 
 if(MSVC_IDE)
-    set(NASM_SRC checkasm-a.obj)
+    set(YASM_SRC checkasm-a.obj)
     add_custom_command(
         OUTPUT checkasm-a.obj
-        COMMAND ${NASM_EXECUTABLE}
-        ARGS ${NASM_FLAGS} ${CMAKE_CURRENT_SOURCE_DIR}/checkasm-a.asm -o checkasm-a.obj
+        COMMAND ${YASM_EXECUTABLE}
+        ARGS ${YASM_FLAGS} ${CMAKE_CURRENT_SOURCE_DIR}/checkasm-a.asm -o checkasm-a.obj
         DEPENDS checkasm-a.asm)
 else()
-    set(NASM_SRC checkasm-a.asm)
+    set(YASM_SRC checkasm-a.asm)
 endif()
 endif(X86)
 
 # add ARM assembly files
 if(ARM OR CROSS_COMPILE_ARM)
     enable_language(ASM)
-    set(NASM_SRC checkasm-arm.S)
+    set(YASM_SRC checkasm-arm.S)
     add_custom_command(
         OUTPUT checkasm-arm.obj
         COMMAND ${CMAKE_CXX_COMPILER}
-        ARGS ${NASM_FLAGS} ${CMAKE_CURRENT_SOURCE_DIR}/checkasm-arm.S -o checkasm-arm.obj
+        ARGS ${YASM_FLAGS} ${CMAKE_CURRENT_SOURCE_DIR}/checkasm-arm.S -o checkasm-arm.obj
         DEPENDS checkasm-arm.S)
 endif(ARM OR CROSS_COMPILE_ARM)
 
 # add PowerPC assembly files
 if(POWER)
-    set(NASM_SRC)
+    set(YASM_SRC)
 endif(POWER)
 
-add_executable(TestBench ${NASM_SRC}
+add_executable(TestBench ${YASM_SRC}
     testbench.cpp testharness.h
     pixelharness.cpp pixelharness.h
     mbdstharness.cpp mbdstharness.h

x265_2.7.tar.gz/source/test/checkasm-a.asm -> x265_2.6.tar.gz/source/test/checkasm-a.asm Changed

@@ -26,7 +26,7 @@
 ;* For more information, contact us at license @ x265.com.
 ;*****************************************************************************
 
-%include "x86inc.asm"
+%include "../common/x86/x86inc.asm"
 
 SECTION_RODATA
 
@@ -35,24 +35,24 @@
 %if ARCH_X86_64
 ; just random numbers to reduce the chance of incidental match
 ALIGN 16
-x6:  dq 0x1a1b2550a612b48c,0x79445c159ce79064
-x7:  dq 0x2eed899d5a28ddcd,0x86b2536fcd8cf636
-x8:  dq 0xb0856806085e7943,0x3f2bf84fc0fcca4e
-x9:  dq 0xacbd382dcf5b8de2,0xd229e1f5b281303f
-x10: dq 0x71aeaff20b095fd9,0xab63e2e11fa38ed9
-x11: dq 0x89b0c0765892729a,0x77d410d5c42c882d
-x12: dq 0xc45ea11a955d8dd5,0x24b3c1d2a024048b
-x13: dq 0x2e8ec680de14b47c,0xdd7b8919edd42786
-x14: dq 0x135ce6888fa02cbf,0x11e53e2b2ac655ef
-x15: dq 0x011ff554472a7a10,0x6de8f4c914c334d5
-n7:  dq 0x21f86d66c8ca00ce
-n8:  dq 0x75b6ba21077c48ad
-n9:  dq 0xed56bb2dcb3c7736
-n10: dq 0x8bda43d3fd1a7e06
-n11: dq 0xb64a9c9e5d318408
-n12: dq 0xdf9a54b303f1d3a3
-n13: dq 0x4a75479abd64e097
-n14: dq 0x249214109d5d1c88
+x6:  ddq 0x79445c159ce790641a1b2550a612b48c
+x7:  ddq 0x86b2536fcd8cf6362eed899d5a28ddcd
+x8:  ddq 0x3f2bf84fc0fcca4eb0856806085e7943
+x9:  ddq 0xd229e1f5b281303facbd382dcf5b8de2
+x10: ddq 0xab63e2e11fa38ed971aeaff20b095fd9
+x11: ddq 0x77d410d5c42c882d89b0c0765892729a
+x12: ddq 0x24b3c1d2a024048bc45ea11a955d8dd5
+x13: ddq 0xdd7b8919edd427862e8ec680de14b47c
+x14: ddq 0x11e53e2b2ac655ef135ce6888fa02cbf
+x15: ddq 0x6de8f4c914c334d5011ff554472a7a10
+n7:   dq 0x21f86d66c8ca00ce
+n8:   dq 0x75b6ba21077c48ad
+n9:   dq 0xed56bb2dcb3c7736
+n10:  dq 0x8bda43d3fd1a7e06
+n11:  dq 0xb64a9c9e5d318408
+n12:  dq 0xdf9a54b303f1d3a3
+n13:  dq 0x4a75479abd64e097
+n14:  dq 0x249214109d5d1c88
 %endif
 
 SECTION .text
@@ -70,14 +70,14 @@
 ;-----------------------------------------------------------------------------
 cglobal checkasm_stack_clobber, 1,2
     ; Clobber the stack with junk below the stack pointer
-    %define argsize (max_args+6)*8
-    SUB  rsp, argsize
-    mov   r1, argsize-8
+    %define size (max_args+6)*8
+    SUB  rsp, size
+    mov   r1, size-8
 .loop:
     mov [rsp+r1], r0
     sub   r1, 8
     jge .loop
-    ADD  rsp, argsize
+    ADD  rsp, size
     RET
 
 %if WIN64
@@ -156,11 +156,7 @@
     mov  r9, rax
     mov r10, rdx
     lea  r0, [error_message]
-%if FORMAT_ELF
-    call puts wrt ..plt
-%else
     call puts
-%endif
     mov  r1, [rsp+max_args*8]
     mov  dword [r1], 0
     mov  rdx, r10

x265_2.7.tar.gz/source/test/regression-tests.txt -> x265_2.6.tar.gz/source/test/regression-tests.txt Changed

@@ -18,17 +18,17 @@
 BasketballDrive_1920x1080_50.y4m,--preset faster --aq-strength 2 --merange 190 --slices 3
 BasketballDrive_1920x1080_50.y4m,--preset medium --ctu 16 --max-tu-size 8 --subme 7 --qg-size 16 --cu-lossless --tu-inter-depth 3 --limit-tu 1
 BasketballDrive_1920x1080_50.y4m,--preset medium --keyint -1 --nr-inter 100 -F4 --no-sao
-BasketballDrive_1920x1080_50.y4m,--preset medium --no-cutree --analysis-save x265_analysis.dat --analysis-reuse-level 2 --bitrate 7000 --limit-modes::--preset medium --no-cutree --analysis-load x265_analysis.dat --analysis-reuse-level 2 --bitrate 7000 --limit-modes
+BasketballDrive_1920x1080_50.y4m,--preset medium --no-cutree --analysis-reuse-mode=save --analysis-reuse-level 2 --bitrate 7000 --limit-modes::--preset medium --no-cutree --analysis-reuse-mode=load --analysis-reuse-level 2 --bitrate 7000 --limit-modes
 BasketballDrive_1920x1080_50.y4m,--preset slow --nr-intra 100 -F4 --aq-strength 3 --qg-size 16 --limit-refs 1
 BasketballDrive_1920x1080_50.y4m,--preset slower --lossless --chromaloc 3 --subme 0 --limit-tu 4
-BasketballDrive_1920x1080_50.y4m,--preset slower --no-cutree --analysis-save x265_analysis.dat --analysis-reuse-level 10 --bitrate 7000 --limit-tu 0::--preset slower --no-cutree --analysis-load x265_analysis.dat --analysis-reuse-level 10 --bitrate 7000 --limit-tu 0
+BasketballDrive_1920x1080_50.y4m,--preset slower --no-cutree --analysis-reuse-mode=save --analysis-reuse-level 10 --bitrate 7000 --limit-tu 0::--preset slower --no-cutree --analysis-reuse-mode=load --analysis-reuse-level 10 --bitrate 7000 --limit-tu 0
 BasketballDrive_1920x1080_50.y4m,--preset veryslow --crf 4 --cu-lossless --pmode --limit-refs 1 --aq-mode 3 --limit-tu 3
-BasketballDrive_1920x1080_50.y4m,--preset veryslow --no-cutree --analysis-save x265_analysis.dat --bitrate 7000 --tskip-fast --limit-tu 2::--preset veryslow --no-cutree --analysis-load x265_analysis.dat --bitrate 7000  --tskip-fast --limit-tu 2
+BasketballDrive_1920x1080_50.y4m,--preset veryslow --no-cutree --analysis-reuse-mode=save --bitrate 7000 --tskip-fast --limit-tu 4::--preset veryslow --no-cutree --analysis-reuse-mode=load --bitrate 7000  --tskip-fast --limit-tu 4
 BasketballDrive_1920x1080_50.y4m,--preset veryslow --recon-y4m-exec "ffplay -i pipe:0 -autoexit"
 Coastguard-4k.y4m,--preset ultrafast --recon-y4m-exec "ffplay -i pipe:0 -autoexit"
 Coastguard-4k.y4m,--preset superfast --tune grain --overscan=crop
 Coastguard-4k.y4m,--preset superfast --tune grain --pme --aq-strength 2 --merange 190
-Coastguard-4k.y4m,--preset veryfast --no-cutree --analysis-save x265_analysis.dat --analysis-reuse-level 1 --bitrate 15000::--preset veryfast --no-cutree --analysis-load x265_analysis.dat --analysis-reuse-level 1 --bitrate 15000
+Coastguard-4k.y4m,--preset veryfast --no-cutree --analysis-reuse-mode=save --analysis-reuse-level 1 --bitrate 15000::--preset veryfast --no-cutree --analysis-reuse-mode=load --analysis-reuse-level 1 --bitrate 15000
 Coastguard-4k.y4m,--preset medium --rdoq-level 1 --tune ssim --no-signhide --me umh --slices 2
 Coastguard-4k.y4m,--preset slow --tune psnr --cbqpoffs -1 --crqpoffs 1 --limit-refs 1
 CrowdRun_1920x1080_50_10bit_422.yuv,--preset ultrafast --weightp --tune zerolatency --qg-size 16
@@ -52,7 +52,7 @@
 DucksAndLegs_1920x1080_60_10bit_444.yuv,--preset veryfast --weightp --nr-intra 1000 -F4
 DucksAndLegs_1920x1080_60_10bit_444.yuv,--preset medium --nr-inter 500 -F4 --no-psy-rdoq
 DucksAndLegs_1920x1080_60_10bit_444.yuv,--preset slower --no-weightp --rdoq-level 0 --limit-refs 3 --tu-inter-depth 4 --limit-tu 3
-DucksAndLegs_1920x1080_60_10bit_422.yuv,--preset fast --no-cutree --analysis-save x265_analysis.dat --bitrate 3000 --early-skip --tu-inter-depth 3 --limit-tu 1::--preset fast --no-cutree --analysis-load x265_analysis.dat --bitrate 3000 --early-skip --tu-inter-depth 3 --limit-tu 1
+DucksAndLegs_1920x1080_60_10bit_422.yuv,--preset fast --no-cutree --analysis-reuse-mode=save --bitrate 3000 --early-skip --tu-inter-depth 3 --limit-tu 1::--preset fast --no-cutree --analysis-reuse-mode=load --bitrate 3000 --early-skip --tu-inter-depth 3 --limit-tu 1
 FourPeople_1280x720_60.y4m,--preset superfast --no-wpp --lookahead-slices 2
 FourPeople_1280x720_60.y4m,--preset veryfast --aq-mode 2 --aq-strength 1.5 --qg-size 8
 FourPeople_1280x720_60.y4m,--preset medium --qp 38 --no-psy-rd
@@ -69,8 +69,8 @@
 KristenAndSara_1280x720_60.y4m,--preset slower --pmode --max-tu-size 8 --limit-refs 0 --limit-modes --limit-tu 1
 NebutaFestival_2560x1600_60_10bit_crop.yuv,--preset superfast --tune psnr
 NebutaFestival_2560x1600_60_10bit_crop.yuv,--preset medium --tune grain --limit-refs 2
-NebutaFestival_2560x1600_60_10bit_crop.yuv,--preset slow --no-cutree --analysis-save x265_analysis.dat --rd 5 --analysis-reuse-level 10 --bitrate 9000::--preset slow --no-cutree --analysis-load x265_analysis.dat --rd 5 --analysis-reuse-level 10 --bitrate 9000
-News-4k.y4m,--preset ultrafast --no-cutree --analysis-save x265_analysis.dat --analysis-reuse-level 2 --bitrate 15000::--preset ultrafast --no-cutree --analysis-load x265_analysis.dat --analysis-reuse-level 2 --bitrate 15000
+NebutaFestival_2560x1600_60_10bit_crop.yuv,--preset slow --no-cutree --analysis-reuse-mode=save --rd 5 --analysis-reuse-level 10 --bitrate 9000::--preset slow --no-cutree --analysis-reuse-mode=load --rd 5 --analysis-reuse-level 10 --bitrate 9000
+News-4k.y4m,--preset ultrafast --no-cutree --analysis-reuse-mode=save --analysis-reuse-level 2 --bitrate 15000::--preset ultrafast --no-cutree --analysis-reuse-mode=load --analysis-reuse-level 2 --bitrate 15000
 News-4k.y4m,--preset superfast --lookahead-slices 6 --aq-mode 0
 News-4k.y4m,--preset superfast --slices 4 --aq-mode 0 
 News-4k.y4m,--preset medium --tune ssim --no-sao --qg-size 16
@@ -125,7 +125,7 @@
 old_town_cross_444_720p50.y4m,--preset superfast --weightp --min-cu 16 --limit-modes
 old_town_cross_444_720p50.y4m,--preset veryfast --qp 1 --tune ssim
 old_town_cross_444_720p50.y4m,--preset faster --rd 1 --tune zero-latency
-old_town_cross_444_720p50.y4m,--preset fast --no-cutree --analysis-save pass1_analysis.dat --analysis-reuse-level 1 --bitrate 3000 --early-skip::--preset fast --no-cutree --analysis-load pass1_analysis.dat --analysis-save pass2_analysis.dat --analysis-reuse-level 1 --bitrate 3000 --early-skip::--preset fast --no-cutree --analysis-load pass2_analysis.dat --analysis-reuse-level 1 --bitrate 3000 --early-skip
+old_town_cross_444_720p50.y4m,--preset fast --no-cutree --analysis-reuse-mode=save --analysis-reuse-level 1 --bitrate 3000 --early-skip::--preset fast --no-cutree --analysis-reuse-mode=load --analysis-reuse-level 1 --bitrate 3000 --early-skip
 old_town_cross_444_720p50.y4m,--preset medium --keyint -1 --no-weightp --ref 6
 old_town_cross_444_720p50.y4m,--preset slow --rdoq-level 1 --early-skip --ref 7 --no-b-pyramid
 old_town_cross_444_720p50.y4m,--preset slower --crf 4 --cu-lossless
@@ -150,8 +150,6 @@
 Kimono1_1920x1080_24_400.yuv,--preset medium --rdoq-level 0 --limit-refs 3 --slices 2
 Kimono1_1920x1080_24_400.yuv,--preset veryslow --crf 4 --cu-lossless --slices 2 --limit-refs 3 --limit-modes
 Kimono1_1920x1080_24_400.yuv,--preset placebo --ctu 32 --max-tu-size 8 --limit-tu 2
-big_buck_bunny_360p24.y4m, --keyint 60 --min-keyint 40 --gop-lookahead 14
-BasketballDrive_1920x1080_50.y4m, --preset medium --no-open-gop --keyint 50 --min-keyint 50 --radl 2
 
 # Main12 intraCost overflow bug test
 720p50_parkrun_ter.y4m,--preset medium

x265_2.7.tar.gz/source/x265.cpp -> x265_2.6.tar.gz/source/x265.cpp Changed

@@ -301,15 +301,9 @@
                 if (!this->qpfile)
                     x265_log_file(param, X265_LOG_ERROR, "%s qpfile not found or error in opening qp file\n", optarg);
             }
-            OPT("fullhelp")
-            {
-                param->logLevel = X265_LOG_FULL;
-                printVersion(param, api);
-                showHelp(param);
-                break;
-            }
             else
                 bError |= !!api->param_parse(param, long_options[long_options_index].name, optarg);
+
             if (bError)
             {
                 const char *name = long_options_index > 0 ? long_options[long_options_index].name : argv[optind - 2];
@@ -585,9 +579,9 @@
 
     x265_picture pic_orig, pic_out;
     x265_picture *pic_in = &pic_orig;
-    /* Allocate recon picture if analysis save/load is enabled */
+    /* Allocate recon picture if analysisReuseMode is enabled */
     std::priority_queue<int64_t>* pts_queue = cliopt.output->needPTS() ? new std::priority_queue<int64_t>() : NULL;
-    x265_picture *pic_recon = (cliopt.recon || param->analysisSave || param->analysisLoad || pts_queue || reconPlay || param->csvLogLevel) ? &pic_out : NULL;
+    x265_picture *pic_recon = (cliopt.recon || !!param->analysisReuseMode || pts_queue || reconPlay || param->csvLogLevel) ? &pic_out : NULL;
     uint32_t inFrameCount = 0;
     uint32_t outFrameCount = 0;
     x265_nal *p_nal;

x265_2.7.tar.gz/source/x265.h -> x265_2.6.tar.gz/source/x265.h Changed

@@ -327,15 +327,15 @@
      * to allow the encoder to determine base QP */
     int     forceqp;
 
-    /* If param.analysisLoad and param.analysisSave are disabled, this field is
-     * ignored on input and output. Else the user must call x265_alloc_analysis_data()
-     * to allocate analysis buffers for every picture passed to the encoder.
+    /* If param.analysisReuseMode is X265_ANALYSIS_OFF this field is ignored on input
+     * and output. Else the user must call x265_alloc_analysis_data() to
+     * allocate analysis buffers for every picture passed to the encoder.
      *
-     * On input when param.analysisLoad is enabled and analysisData
+     * On input when param.analysisReuseMode is X265_ANALYSIS_LOAD and analysisData
      * member pointers are valid, the encoder will use the data stored here to
      * reduce encoder work.
      *
-     * On output when param.analysisSave is enabled and analysisData
+     * On output when param.analysisReuseMode is X265_ANALYSIS_SAVE and analysisData
      * member pointers are valid, the encoder will write output analysis into
      * this data structure */
     x265_analysis_data analysisData;
@@ -481,7 +481,9 @@
 #define X265_CSP_BGRA           7  /* packed bgr 32bits   */
 #define X265_CSP_RGB            8  /* packed rgb 24bits   */
 #define X265_CSP_MAX            9  /* end of list */
+
 #define X265_EXTENDED_SAR       255 /* aspect ratio explicitly specified as width:height */
+
 /* Analysis options */
 #define X265_ANALYSIS_OFF  0
 #define X265_ANALYSIS_SAVE 1
@@ -1127,13 +1129,13 @@
      * Default disabled */
     int       bEnableRdRefine;
 
-    /* If save, write per-frame analysis information into analysis buffers.
-     * If load, read analysis information into analysis buffer and use this
-     * analysis information to reduce the amount of work the encoder must perform.
-     * Default disabled. Now deprecated*/
+    /* If X265_ANALYSIS_SAVE, write per-frame analysis information into analysis
+     * buffers.  if X265_ANALYSIS_LOAD, read analysis information into analysis
+     * buffer and use this analysis information to reduce the amount of work
+     * the encoder must perform. Default X265_ANALYSIS_OFF */
     int       analysisReuseMode;
 
-    /* Filename for multi-pass-opt-analysis/distortion. Default name is "x265_analysis.dat" */
+    /* Filename for analysisReuseMode save/load. Default name is "x265_analysis.dat" */
     const char* analysisReuseFileName;
 
     /*== Rate Control ==*/
@@ -1271,7 +1273,6 @@
 
         /* internally enable if tune grain is set */
         int      bEnableConstVbv;
-
     } rc;
 
     /*== Video Usability Information ==*/
@@ -1454,7 +1455,7 @@
     int       bHDROpt;
 
     /* A value between 1 and 10 (both inclusive) determines the level of
-    * information stored/reused in analysis save/load. Higher the refine
+    * information stored/reused in save/load analysis-reuse-mode. Higher the refine
     * level higher the information stored/reused. Default is 5 */
     int       analysisReuseLevel;
 
@@ -1531,23 +1532,9 @@
 
     /* Reuse MV information obtained through API */
     int       bMVType;
+
     /* Allow the encoder to have a copy of the planes of x265_picture in Frame */
     int       bCopyPicToFrame;
-
-    /*Number of frames for GOP boundary decision lookahead.If a scenecut frame is found
-    * within this from the gop boundary set by keyint, the GOP will be extented until such a point,
-    * otherwise the GOP will be terminated as set by keyint*/
-    int       gopLookahead;
-
-    /*Write per-frame analysis information into analysis buffers. Default disabled. */
-    const char* analysisSave;
-
-    /* Read analysis information into analysis buffer and use this analysis information
-     * to reduce the amount of work the encoder must perform. Default disabled. */
-    const char* analysisLoad;
-
-    /*Number of RADL pictures allowed in front of IDR*/
-    int radl;
 } x265_param;
 
 /* x265_param_alloc:
@@ -1756,7 +1743,7 @@
 /* x265_get_ref_frame_list:
  *     returns negative on error, 0 when access unit were output.
  *     This API must be called after(poc >= lookaheadDepth + bframes + 2) condition check */
-int x265_get_ref_frame_list(x265_encoder *encoder, x265_picyuv**, x265_picyuv**, int, int, int*, int*);
+int x265_get_ref_frame_list(x265_encoder *encoder, x265_picyuv**, x265_picyuv**, int, int);
 
 /* x265_set_analysis_data:
  *     set the analysis data. The incoming analysis_data structure is assumed to be AVC-sized blocks.
@@ -1779,10 +1766,9 @@
 void x265_csvlog_frame(const x265_param *, const x265_picture *);
 
 /* Log final encode statistics to the CSV file handle. 'argc' and 'argv' are
- * intended to be command line arguments passed to the encoder. padx and pady are
- * padding offsets for conformance and can be given from sps settings. Encode
+ * intended to be command line arguments passed to the encoder. Encode
  * statistics should be queried from the encoder just prior to closing it. */
-void x265_csvlog_encode(const x265_param*, const x265_stats *, int padx, int pady, int argc, char** argv);
+void x265_csvlog_encode(x265_encoder *encoder, const x265_stats *, int argc, char** argv);
 
 /* In-place downshift from a bit-depth greater than 8 to a bit-depth of 8, using
  * the residual bits to dither each row. */
@@ -1834,10 +1820,10 @@
     int           (*encoder_intra_refresh)(x265_encoder*);
     int           (*encoder_ctu_info)(x265_encoder*, int, x265_ctu_info_t**);
     int           (*get_slicetype_poc_and_scenecut)(x265_encoder*, int*, int*, int*);
-    int           (*get_ref_frame_list)(x265_encoder*, x265_picyuv**, x265_picyuv**, int, int, int*, int*);
+    int           (*get_ref_frame_list)(x265_encoder*, x265_picyuv**, x265_picyuv**, int, int);
     FILE*         (*csvlog_open)(const x265_param*);
     void          (*csvlog_frame)(const x265_param*, const x265_picture*);
-    void          (*csvlog_encode)(const x265_param*, const x265_stats *, int, int, int, char**);
+    void          (*csvlog_encode)(x265_encoder*, const x265_stats*, int, char**);
     void          (*dither_image)(x265_picture*, int, int, int16_t*, int);
     int           (*set_analysis_data)(x265_encoder *encoder, x265_analysis_data *analysis_data, int poc, uint32_t cuBytes);
     /* add new pointers to the end, or increment X265_MAJOR_VERSION */

x265_2.7.tar.gz/source/x265cli.h -> x265_2.6.tar.gz/source/x265cli.h Changed

@@ -38,7 +38,6 @@
 static const struct option long_options[] =
 {
     { "help",                 no_argument, NULL, 'h' },
-    { "fullhelp",             no_argument, NULL, 0 },
     { "version",              no_argument, NULL, 'V' },
     { "asm",            required_argument, NULL, 0 },
     { "no-asm",               no_argument, NULL, 0 },
@@ -120,11 +119,9 @@
     { "open-gop",             no_argument, NULL, 0 },
     { "keyint",         required_argument, NULL, 'I' },
     { "min-keyint",     required_argument, NULL, 'i' },
-    { "gop-lookahead",  required_argument, NULL, 0 },
     { "scenecut",       required_argument, NULL, 0 },
     { "no-scenecut",          no_argument, NULL, 0 },
     { "scenecut-bias",  required_argument, NULL, 0 },
-    { "radl",           required_argument, NULL, 0 },
     { "ctu-info",       required_argument, NULL, 0 },
     { "intra-refresh",        no_argument, NULL, 0 },
     { "rc-lookahead",   required_argument, NULL, 0 },
@@ -255,11 +252,9 @@
     { "no-slow-firstpass",    no_argument, NULL, 0 },
     { "multi-pass-opt-rps",   no_argument, NULL, 0 },
     { "no-multi-pass-opt-rps", no_argument, NULL, 0 },
-    { "analysis-reuse-mode", required_argument, NULL, 0 }, /* DEPRECATED */
-    { "analysis-reuse-file", required_argument, NULL, 0 },
+    { "analysis-reuse-mode",  required_argument, NULL, 0 },
+    { "analysis-reuse-file",  required_argument, NULL, 0 },
     { "analysis-reuse-level", required_argument, NULL, 0 },
-    { "analysis-save",  required_argument, NULL, 0 },
-    { "analysis-load",  required_argument, NULL, 0 },
     { "scale-factor",   required_argument, NULL, 0 },
     { "refine-intra",   required_argument, NULL, 0 },
     { "refine-inter",   required_argument, NULL, 0 },
@@ -319,7 +314,6 @@
     H0("    outfile is raw HEVC bitstream\n");
     H0("\nExecutable Options:\n");
     H0("-h/--help                        Show this help text and exit\n");
-    H0("   --fullhelp                    Show all options and exit\n");
     H0("-V/--version                     Show version info and exit\n");
     H0("\nOutput Options:\n");
     H0("-o/--output <filename>           Bitstream output file name\n");
@@ -424,11 +418,9 @@
     H0("   --[no-]open-gop               Enable open-GOP, allows I slices to be non-IDR. Default %s\n", OPT(param->bOpenGOP));
     H0("-I/--keyint <integer>            Max IDR period in frames. -1 for infinite-gop. Default %d\n", param->keyframeMax);
     H0("-i/--min-keyint <integer>        Scenecuts closer together than this are coded as I, not IDR. Default: auto\n");
-    H0("   --gop-lookahead <integer>     Extends gop boundary if a scenecut is found within this from keyint boundary. Default 0\n");
     H0("   --no-scenecut                 Disable adaptive I-frame decision\n");
     H0("   --scenecut <integer>          How aggressively to insert extra I-frames. Default %d\n", param->scenecutThreshold);
     H1("   --scenecut-bias <0..100.0>    Bias for scenecut detection. Default %.2f\n", param->scenecutBias);
-    H0("   --radl <integer>              Number of RADL pictures allowed in front of IDR. Default %d\n", param->radl);
     H0("   --intra-refresh               Use Periodic Intra Refresh instead of IDR frames\n");
     H0("   --rc-lookahead <integer>      Number of frames for frame-type lookahead (determines encoder latency) Default %d\n", param->lookaheadDepth);
     H1("   --lookahead-slices <0..16>    Number of slices to use per lookahead cost estimate. Default %d\n", param->lookaheadSlices);
@@ -469,19 +461,18 @@
     H0("   --[no-]analyze-src-pics       Motion estimation uses source frame planes. Default disable\n");
     H0("   --[no-]slow-firstpass         Enable a slow first pass in a multipass rate control mode. Default %s\n", OPT(param->rc.bEnableSlowFirstPass));
     H0("   --[no-]strict-cbr             Enable stricter conditions and tolerance for bitrate deviations in CBR mode. Default %s\n", OPT(param->rc.bStrictCbr));
-    H0("   --analysis-save <filename>    Dump analysis info into the specified file. Default Disabled\n");
-    H0("   --analysis-load <filename>    Load analysis buffers from the file specified. Default Disabled\n");
+    H0("   --analysis-reuse-mode <string|int>  save - Dump analysis info into file, load - Load analysis buffers from the file. Default %d\n", param->analysisReuseMode);
     H0("   --analysis-reuse-file <filename>    Specify file name used for either dumping or reading analysis data. Deault x265_analysis.dat\n");
     H0("   --analysis-reuse-level <1..10>      Level of analysis reuse indicates amount of info stored/reused in save/load mode, 1:least..10:most. Default %d\n", param->analysisReuseLevel);
     H0("   --refine-mv-type <string>     Reuse MV information received through API call. Supported option is avc. Default disabled - %d\n", param->bMVType);
     H0("   --scale-factor <int>          Specify factor by which input video is scaled down for analysis save mode. Default %d\n", param->scaleFactor);
-    H0("   --refine-intra <0..3>         Enable intra refinement for encode that uses analysis-load.\n"
+    H0("   --refine-intra <0..3>         Enable intra refinement for encode that uses analysis-reuse-mode=load.\n"
         "                                    - 0 : Forces both mode and depth from the save encode.\n"
         "                                    - 1 : Functionality of (0) + evaluate all intra modes at min-cu-size's depth when current depth is one smaller than min-cu-size's depth.\n"
         "                                    - 2 : Functionality of (1) + irrespective of size evaluate all angular modes when the save encode decides the best mode as angular.\n"
         "                                    - 3 : Functionality of (1) + irrespective of size evaluate all intra modes.\n"
         "                                Default:%d\n", param->intraRefine);
-    H0("   --refine-inter <0..3>         Enable inter refinement for encode that uses analysis-load.\n"
+    H0("   --refine-inter <0..3>         Enable inter refinement for encode that uses analysis-reuse-mode=load.\n"
         "                                    - 0 : Forces both mode and depth from the save encode.\n"
         "                                    - 1 : Functionality of (0) + evaluate all inter modes at min-cu-size's depth when current depth is one smaller than\n"
         "                                          min-cu-size's depth. When save encode decides the current block as skip(for all sizes) evaluate skip/merge.\n"
@@ -572,8 +563,9 @@
 #undef OPT
 #undef H0
 #undef H1
+
     if (level < X265_LOG_DEBUG)
-        printf("\nUse --fullhelp for a full listing (or --log-level full --help)\n");
+        printf("\nUse --log-level full --help for a full listing\n");
     printf("\n\nComplete documentation may be found at http://x265.readthedocs.org/en/default/cli.html\n");
     exit(1);
 }

x265_2.7.tar.gz/source/cmake/CMakeASM_NASMInformation.cmake Deleted

@@ -1,68 +0,0 @@
-set(ASM_DIALECT "_NASM")
-set(CMAKE_ASM${ASM_DIALECT}_SOURCE_FILE_EXTENSIONS asm)
-
-if(X64)
-    list(APPEND ASM_FLAGS -DARCH_X86_64=1 -I ${CMAKE_CURRENT_SOURCE_DIR}/../common/x86/)
-    if(ENABLE_PIC)
-        list(APPEND ASM_FLAGS -DPIC)
-    endif()
-    if(APPLE)
-        set(ARGS -f macho64 -DPREFIX)
-    elseif(UNIX AND NOT CYGWIN)
-        set(ARGS -f elf64)
-    else()
-        set(ARGS -f win64)
-    endif()
-else()
-    list(APPEND ASM_FLAGS -DARCH_X86_64=0 -I ${CMAKE_CURRENT_SOURCE_DIR}/../common/x86/)
-    if(APPLE)
-        set(ARGS -f macho32 -DPREFIX)
-    elseif(UNIX AND NOT CYGWIN)
-        set(ARGS -f elf32)
-    else()
-        set(ARGS -f win32 -DPREFIX)
-    endif()
-endif()
-
-if(GCC)
-    list(APPEND ASM_FLAGS -DHAVE_ALIGNED_STACK=1)
-else()
-    list(APPEND ASM_FLAGS -DHAVE_ALIGNED_STACK=0)
-endif()
-
-if(HIGH_BIT_DEPTH)
-    if(MAIN12)
-        list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=1 -DBIT_DEPTH=12 -DX265_NS=${X265_NS})
-    else()
-        list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=1 -DBIT_DEPTH=10 -DX265_NS=${X265_NS})
-    endif()
-else()
-    list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=0 -DBIT_DEPTH=8 -DX265_NS=${X265_NS})
-endif()
-
-list(APPEND ASM_FLAGS "${CMAKE_ASM_NASM_FLAGS}")
-
-if(CMAKE_BUILD_TYPE MATCHES Release)
-    list(APPEND ASM_FLAGS "${CMAKE_ASM_NASM_FLAGS_RELEASE}")
-elseif(CMAKE_BUILD_TYPE MATCHES Debug)
-    list(APPEND ASM_FLAGS "${CMAKE_ASM_NASM_FLAGS_DEBUG}")
-elseif(CMAKE_BUILD_TYPE MATCHES MinSizeRel)
-    list(APPEND ASM_FLAGS "${CMAKE_ASM_NASM_FLAGS_MINSIZEREL}")
-elseif(CMAKE_BUILD_TYPE MATCHES RelWithDebInfo)
-    list(APPEND ASM_FLAGS "${CMAKE_ASM_NASM_FLAGS_RELWITHDEBINFO}")
-endif()
-
-set(NASM_FLAGS ${ARGS} ${ASM_FLAGS} PARENT_SCOPE)
-string(REPLACE ";" " " CMAKE_ASM_NASM_COMPILER_ARG1 "${ARGS}")
-
-# This section exists to override the one in CMakeASMInformation.cmake
-# (the default Information file). This removes the <FLAGS>
-# thing so that your C compiler flags that have been set via
-# set_target_properties don't get passed to nasm and confuse it.
-if(NOT CMAKE_ASM${ASM_DIALECT}_COMPILE_OBJECT)
-    string(REPLACE ";" " " STR_ASM_FLAGS "${ASM_FLAGS}")
-    set(CMAKE_ASM${ASM_DIALECT}_COMPILE_OBJECT "<CMAKE_ASM${ASM_DIALECT}_COMPILER> ${STR_ASM_FLAGS} -o <OBJECT> <SOURCE>")
-endif()
-
-include(CMakeASMInformation)
-set(ASM_DIALECT)

x265_2.7.tar.gz/source/cmake/CMakeDetermineASM_NASMCompiler.cmake Deleted

x265_2.7.tar.gz/source/cmake/CMakeTestASM_NASMCompiler.cmake Deleted

x265_2.7.tar.gz/source/cmake/FindNasm.cmake Deleted

x265_2.7.tar.gz/source/common/x86/h-ipfilter16.asm Deleted

@@ -1,2537 +0,0 @@
-;*****************************************************************************
-;* Copyright (C) 2013-2017 MulticoreWare, Inc
-;*
-;* Authors: Nabajit Deka <nabajit@multicorewareinc.com>
-;*          Murugan Vairavel <murugan@multicorewareinc.com>
-;*          Min Chen <chenm003@163.com>
-;*
-;* This program is free software; you can redistribute it and/or modify
-;* it under the terms of the GNU General Public License as published by
-;* the Free Software Foundation; either version 2 of the License, or
-;* (at your option) any later version.
-;*
-;* This program 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 General Public License for more details.
-;*
-;* You should have received a copy of the GNU General Public License
-;* along with this program; if not, write to the Free Software
-;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
-;*
-;* This program is also available under a commercial proprietary license.
-;* For more information, contact us at license @ x265.com.
-;*****************************************************************************/
-%include "x86inc.asm"
-%include "x86util.asm"
-
-
-%define INTERP_OFFSET_PP        pd_32
-%define INTERP_SHIFT_PP         6
-
-%if BIT_DEPTH == 10
-    %define INTERP_SHIFT_PS         2
-    %define INTERP_OFFSET_PS        pd_n32768
-    %define INTERP_SHIFT_SP         10
-    %define INTERP_OFFSET_SP        h_pd_524800
-%elif BIT_DEPTH == 12
-    %define INTERP_SHIFT_PS         4
-    %define INTERP_OFFSET_PS        pd_n131072
-    %define INTERP_SHIFT_SP         8
-    %define INTERP_OFFSET_SP        pd_524416
-%else
-    %error Unsupport bit depth!
-%endif
-
-SECTION_RODATA 32
-
-h_pd_524800:        times 8 dd 524800
-                                    
-tab_LumaCoeff:    dw   0, 0,  0,  64,  0,   0,  0,  0
-                  dw  -1, 4, -10, 58,  17, -5,  1,  0
-                  dw  -1, 4, -11, 40,  40, -11, 4, -1
-                  dw   0, 1, -5,  17,  58, -10, 4, -1
-                  
-ALIGN 32
-h_tab_LumaCoeffV:   times 4 dw 0, 0
-                  times 4 dw 0, 64
-                  times 4 dw 0, 0
-                  times 4 dw 0, 0
-
-                  times 4 dw -1, 4
-                  times 4 dw -10, 58
-                  times 4 dw 17, -5
-                  times 4 dw 1, 0
-
-                  times 4 dw -1, 4
-                  times 4 dw -11, 40
-                  times 4 dw 40, -11
-                  times 4 dw 4, -1
-
-                  times 4 dw 0, 1
-                  times 4 dw -5, 17
-                  times 4 dw 58, -10
-                  times 4 dw 4, -1
-                  
-const interp8_hps_shuf,     dd 0, 4, 1, 5, 2, 6, 3, 7                 
-
-const interp8_hpp_shuf,     db 0, 1, 2, 3, 4, 5, 6, 7, 2, 3, 4, 5, 6, 7, 8, 9
-                            db 4, 5, 6, 7, 8, 9, 10, 11, 6, 7, 8, 9, 10, 11, 12, 13 
-
-const interp8_hpp_shuf_new, db 0, 1, 2, 3, 2, 3, 4, 5, 4, 5, 6, 7, 6, 7, 8, 9
-                            db 4, 5, 6, 7, 6, 7, 8, 9, 8, 9, 10, 11, 10, 11, 12, 13                         
-                            
-SECTION .text
-cextern pd_8
-cextern pd_32
-cextern pw_pixel_max
-cextern pd_524416
-cextern pd_n32768
-cextern pd_n131072
-cextern pw_2000
-cextern idct8_shuf2
-
-%macro FILTER_LUMA_HOR_4_sse2 1
-    movu        m4,     [r0 + %1]       ; m4 = src[0-7]
-    movu        m5,     [r0 + %1 + 2]   ; m5 = src[1-8]
-    pmaddwd     m4,     m0
-    pmaddwd     m5,     m0
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m4,     m4,     q3120
-    pshufd      m5,     m5,     q3120
-    punpcklqdq  m4,     m5
-
-    movu        m5,     [r0 + %1 + 4]   ; m5 = src[2-9]
-    movu        m3,     [r0 + %1 + 6]   ; m3 = src[3-10]
-    pmaddwd     m5,     m0
-    pmaddwd     m3,     m0
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m2,     m3,     q2301
-    paddd       m3,     m2
-    pshufd      m5,     m5,     q3120
-    pshufd      m3,     m3,     q3120
-    punpcklqdq  m5,     m3
-
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m4,     m4,     q3120
-    pshufd      m5,     m5,     q3120
-    punpcklqdq  m4,     m5
-    paddd       m4,     m1
-%endmacro
-
-%macro FILTER_LUMA_HOR_8_sse2 1
-    movu        m4,     [r0 + %1]       ; m4 = src[0-7]
-    movu        m5,     [r0 + %1 + 2]   ; m5 = src[1-8]
-    pmaddwd     m4,     m0
-    pmaddwd     m5,     m0
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m4,     m4,     q3120
-    pshufd      m5,     m5,     q3120
-    punpcklqdq  m4,     m5
-
-    movu        m5,     [r0 + %1 + 4]   ; m5 = src[2-9]
-    movu        m3,     [r0 + %1 + 6]   ; m3 = src[3-10]
-    pmaddwd     m5,     m0
-    pmaddwd     m3,     m0
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m2,     m3,     q2301
-    paddd       m3,     m2
-    pshufd      m5,     m5,     q3120
-    pshufd      m3,     m3,     q3120
-    punpcklqdq  m5,     m3
-
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m4,     m4,     q3120
-    pshufd      m5,     m5,     q3120
-    punpcklqdq  m4,     m5
-    paddd       m4,     m1
-
-    movu        m5,     [r0 + %1 + 8]   ; m5 = src[4-11]
-    movu        m6,     [r0 + %1 + 10]  ; m6 = src[5-12]
-    pmaddwd     m5,     m0
-    pmaddwd     m6,     m0
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m2,     m6,     q2301
-    paddd       m6,     m2
-    pshufd      m5,     m5,     q3120
-    pshufd      m6,     m6,     q3120
-    punpcklqdq  m5,     m6
-
-    movu        m6,     [r0 + %1 + 12]  ; m6 = src[6-13]
-    movu        m3,     [r0 + %1 + 14]  ; m3 = src[7-14]
-    pmaddwd     m6,     m0
-    pmaddwd     m3,     m0
-    pshufd      m2,     m6,     q2301
-    paddd       m6,     m2
-    pshufd      m2,     m3,     q2301
-    paddd       m3,     m2
-    pshufd      m6,     m6,     q3120
-    pshufd      m3,     m3,     q3120
-    punpcklqdq  m6,     m3
-
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m2,     m6,     q2301
-    paddd       m6,     m2
-    pshufd      m5,     m5,     q3120
-    pshufd      m6,     m6,     q3120
-    punpcklqdq  m5,     m6
-    paddd       m5,     m1
-%endmacro
-
-;------------------------------------------------------------------------------------------------------------
-; void interp_8tap_horiz_p%3_%1x%2(pixel *src, intptr_t srcStride, pixel *dst, intptr_t dstStride, int coeffIdx)
-;------------------------------------------------------------------------------------------------------------

x265_2.7.tar.gz/source/common/x86/h-ipfilter8.asm Deleted

@@ -1,6736 +0,0 @@
-;*****************************************************************************
-;* Copyright (C) 2013-2017 MulticoreWare, Inc
-;*
-;* Authors: Min Chen <chenm003@163.com>
-;*          Nabajit Deka <nabajit@multicorewareinc.com>
-;*          Praveen Kumar Tiwari <praveen@multicorewareinc.com>
-;*
-;* This program is free software; you can redistribute it and/or modify
-;* it under the terms of the GNU General Public License as published by
-;* the Free Software Foundation; either version 2 of the License, or
-;* (at your option) any later version.
-;*
-;* This program 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 General Public License for more details.
-;*
-;* You should have received a copy of the GNU General Public License
-;* along with this program; if not, write to the Free Software
-;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
-;*
-;* This program is also available under a commercial proprietary license.
-;* For more information, contact us at license @ x265.com.
-;*****************************************************************************/
-
-%include "x86inc.asm"
-%include "x86util.asm"
-
-SECTION_RODATA 32
-
-const h_tabw_LumaCoeff,  dw   0, 0,  0,  64,  0,   0,  0,  0
-                       dw  -1, 4, -10, 58,  17, -5,  1,  0
-                       dw  -1, 4, -11, 40,  40, -11, 4, -1
-                       dw   0, 1, -5,  17,  58, -10, 4, -1
-
-const h_tabw_ChromaCoeff, dw  0, 64,  0,  0
-                        dw -2, 58, 10, -2
-                        dw -4, 54, 16, -2
-                        dw -6, 46, 28, -4
-                        dw -4, 36, 36, -4
-                        dw -4, 28, 46, -6
-                        dw -2, 16, 54, -4
-                        dw -2, 10, 58, -2
-
-const h_tab_ChromaCoeff, db  0, 64,  0,  0
-                       db -2, 58, 10, -2
-                       db -4, 54, 16, -2
-                       db -6, 46, 28, -4
-                       db -4, 36, 36, -4
-                       db -4, 28, 46, -6
-                       db -2, 16, 54, -4
-                       db -2, 10, 58, -2
-
-const h_tab_LumaCoeff,   db   0, 0,  0,  64,  0,   0,  0,  0
-                       db  -1, 4, -10, 58,  17, -5,  1,  0
-                       db  -1, 4, -11, 40,  40, -11, 4, -1
-                       db   0, 1, -5,  17,  58, -10, 4, -1
-
-const h_tab_Tm,    db 0, 1, 2, 3, 1, 2, 3, 4, 2, 3, 4, 5, 3, 4, 5, 6
-                 db 4, 5, 6, 7, 5, 6, 7, 8, 6, 7, 8, 9, 7, 8, 9, 10
-                 db 8, 9,10,11, 9,10,11,12,10,11,12,13,11,12,13, 14
-
-
-const h_tab_Lm,    db 0, 1, 2, 3, 4,  5,  6,  7,  1, 2, 3, 4,  5,  6,  7,  8
-                 db 2, 3, 4, 5, 6,  7,  8,  9,  3, 4, 5, 6,  7,  8,  9,  10
-                 db 4, 5, 6, 7, 8,  9,  10, 11, 5, 6, 7, 8,  9,  10, 11, 12
-                 db 6, 7, 8, 9, 10, 11, 12, 13, 7, 8, 9, 10, 11, 12, 13, 14
-
-const interp4_shuf, times 2 db 0, 1, 8, 9, 4, 5, 12, 13, 2, 3, 10, 11, 6, 7, 14, 15
-
-const h_interp8_hps_shuf,     dd 0, 4, 1, 5, 2, 6, 3, 7
-
-const interp4_hpp_shuf,     times 2 db 0, 1, 2, 3, 1, 2, 3, 4, 8, 9, 10, 11, 9, 10, 11, 12
-
-const interp4_horiz_shuf1,  db 0, 1, 2, 3, 1, 2, 3, 4, 2, 3, 4, 5, 3, 4, 5, 6
-                            db 8, 9, 10, 11, 9, 10, 11, 12, 10, 11, 12, 13, 11, 12, 13, 14
-
-const h_pd_526336, times 8 dd 8192*64+2048
-
-const pb_LumaCoeffVer,  times 16 db 0, 0
-                        times 16 db 0, 64
-                        times 16 db 0, 0
-                        times 16 db 0, 0
-
-                        times 16 db -1, 4
-                        times 16 db -10, 58
-                        times 16 db 17, -5
-                        times 16 db 1, 0
-
-                        times 16 db -1, 4
-                        times 16 db -11, 40
-                        times 16 db 40, -11
-                        times 16 db 4, -1
-
-                        times 16 db 0, 1
-                        times 16 db -5, 17
-                        times 16 db 58, -10
-                        times 16 db 4, -1
-
-const h_pw_LumaCoeffVer,  times 8 dw 0, 0
-                        times 8 dw 0, 64
-                        times 8 dw 0, 0
-                        times 8 dw 0, 0
-
-                        times 8 dw -1, 4
-                        times 8 dw -10, 58
-                        times 8 dw 17, -5
-                        times 8 dw 1, 0
-
-                        times 8 dw -1, 4
-                        times 8 dw -11, 40
-                        times 8 dw 40, -11
-                        times 8 dw 4, -1
-
-                        times 8 dw 0, 1
-                        times 8 dw -5, 17
-                        times 8 dw 58, -10
-                        times 8 dw 4, -1
-
-const pb_8tap_hps_0, times 2 db 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8
-                     times 2 db 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9,10
-                     times 2 db 4, 5, 5, 6, 6, 7, 7, 8, 8, 9, 9,10,10,11,11,12
-                     times 2 db 6, 7, 7, 8, 8, 9, 9,10,10,11,11,12,12,13,13,14
-
-ALIGN 32
-interp4_hps_shuf: times 2 db 0, 1, 2, 3, 1, 2, 3, 4, 8, 9, 10, 11, 9, 10, 11, 12
-
-SECTION .text
-
-cextern pw_1
-cextern pw_32
-cextern pw_2000
-cextern pw_512
-
-%macro PROCESS_LUMA_AVX2_W8_16R 1
-    movu            xm0, [r0]                       ; m0 = row 0
-    movu            xm1, [r0 + r1]                  ; m1 = row 1
-    punpckhwd       xm2, xm0, xm1
-    punpcklwd       xm0, xm1
-    vinserti128     m0, m0, xm2, 1
-    pmaddwd         m0, [r5]
-    movu            xm2, [r0 + r1 * 2]              ; m2 = row 2
-    punpckhwd       xm3, xm1, xm2
-    punpcklwd       xm1, xm2
-    vinserti128     m1, m1, xm3, 1
-    pmaddwd         m1, [r5]
-    movu            xm3, [r0 + r4]                  ; m3 = row 3
-    punpckhwd       xm4, xm2, xm3
-    punpcklwd       xm2, xm3
-    vinserti128     m2, m2, xm4, 1
-    pmaddwd         m4, m2, [r5 + 1 * mmsize]
-    paddd           m0, m4
-    pmaddwd         m2, [r5]
-    lea             r7, [r0 + r1 * 4]
-    movu            xm4, [r7]                       ; m4 = row 4
-    punpckhwd       xm5, xm3, xm4
-    punpcklwd       xm3, xm4
-    vinserti128     m3, m3, xm5, 1
-    pmaddwd         m5, m3, [r5 + 1 * mmsize]
-    paddd           m1, m5
-    pmaddwd         m3, [r5]
-    movu            xm5, [r7 + r1]                  ; m5 = row 5
-    punpckhwd       xm6, xm4, xm5
-    punpcklwd       xm4, xm5
-    vinserti128     m4, m4, xm6, 1
-    pmaddwd         m6, m4, [r5 + 2 * mmsize]
-    paddd           m0, m6
-    pmaddwd         m6, m4, [r5 + 1 * mmsize]
-    paddd           m2, m6
-    pmaddwd         m4, [r5]
-    movu            xm6, [r7 + r1 * 2]              ; m6 = row 6
-    punpckhwd       xm7, xm5, xm6
-    punpcklwd       xm5, xm6
-    vinserti128     m5, m5, xm7, 1
-    pmaddwd         m7, m5, [r5 + 2 * mmsize]
-    paddd           m1, m7
-    pmaddwd         m7, m5, [r5 + 1 * mmsize]
-    paddd           m3, m7
-    pmaddwd         m5, [r5]
-    movu            xm7, [r7 + r4]                  ; m7 = row 7
-    punpckhwd       xm8, xm6, xm7
-    punpcklwd       xm6, xm7
-    vinserti128     m6, m6, xm8, 1
-    pmaddwd         m8, m6, [r5 + 3 * mmsize]
-    paddd           m0, m8
-    pmaddwd         m8, m6, [r5 + 2 * mmsize]
-    paddd           m2, m8
-    pmaddwd         m8, m6, [r5 + 1 * mmsize]
-    paddd           m4, m8
-    pmaddwd         m6, [r5]
-    lea             r7, [r7 + r1 * 4]
-    movu            xm8, [r7]                       ; m8 = row 8
-    punpckhwd       xm9, xm7, xm8
-    punpcklwd       xm7, xm8
-    vinserti128     m7, m7, xm9, 1
-    pmaddwd         m9, m7, [r5 + 3 * mmsize]
-    paddd           m1, m9
-    pmaddwd         m9, m7, [r5 + 2 * mmsize]
-    paddd           m3, m9

x265_2.7.tar.gz/source/common/x86/h4-ipfilter16.asm Deleted

@@ -1,2632 +0,0 @@
-;*****************************************************************************
-;* Copyright (C) 2013-2017 MulticoreWare, Inc
-;*
-;* Authors: Nabajit Deka <nabajit@multicorewareinc.com>
-;*          Murugan Vairavel <murugan@multicorewareinc.com>
-;*          Min Chen <chenm003@163.com>
-;*
-;* This program is free software; you can redistribute it and/or modify
-;* it under the terms of the GNU General Public License as published by
-;* the Free Software Foundation; either version 2 of the License, or
-;* (at your option) any later version.
-;*
-;* This program 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 General Public License for more details.
-;*
-;* You should have received a copy of the GNU General Public License
-;* along with this program; if not, write to the Free Software
-;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
-;*
-;* This program is also available under a commercial proprietary license.
-;* For more information, contact us at license @ x265.com.
-;*****************************************************************************/
-
-%include "x86inc.asm"
-%include "x86util.asm"
-
-
-%define INTERP_OFFSET_PP        pd_32
-%define INTERP_SHIFT_PP         6
-
-%if BIT_DEPTH == 10
-    %define INTERP_SHIFT_PS         2
-    %define INTERP_OFFSET_PS        pd_n32768
-    %define INTERP_SHIFT_SP         10
-    %define INTERP_OFFSET_SP        h4_pd_524800
-%elif BIT_DEPTH == 12
-    %define INTERP_SHIFT_PS         4
-    %define INTERP_OFFSET_PS        pd_n131072
-    %define INTERP_SHIFT_SP         8
-    %define INTERP_OFFSET_SP        pd_524416
-%else
-    %error Unsupport bit depth!
-%endif
-
-
-SECTION_RODATA 32
-
-tab_c_32:         times 8 dd 32
-h4_pd_524800:        times 8 dd 524800
-
-tab_Tm16:         db 0, 1, 2, 3, 4,  5,  6, 7, 2, 3, 4,  5, 6, 7, 8, 9
-
-tab_ChromaCoeff:  dw  0, 64,  0,  0
-                  dw -2, 58, 10, -2
-                  dw -4, 54, 16, -2
-                  dw -6, 46, 28, -4
-                  dw -4, 36, 36, -4
-                  dw -4, 28, 46, -6
-                  dw -2, 16, 54, -4
-                  dw -2, 10, 58, -2
-
-const h4_interp8_hpp_shuf,     db 0, 1, 2, 3, 4, 5, 6, 7, 2, 3, 4, 5, 6, 7, 8, 9
-                            db 4, 5, 6, 7, 8, 9, 10, 11, 6, 7, 8, 9, 10, 11, 12, 13
-
-SECTION .text
-cextern pd_8
-cextern pd_32
-cextern pw_pixel_max
-cextern pd_524416
-cextern pd_n32768
-cextern pd_n131072
-cextern pw_2000
-cextern idct8_shuf2
-
-%macro FILTERH_W2_4_sse3 2
-    movh        m3,     [r0 + %1]
-    movhps      m3,     [r0 + %1 + 2]
-    pmaddwd     m3,     m0
-    movh        m4,     [r0 + r1 + %1]
-    movhps      m4,     [r0 + r1 + %1 + 2]
-    pmaddwd     m4,     m0
-    pshufd      m2,     m3,     q2301
-    paddd       m3,     m2
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m3,     m3,     q3120
-    pshufd      m4,     m4,     q3120
-    punpcklqdq  m3,     m4
-    paddd       m3,     m1
-    movh        m5,     [r0 + 2 * r1 + %1]
-    movhps      m5,     [r0 + 2 * r1 + %1 + 2]
-    pmaddwd     m5,     m0
-    movh        m4,     [r0 + r4 + %1]
-    movhps      m4,     [r0 + r4 + %1 + 2]
-    pmaddwd     m4,     m0
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m5,     m5,     q3120
-    pshufd      m4,     m4,     q3120
-    punpcklqdq  m5,     m4
-    paddd       m5,     m1
-%ifidn %2, pp
-    psrad       m3,     6
-    psrad       m5,     6
-    packssdw    m3,     m5
-    CLIPW       m3,     m7,     m6
-%else
-    psrad       m3,     INTERP_SHIFT_PS
-    psrad       m5,     INTERP_SHIFT_PS
-    packssdw    m3,     m5
-%endif
-    movd        [r2 + %1], m3
-    psrldq      m3,     4
-    movd        [r2 + r3 + %1], m3
-    psrldq      m3,     4
-    movd        [r2 + r3 * 2 + %1], m3
-    psrldq      m3,     4
-    movd        [r2 + r5 + %1], m3
-%endmacro
-
-%macro FILTERH_W2_3_sse3 1
-    movh        m3,     [r0 + %1]
-    movhps      m3,     [r0 + %1 + 2]
-    pmaddwd     m3,     m0
-    movh        m4,     [r0 + r1 + %1]
-    movhps      m4,     [r0 + r1 + %1 + 2]
-    pmaddwd     m4,     m0
-    pshufd      m2,     m3,     q2301
-    paddd       m3,     m2
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m3,     m3,     q3120
-    pshufd      m4,     m4,     q3120
-    punpcklqdq  m3,     m4
-    paddd       m3,     m1
-
-    movh        m5,     [r0 + 2 * r1 + %1]
-    movhps      m5,     [r0 + 2 * r1 + %1 + 2]
-    pmaddwd     m5,     m0
-
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m5,     m5,     q3120
-    paddd       m5,     m1
-
-    psrad       m3,     INTERP_SHIFT_PS
-    psrad       m5,     INTERP_SHIFT_PS
-    packssdw    m3,     m5
-
-    movd        [r2 + %1], m3
-    psrldq      m3,     4
-    movd        [r2 + r3 + %1], m3
-    psrldq      m3,     4
-    movd        [r2 + r3 * 2 + %1], m3
-%endmacro
-
-%macro FILTERH_W4_2_sse3 2
-    movh        m3,     [r0 + %1]
-    movhps      m3,     [r0 + %1 + 2]
-    pmaddwd     m3,     m0
-    movh        m4,     [r0 + %1 + 4]
-    movhps      m4,     [r0 + %1 + 6]
-    pmaddwd     m4,     m0
-    pshufd      m2,     m3,     q2301
-    paddd       m3,     m2
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m3,     m3,     q3120
-    pshufd      m4,     m4,     q3120
-    punpcklqdq  m3,     m4
-    paddd       m3,     m1
-
-    movh        m5,     [r0 + r1 + %1]
-    movhps      m5,     [r0 + r1 + %1 + 2]
-    pmaddwd     m5,     m0
-    movh        m4,     [r0 + r1 + %1 + 4]
-    movhps      m4,     [r0 + r1 + %1 + 6]
-    pmaddwd     m4,     m0
-    pshufd      m2,     m5,     q2301
-    paddd       m5,     m2
-    pshufd      m2,     m4,     q2301
-    paddd       m4,     m2
-    pshufd      m5,     m5,     q3120
-    pshufd      m4,     m4,     q3120
-    punpcklqdq  m5,     m4
-    paddd       m5,     m1
-%ifidn %2, pp
-    psrad       m3,     6
-    psrad       m5,     6
-    packssdw    m3,     m5
-    CLIPW       m3,     m7,     m6
-%else
-    psrad       m3,     INTERP_SHIFT_PS
-    psrad       m5,     INTERP_SHIFT_PS
-    packssdw    m3,     m5

x265_2.7.tar.gz/source/common/x86/v4-ipfilter16.asm Deleted

@@ -1,3529 +0,0 @@
-;*****************************************************************************
-;* Copyright (C) 2013-2017 MulticoreWare, Inc
-;*
-;* Authors: Nabajit Deka <nabajit@multicorewareinc.com>
-;*          Murugan Vairavel <murugan@multicorewareinc.com>
-;*          Min Chen <chenm003@163.com>
-;*
-;* This program is free software; you can redistribute it and/or modify
-;* it under the terms of the GNU General Public License as published by
-;* the Free Software Foundation; either version 2 of the License, or
-;* (at your option) any later version.
-;*
-;* This program 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 General Public License for more details.
-;*
-;* You should have received a copy of the GNU General Public License
-;* along with this program; if not, write to the Free Software
-;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
-;*
-;* This program is also available under a commercial proprietary license.
-;* For more information, contact us at license @ x265.com.
-;*****************************************************************************/
-
-%include "x86inc.asm"
-%include "x86util.asm"
-
-
-%define INTERP_OFFSET_PP        pd_32
-%define INTERP_SHIFT_PP         6
-
-%if BIT_DEPTH == 10
-    %define INTERP_SHIFT_PS         2
-    %define INTERP_OFFSET_PS        pd_n32768
-    %define INTERP_SHIFT_SP         10
-    %define INTERP_OFFSET_SP        v4_pd_524800
-%elif BIT_DEPTH == 12
-    %define INTERP_SHIFT_PS         4
-    %define INTERP_OFFSET_PS        pd_n131072
-    %define INTERP_SHIFT_SP         8
-    %define INTERP_OFFSET_SP        pd_524416
-%else
-    %error Unsupport bit depth!
-%endif
-
-
-SECTION_RODATA 32
-
-v4_pd_524800:        times 8 dd 524800
-tab_c_n8192:      times 8 dw -8192
-
-const tab_ChromaCoeffV,  times 8 dw 0, 64
-                         times 8 dw 0, 0
-
-                         times 8 dw -2, 58
-                         times 8 dw 10, -2
-
-                         times 8 dw -4, 54
-                         times 8 dw 16, -2
-
-                         times 8 dw -6, 46
-                         times 8 dw 28, -4
-
-                         times 8 dw -4, 36
-                         times 8 dw 36, -4
-
-                         times 8 dw -4, 28
-                         times 8 dw 46, -6
-
-                         times 8 dw -2, 16
-                         times 8 dw 54, -4
-
-                         times 8 dw -2, 10
-                         times 8 dw 58, -2
-                        
-tab_ChromaCoeffVer: times 8 dw 0, 64
-                    times 8 dw 0, 0
-
-                    times 8 dw -2, 58
-                    times 8 dw 10, -2
-
-                    times 8 dw -4, 54
-                    times 8 dw 16, -2
-
-                    times 8 dw -6, 46
-                    times 8 dw 28, -4
-
-                    times 8 dw -4, 36
-                    times 8 dw 36, -4
-
-                    times 8 dw -4, 28
-                    times 8 dw 46, -6
-
-                    times 8 dw -2, 16
-                    times 8 dw 54, -4
-
-                    times 8 dw -2, 10
-                    times 8 dw 58, -2
-                        
-SECTION .text
-cextern pd_8
-cextern pd_32
-cextern pw_pixel_max
-cextern pd_524416
-cextern pd_n32768
-cextern pd_n131072
-cextern pw_2000
-cextern idct8_shuf2
-
-%macro PROCESS_CHROMA_SP_W4_4R 0
-    movq       m0, [r0]
-    movq       m1, [r0 + r1]
-    punpcklwd  m0, m1                          ;m0=[0 1]
-    pmaddwd    m0, [r6 + 0 *32]                ;m0=[0+1]         Row1
-
-    lea        r0, [r0 + 2 * r1]
-    movq       m4, [r0]
-    punpcklwd  m1, m4                          ;m1=[1 2]
-    pmaddwd    m1, [r6 + 0 *32]                ;m1=[1+2]         Row2
-
-    movq       m5, [r0 + r1]
-    punpcklwd  m4, m5                          ;m4=[2 3]
-    pmaddwd    m2, m4, [r6 + 0 *32]            ;m2=[2+3]         Row3
-    pmaddwd    m4, [r6 + 1 * 32]
-    paddd      m0, m4                          ;m0=[0+1+2+3]     Row1 done
-
-    lea        r0, [r0 + 2 * r1]
-    movq       m4, [r0]
-    punpcklwd  m5, m4                          ;m5=[3 4]
-    pmaddwd    m3, m5, [r6 + 0 *32]            ;m3=[3+4]         Row4
-    pmaddwd    m5, [r6 + 1 * 32]
-    paddd      m1, m5                          ;m1 = [1+2+3+4]   Row2
-
-    movq       m5, [r0 + r1]
-    punpcklwd  m4, m5                          ;m4=[4 5]
-    pmaddwd    m4, [r6 + 1 * 32]
-    paddd      m2, m4                          ;m2=[2+3+4+5]     Row3
-
-    movq       m4, [r0 + 2 * r1]
-    punpcklwd  m5, m4                          ;m5=[5 6]
-    pmaddwd    m5, [r6 + 1 * 32]
-    paddd      m3, m5                          ;m3=[3+4+5+6]     Row4
-%endmacro
-
-;-----------------------------------------------------------------------------------------------------------------
-; void interp_4tap_vert_%3_%1x%2(int16_t *src, intptr_t srcStride, int16_t *dst, intptr_t dstStride, int coeffIdx)
-;-----------------------------------------------------------------------------------------------------------------
-%macro FILTER_VER_CHROMA_SS 4
-INIT_XMM sse2
-cglobal interp_4tap_vert_%3_%1x%2, 5, 7, %4 ,0-gprsize
-
-    add       r1d, r1d
-    add       r3d, r3d
-    sub       r0, r1
-    shl       r4d, 6
-
-%ifdef PIC
-    lea       r5, [tab_ChromaCoeffV]
-    lea       r6, [r5 + r4]
-%else
-    lea       r6, [tab_ChromaCoeffV + r4]
-%endif
-
-    mov       dword [rsp], %2/4
-
-%ifnidn %3, ss
-    %ifnidn %3, ps
-        mova      m7, [pw_pixel_max]
-        %ifidn %3, pp
-            mova      m6, [INTERP_OFFSET_PP]
-        %else
-            mova      m6, [INTERP_OFFSET_SP]
-        %endif
-    %else
-        mova      m6, [INTERP_OFFSET_PS]
-    %endif
-%endif
-
-.loopH:
-    mov       r4d, (%1/4)
-.loopW:
-    PROCESS_CHROMA_SP_W4_4R
-
-%ifidn %3, ss
-    psrad     m0, 6
-    psrad     m1, 6
-    psrad     m2, 6
-    psrad     m3, 6
-
-    packssdw  m0, m1
-    packssdw  m2, m3
-%elifidn %3, ps
-    paddd     m0, m6
-    paddd     m1, m6
-    paddd     m2, m6
-    paddd     m3, m6
-    psrad     m0, INTERP_SHIFT_PS
-    psrad     m1, INTERP_SHIFT_PS

x265_2.7.tar.gz/source/common/x86/v4-ipfilter8.asm Deleted

@@ -1,12799 +0,0 @@
-;*****************************************************************************
-;* Copyright (C) 2013-2017 MulticoreWare, Inc
-;*
-;* Authors: Min Chen <chenm003@163.com>
-;*          Nabajit Deka <nabajit@multicorewareinc.com>
-;*          Praveen Kumar Tiwari <praveen@multicorewareinc.com>
-;*
-;* This program is free software; you can redistribute it and/or modify
-;* it under the terms of the GNU General Public License as published by
-;* the Free Software Foundation; either version 2 of the License, or
-;* (at your option) any later version.
-;*
-;* This program 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 General Public License for more details.
-;*
-;* You should have received a copy of the GNU General Public License
-;* along with this program; if not, write to the Free Software
-;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02111, USA.
-;*
-;* This program is also available under a commercial proprietary license.
-;* For more information, contact us at license @ x265.com.
-;*****************************************************************************/
-
-%include "x86inc.asm"
-%include "x86util.asm"
-
-SECTION_RODATA 32
-
-const v4_pd_526336, times 8 dd 8192*64+2048
-
-const tab_Vm,    db 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1
-                 db 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3, 2, 3
-
-const tab_Cm,    db 0, 2, 1, 3, 0, 2, 1, 3, 0, 2, 1, 3, 0, 2, 1, 3
-
-const interp_vert_shuf, times 2 db 0, 2, 1, 3, 2, 4, 3, 5, 4, 6, 5, 7, 6, 8, 7, 9
-                        times 2 db 4, 6, 5, 7, 6, 8, 7, 9, 8, 10, 9, 11, 10, 12, 11, 13
-
-const v4_interp4_vpp_shuf, times 2 db 0, 4, 1, 5, 2, 6, 3, 7, 8, 12, 9, 13, 10, 14, 11, 15
-
-const v4_interp4_vpp_shuf1, dd 0, 1, 1, 2, 2, 3, 3, 4
-                         dd 2, 3, 3, 4, 4, 5, 5, 6
-
-const tab_ChromaCoeff, db  0, 64,  0,  0
-                       db -2, 58, 10, -2
-                       db -4, 54, 16, -2
-                       db -6, 46, 28, -4
-                       db -4, 36, 36, -4
-                       db -4, 28, 46, -6
-                       db -2, 16, 54, -4
-                       db -2, 10, 58, -2
-
-const tabw_ChromaCoeff, dw  0, 64,  0,  0
-                        dw -2, 58, 10, -2
-                        dw -4, 54, 16, -2
-                        dw -6, 46, 28, -4
-                        dw -4, 36, 36, -4
-                        dw -4, 28, 46, -6
-                        dw -2, 16, 54, -4
-                        dw -2, 10, 58, -2
-
-const tab_ChromaCoeffV, times 4 dw 0, 64
-                        times 4 dw 0, 0
-
-                        times 4 dw -2, 58
-                        times 4 dw 10, -2
-
-                        times 4 dw -4, 54
-                        times 4 dw 16, -2
-
-                        times 4 dw -6, 46
-                        times 4 dw 28, -4
-
-                        times 4 dw -4, 36
-                        times 4 dw 36, -4
-
-                        times 4 dw -4, 28
-                        times 4 dw 46, -6
-
-                        times 4 dw -2, 16
-                        times 4 dw 54, -4
-
-                        times 4 dw -2, 10
-                        times 4 dw 58, -2
-
-const tab_ChromaCoeff_V, times 8 db 0, 64
-                         times 8 db 0,  0
-
-                         times 8 db -2, 58
-                         times 8 db 10, -2
-
-                         times 8 db -4, 54
-                         times 8 db 16, -2
-
-                         times 8 db -6, 46
-                         times 8 db 28, -4
-
-                         times 8 db -4, 36
-                         times 8 db 36, -4
-
-                         times 8 db -4, 28
-                         times 8 db 46, -6
-
-                         times 8 db -2, 16
-                         times 8 db 54, -4
-
-                         times 8 db -2, 10
-                         times 8 db 58, -2
-
-const tab_ChromaCoeffVer_32,    times 16 db 0, 64
-                                times 16 db 0, 0
-
-                                times 16 db -2, 58
-                                times 16 db 10, -2
-
-                                times 16 db -4, 54
-                                times 16 db 16, -2
-
-                                times 16 db -6, 46
-                                times 16 db 28, -4
-
-                                times 16 db -4, 36
-                                times 16 db 36, -4
-
-                                times 16 db -4, 28
-                                times 16 db 46, -6
-
-                                times 16 db -2, 16
-                                times 16 db 54, -4
-
-                                times 16 db -2, 10
-                                times 16 db 58, -2
-
-const pw_ChromaCoeffV,  times 8 dw 0, 64
-                        times 8 dw 0, 0
-
-                        times 8 dw -2, 58
-                        times 8 dw 10, -2
-
-                        times 8 dw -4, 54
-                        times 8 dw 16, -2
-
-                        times 8 dw -6, 46
-                        times 8 dw 28, -4
-
-                        times 8 dw -4, 36
-                        times 8 dw 36, -4
-
-                        times 8 dw -4, 28
-                        times 8 dw 46, -6
-
-                        times 8 dw -2, 16
-                        times 8 dw 54, -4
-
-                        times 8 dw -2, 10
-                        times 8 dw 58, -2
-
-const v4_interp8_hps_shuf,     dd 0, 4, 1, 5, 2, 6, 3, 7
-
-SECTION .text
-
-cextern pw_32
-cextern pw_512
-cextern pw_2000
-
-%macro  WORD_TO_DOUBLE 1
-%if ARCH_X86_64
-    punpcklbw   %1,     m8
-%else
-    punpcklbw   %1,     %1
-    psrlw       %1,     8
-%endif
-%endmacro
-
-;-----------------------------------------------------------------------------
-; void interp_4tap_vert_%1_2x%2(pixel *src, intptr_t srcStride, pixel *dst, intptr_t dstStride, int coeffIdx)
-;-----------------------------------------------------------------------------
-%macro FILTER_V4_W2_H4_sse2 2
-INIT_XMM sse2
-%if ARCH_X86_64
-cglobal interp_4tap_vert_%1_2x%2, 4, 6, 9
-    pxor        m8,        m8
-%else
-cglobal interp_4tap_vert_%1_2x%2, 4, 6, 8
-%endif
-    mov         r4d,       r4m
-    sub         r0,        r1
-
-%ifidn %1,pp
-    mova        m1,        [pw_32]
-%elifidn %1,ps
-    mova        m1,        [pw_2000]
-    add         r3d,       r3d
-%endif
-
-%ifdef PIC
-    lea         r5,        [tabw_ChromaCoeff]

Changes of Revision 27