tbb-commits

Download

tbb-commits@lists.torproject.org

1 participants
18494 discussions

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1448483 - Remove reference and use of ssize_t in CityHash to avoid conflicting definitions in MinGW x64. r=froydnj, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 9b6eeae6e3a2aa909de97617d93c9dbf3d02ceca Author: Tom Ritter <tom(a)mozilla.com> Date: Fri Mar 23 16:27:49 2018 -0500 Bug 1448483 - Remove reference and use of ssize_t in CityHash to avoid conflicting definitions in MinGW x64. r=froydnj, a=jcristau MozReview-Commit-ID: ErQGSPNk4Bg --HG-- extra : rebase_source : 36015874d1abb0699e952d514e85d7a7b84c63b5 extra : source : 149a759643fbf35d45d4ffbc86706db8ba2d4ffd --- other-licenses/nsis/Contrib/CityHash/CityHash.h | 4 ---- other-licenses/nsis/Contrib/CityHash/cityhash/city.cpp | 4 ++-- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/other-licenses/nsis/Contrib/CityHash/CityHash.h b/other-licenses/nsis/Contrib/CityHash/CityHash.h old mode 100644 new mode 100755 index d74f30feb64a..4daa91d29498 --- a/other-licenses/nsis/Contrib/CityHash/CityHash.h +++ b/other-licenses/nsis/Contrib/CityHash/CityHash.h @@ -29,7 +29,3 @@ #else #define CITYHASH_API __declspec(dllimport) #endif - -#ifndef ssize_t -typedef int ssize_t; -#endif diff --git a/other-licenses/nsis/Contrib/CityHash/cityhash/city.cpp b/other-licenses/nsis/Contrib/CityHash/cityhash/city.cpp old mode 100644 new mode 100755 index 8ac4b5234914..b155241f6a28 --- a/other-licenses/nsis/Contrib/CityHash/cityhash/city.cpp +++ b/other-licenses/nsis/Contrib/CityHash/cityhash/city.cpp @@ -202,13 +202,13 @@ uint64 CityHash64WithSeeds(const char *s, size_t len, } // A subroutine for CityHash128(). Returns a decent 128-bit hash for strings -// of any length representable in ssize_t. Based on City and Murmur. +// of any length representable in an int. Based on City and Murmur. static uint128 CityMurmur(const char *s, size_t len, uint128 seed) { uint64 a = Uint128Low64(seed); uint64 b = Uint128High64(seed); uint64 c = 0; uint64 d = 0; - ssize_t l = len - 16; + int l = len - 16; if (l <= 0) { // len <= 16 c = b * k1 + HashLen0to16(s, len); d = Rotate(a + (len >= 8 ? UNALIGNED_LOAD64(s) : c), 32);

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1440013 - For MinGW build, pass -Wa, -mbig-obj to solve 'too many sections' errors. r=glandium, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 97271ab4577793c2db5a8a9b340a2736aaf784a0 Author: Tom Ritter <tom(a)mozilla.com> Date: Tue Mar 6 16:40:38 2018 -0600 Bug 1440013 - For MinGW build, pass -Wa,-mbig-obj to solve 'too many sections' errors. r=glandium, a=jcristau MozReview-Commit-ID: 9ObJnrcpeKe --HG-- extra : rebase_source : 074b4f47ef4c578571740606689fe36a20483d1f extra : source : f5c601a739458d391a022bf807149e100eff8aae --- build/autoconf/compiler-opts.m4 | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/build/autoconf/compiler-opts.m4 b/build/autoconf/compiler-opts.m4 index 3d9dc5a80032..b8ff219aa5d2 100644 --- a/build/autoconf/compiler-opts.m4 +++ b/build/autoconf/compiler-opts.m4 @@ -123,6 +123,12 @@ if test "$GNU_CC"; then if test -z "$DEVELOPER_OPTIONS"; then CFLAGS="$CFLAGS -ffunction-sections -fdata-sections" CXXFLAGS="$CXXFLAGS -ffunction-sections -fdata-sections" + + # For MinGW, we need big-obj otherwise we create too many sections in Unified builds + if test "${OS_ARCH}" = "WINNT"; then + CFLAGS="$CFLAGS -Wa,-mbig-obj" + CXXFLAGS="$CXXFLAGS -Wa,-mbig-obj" + fi fi CFLAGS="$CFLAGS -fno-math-errno" CXXFLAGS="$CXXFLAGS -fno-exceptions -fno-math-errno"

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1448746 - Capitalization fixes for MinGW x64 build in the crash reporter. r=gsvelto, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit fd2af1d9077e5ff07cb0e76976026b81663ac0ab Author: Tom Ritter <tom(a)mozilla.com> Date: Fri Mar 23 18:01:19 2018 -0500 Bug 1448746 - Capitalization fixes for MinGW x64 build in the crash reporter. r=gsvelto, a=jcristau MozReview-Commit-ID: 8tZkuachYhX --HG-- extra : rebase_source : 9170d2fdbfc92d7aba81a91d5438e0beeda2c139 extra : source : 412b3c06c06d191d1c0db2d19ccb5e9ff954813d --- toolkit/crashreporter/minidump-analyzer/moz.build | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/toolkit/crashreporter/minidump-analyzer/moz.build b/toolkit/crashreporter/minidump-analyzer/moz.build index 50852baee8a2..d52eaacf6704 100644 --- a/toolkit/crashreporter/minidump-analyzer/moz.build +++ b/toolkit/crashreporter/minidump-analyzer/moz.build @@ -25,8 +25,8 @@ if CONFIG['OS_TARGET'] != 'Android': ] OS_LIBS += [ - 'Dbghelp', - 'Imagehlp' + 'dbghelp', + 'imagehlp' ] if CONFIG['OS_TARGET'] == 'WINNT' and CONFIG['CC_TYPE'] == 'gcc':

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1457598 - Add MinGW and GCC scripts to the resources of fxc2 and nsis to ensure they get rebuilt. r=glandium, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit f00af23bb8832f6bdbfc29669a9f95730628cfeb Author: Tom Ritter <tom(a)mozilla.com> Date: Wed May 16 12:59:23 2018 -0500 Bug 1457598 - Add MinGW and GCC scripts to the resources of fxc2 and nsis to ensure they get rebuilt. r=glandium, a=jcristau --- taskcluster/ci/toolchain/linux.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/taskcluster/ci/toolchain/linux.yml b/taskcluster/ci/toolchain/linux.yml index 3b9449c89828..93274257ee56 100755 --- a/taskcluster/ci/toolchain/linux.yml +++ b/taskcluster/ci/toolchain/linux.yml @@ -546,6 +546,9 @@ linux64-mingw32-nsis: run: using: toolchain-script script: build-mingw32-nsis.sh + resources: + - 'build/unix/build-gcc/build-gcc.sh' + - 'taskcluster/scripts/misc/build-gcc-mingw32.sh' toolchain-artifact: public/build/nsis.tar.xz toolchains: - linux64-mingw32-gcc @@ -564,6 +567,9 @@ linux64-mingw32-fxc2: run: using: toolchain-script script: build-mingw32-fxc2.sh + resources: + - 'build/unix/build-gcc/build-gcc.sh' + - 'taskcluster/scripts/misc/build-gcc-mingw32.sh' toolchain-artifact: public/build/fxc2.tar.xz toolchains: - linux64-mingw32-gcc

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1456552 - Make Optimized MinGW builds use -O# instead of falling through and collecting a -O. r=ted, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 77f47f2b623a4dffac9162570ea0eaf0c58aeb68 Author: Tom Ritter <tom(a)mozilla.com> Date: Wed May 16 16:32:47 2018 -0500 Bug 1456552 - Make Optimized MinGW builds use -O# instead of falling through and collecting a -O. r=ted, a=jcristau We use -O2 for js (because we can) and we use -O1 for the root because there is an x86 compiler bug that is not immediately bypassable MozReview-Commit-ID: CnDk2ko3jfo --HG-- extra : source : 87f1c846afc3eca37b82d8e86dd3fe451175ab21 --- js/src/old-configure.in | 2 ++ old-configure.in | 2 ++ 2 files changed, 4 insertions(+) diff --git a/js/src/old-configure.in b/js/src/old-configure.in index b9aa86c0d83b..e4df0b05c526 100644 --- a/js/src/old-configure.in +++ b/js/src/old-configure.in @@ -655,6 +655,8 @@ case "$target" in LIBS="$LIBS -lgdi32 -lwinmm -lwsock32" MOZ_FIX_LINK_PATHS= + MOZ_OPTIMIZE_FLAGS="-O2" + WIN32_CONSOLE_EXE_LDFLAGS=-mconsole WIN32_GUI_EXE_LDFLAGS=-mwindows else diff --git a/old-configure.in b/old-configure.in index dd2fb701cd79..3d3e631d52fd 100644 --- a/old-configure.in +++ b/old-configure.in @@ -870,6 +870,8 @@ case "$target" in LIBS="$LIBS -luuid -lgdi32 -lwinmm -lwsock32 -luserenv -lsecur32" MOZ_FIX_LINK_PATHS= + MOZ_OPTIMIZE_FLAGS="-O1" + WIN32_CONSOLE_EXE_LDFLAGS=-mconsole WIN32_GUI_EXE_LDFLAGS=-mwindows

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Include <cstring> for memcmp in certverifier/Buffer.cpp
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit e65019d6dc6da89219673a9b688092c727ff07a4 Author: Sukhbir Singh <sukhbir(a)torproject.org> Date: Tue Jun 12 14:58:48 2018 -0400 Include <cstring> for memcmp in certverifier/Buffer.cpp --- security/certverifier/Buffer.cpp | 1 + 1 file changed, 1 insertion(+) diff --git a/security/certverifier/Buffer.cpp b/security/certverifier/Buffer.cpp index a36bfeabc13f..407d45a41253 100644 --- a/security/certverifier/Buffer.cpp +++ b/security/certverifier/Buffer.cpp @@ -5,6 +5,7 @@ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */ #include "Buffer.h" +#include <cstring> namespace mozilla {

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1448461 - Give libaom a x64 MinGW config. r=kinetik, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit ed7d52061e83d4dffe1443121852bec0d1c03c82 Author: Tom Ritter <tom(a)mozilla.com> Date: Fri Mar 23 15:14:00 2018 -0500 Bug 1448461 - Give libaom a x64 MinGW config. r=kinetik, a=jcristau MozReview-Commit-ID: BiBqBFSWYtK --HG-- extra : rebase_source : 891c101a9f37cd9b2e0e98914a4bf80ebbf216b5 extra : source : d4ffee5831765d4ee616d3dd88c601268db5fb31 --- media/libaom/config/win/mingw64/aom_config.asm | 176 + media/libaom/config/win/mingw64/aom_config.c | 11 + media/libaom/config/win/mingw64/aom_config.h | 192 + media/libaom/config/win/mingw64/aom_dsp_rtcd.h | 4524 ++++++++++++++++++++++ media/libaom/config/win/mingw64/aom_scale_rtcd.h | 78 + media/libaom/config/win/mingw64/av1_rtcd.h | 590 +++ media/libaom/generate_sources_mozbuild.sh | 4 + media/libaom/moz.build | 11 +- 8 files changed, 5583 insertions(+), 3 deletions(-) diff --git a/media/libaom/config/win/mingw64/aom_config.asm b/media/libaom/config/win/mingw64/aom_config.asm new file mode 100644 index 000000000000..455683b8f89b --- /dev/null +++ b/media/libaom/config/win/mingw64/aom_config.asm @@ -0,0 +1,176 @@ +ARCH_ARM equ 0 +ARCH_MIPS equ 0 +ARCH_X86 equ 0 +ARCH_X86_64 equ 1 +HAVE_NEON equ 0 +HAVE_NEON_ASM equ 0 +HAVE_MIPS32 equ 0 +HAVE_DSPR2 equ 0 +HAVE_MSA equ 0 +HAVE_MIPS64 equ 0 +HAVE_MMX equ 1 +HAVE_SSE equ 1 +HAVE_SSE2 equ 1 +HAVE_SSE3 equ 1 +HAVE_SSSE3 equ 1 +HAVE_SSE4_1 equ 1 +HAVE_AVX equ 1 +HAVE_AVX2 equ 1 +HAVE_AOM_PORTS equ 1 +HAVE_FEXCEPT equ 1 +HAVE_PTHREAD_H equ 1 +HAVE_WXWIDGETS equ 0 +CONFIG_DEPENDENCY_TRACKING equ 1 +CONFIG_EXTERNAL_BUILD equ 1 +CONFIG_INSTALL_DOCS equ 1 +CONFIG_INSTALL_BINS equ 1 +CONFIG_INSTALL_LIBS equ 1 +CONFIG_INSTALL_SRCS equ 0 +CONFIG_DEBUG equ 0 +CONFIG_GPROF equ 0 +CONFIG_GCOV equ 0 +CONFIG_RVCT equ 0 +CONFIG_GCC equ 1 +CONFIG_MSVS equ 0 +CONFIG_PIC equ 1 +CONFIG_BIG_ENDIAN equ 0 +CONFIG_CODEC_SRCS equ 0 +CONFIG_DEBUG_LIBS equ 0 +CONFIG_RUNTIME_CPU_DETECT equ 1 +CONFIG_POSTPROC equ 1 +CONFIG_MULTITHREAD equ 1 +CONFIG_INTERNAL_STATS equ 0 +CONFIG_AV1_ENCODER equ 1 +CONFIG_AV1_DECODER equ 1 +CONFIG_AV1 equ 1 +CONFIG_STATIC_MSVCRT equ 0 +CONFIG_SPATIAL_RESAMPLING equ 1 +CONFIG_REALTIME_ONLY equ 0 +CONFIG_SHARED equ 0 +CONFIG_STATIC equ 1 +CONFIG_SMALL equ 0 +CONFIG_POSTPROC_VISUALIZER equ 0 +CONFIG_OS_SUPPORT equ 1 +CONFIG_UNIT_TESTS equ 0 +CONFIG_WEBM_IO equ 1 +CONFIG_LIBYUV equ 1 +CONFIG_ACCOUNTING equ 0 +CONFIG_INSPECTION equ 0 +CONFIG_DECODE_PERF_TESTS equ 0 +CONFIG_ENCODE_PERF_TESTS equ 0 +CONFIG_BITSTREAM_DEBUG equ 0 +CONFIG_SYMBOLRATE equ 0 +CONFIG_COEFFICIENT_RANGE_CHECKING equ 0 +CONFIG_LOWBITDEPTH equ 1 +CONFIG_HIGHBITDEPTH equ 1 +CONFIG_EXPERIMENTAL equ 0 +CONFIG_SIZE_LIMIT equ 1 +CONFIG_FP_MB_STATS equ 0 +CONFIG_CDEF equ 1 +CONFIG_CDEF_SINGLEPASS equ 1 +CONFIG_VAR_TX equ 1 +CONFIG_RECT_TX equ 1 +CONFIG_RECT_TX_EXT equ 0 +CONFIG_TPL_MV equ 0 +CONFIG_DUAL_FILTER equ 1 +CONFIG_CONVOLVE_ROUND equ 1 +CONFIG_COMPOUND_ROUND equ 0 +CONFIG_EXT_TX equ 1 +CONFIG_TX64X64 equ 0 +CONFIG_EXT_INTRA equ 1 +CONFIG_INTRA_INTERP equ 0 +CONFIG_FILTER_INTRA equ 0 +CONFIG_INTRA_EDGE equ 1 +CONFIG_INTRABC equ 0 +CONFIG_INTERINTRA equ 1 +CONFIG_WEDGE equ 1 +CONFIG_COMPOUND_SEGMENT equ 1 +CONFIG_EXT_REFS equ 1 +CONFIG_GLOBAL_MOTION equ 1 +CONFIG_NEW_QUANT equ 0 +CONFIG_SUPERTX equ 0 +CONFIG_ANS equ 0 +CONFIG_LOOP_RESTORATION equ 1 +CONFIG_STRIPED_LOOP_RESTORATION equ 0 +CONFIG_EXT_PARTITION equ 0 +CONFIG_EXT_PARTITION_TYPES equ 0 +CONFIG_EXT_PARTITION_TYPES_AB equ 0 +CONFIG_UNPOISON_PARTITION_CTX equ 0 +CONFIG_EXT_TILE equ 0 +CONFIG_MOTION_VAR equ 1 +CONFIG_NCOBMC equ 0 +CONFIG_WARPED_MOTION equ 1 +CONFIG_Q_ADAPT_PROBS equ 0 +CONFIG_INTER_STATS_ONLY equ 0 +CONFIG_PALETTE_DELTA_ENCODING equ 0 +CONFIG_RAWBITS equ 0 +CONFIG_KF_CTX equ 0 +CONFIG_PVQ equ 0 +CONFIG_CFL equ 0 +CONFIG_XIPHRC equ 0 +CONFIG_DCT_ONLY equ 0 +CONFIG_DAALA_TX equ 0 +CONFIG_DAALA_DCT4 equ 0 +CONFIG_DAALA_DCT8 equ 0 +CONFIG_DAALA_DCT16 equ 0 +CONFIG_DAALA_DCT32 equ 0 +CONFIG_DAALA_DCT64 equ 0 +CONFIG_CB4X4 equ 1 +CONFIG_CHROMA_2X2 equ 0 +CONFIG_CHROMA_SUB8X8 equ 1 +CONFIG_FRAME_SIZE equ 0 +CONFIG_EXT_DELTA_Q equ 1 +CONFIG_ADAPT_SCAN equ 0 +CONFIG_PARALLEL_DEBLOCKING equ 1 +CONFIG_DEBLOCK_13TAP equ 0 +CONFIG_LOOPFILTERING_ACROSS_TILES equ 1 +CONFIG_TEMPMV_SIGNALING equ 1 +CONFIG_RD_DEBUG equ 0 +CONFIG_REFERENCE_BUFFER equ 1 +CONFIG_COEF_INTERLEAVE equ 0 +CONFIG_ENTROPY_STATS equ 0 +CONFIG_MASKED_TX equ 0 +CONFIG_DEPENDENT_HORZTILES equ 0 +CONFIG_DIST_8X8 equ 1 +CONFIG_PALETTE_THROUGHPUT equ 1 +CONFIG_REF_ADAPT equ 0 +CONFIG_LV_MAP equ 0 +CONFIG_CTX1D equ 0 +CONFIG_TXK_SEL equ 0 +CONFIG_MV_COMPRESS equ 1 +CONFIG_SEGMENT_ZEROMV equ 0 +CONFIG_FRAME_SUPERRES equ 0 +CONFIG_NEW_MULTISYMBOL equ 0 +CONFIG_COMPOUND_SINGLEREF equ 0 +CONFIG_AOM_QM equ 1 +CONFIG_ONE_SIDED_COMPOUND equ 1 +CONFIG_EXT_COMP_REFS equ 1 +CONFIG_SMOOTH_HV equ 1 +CONFIG_VAR_REFS equ 0 +CONFIG_LGT equ 0 +CONFIG_LGT_FROM_PRED equ 0 +CONFIG_SBL_SYMBOL equ 0 +CONFIG_NCOBMC_ADAPT_WEIGHT equ 0 +CONFIG_BGSPRITE equ 0 +CONFIG_VAR_TX_NO_TX_MODE equ 0 +CONFIG_MRC_TX equ 0 +CONFIG_LPF_DIRECT equ 0 +CONFIG_LOOPFILTER_LEVEL equ 0 +CONFIG_NO_FRAME_CONTEXT_SIGNALING equ 0 +CONFIG_TXMG equ 1 +CONFIG_MAX_TILE equ 0 +CONFIG_HASH_ME equ 0 +CONFIG_COLORSPACE_HEADERS equ 0 +CONFIG_MFMV equ 0 +CONFIG_FRAME_MARKER equ 0 +CONFIG_JNT_COMP equ 0 +CONFIG_FRAME_SIGN_BIAS equ 0 +CONFIG_EXT_SKIP equ 0 +CONFIG_OBU equ 0 +CONFIG_AMVR equ 0 +CONFIG_LPF_SB equ 0 +CONFIG_OPT_REF_MV equ 0 +CONFIG_TMV equ 0 +CONFIG_RESTRICT_COMPRESSED_HDR equ 0 +CONFIG_HORZONLY_FRAME_SUPERRES equ 0 +CONFIG_ANALYZER equ 0 diff --git a/media/libaom/config/win/mingw64/aom_config.c b/media/libaom/config/win/mingw64/aom_config.c new file mode 100644 index 000000000000..3d86ef9bc2a1 --- /dev/null +++ b/media/libaom/config/win/mingw64/aom_config.c @@ -0,0 +1,11 @@ +/* Copyright (c) 2016, Alliance for Open Media. All rights reserved. */ +/* */ +/* This source code is subject to the terms of the BSD 2 Clause License and */ +/* the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License */ +/* was not distributed with this source code in the LICENSE file, you can */ +/* obtain it at www.aomedia.org/license/software. If the Alliance for Open */ +/* Media Patent License 1.0 was not distributed with this source code in the */ +/* PATENTS file, you can obtain it at www.aomedia.org/license/patent. */ +#include "aom/aom_codec.h" +static const char* const cfg = "--target=x86_64-win64-gcc --enable-external-build --disable-examples --disable-docs --disable-unit-tests --size-limit=8192x4608 --enable-pic --enable-postproc --as=yasm"; +const char *aom_codec_build_config(void) {return cfg;} diff --git a/media/libaom/config/win/mingw64/aom_config.h b/media/libaom/config/win/mingw64/aom_config.h new file mode 100644 index 000000000000..675561be8fcd --- /dev/null +++ b/media/libaom/config/win/mingw64/aom_config.h @@ -0,0 +1,192 @@ +/* Copyright (c) 2016, Alliance for Open Media. All rights reserved. */ +/* */ +/* This source code is subject to the terms of the BSD 2 Clause License and */ +/* the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License */ +/* was not distributed with this source code in the LICENSE file, you can */ +/* obtain it at www.aomedia.org/license/software. If the Alliance for Open */ +/* Media Patent License 1.0 was not distributed with this source code in the */ +/* PATENTS file, you can obtain it at www.aomedia.org/license/patent. */ +/* This file automatically generated by configure. Do not edit! */ +#ifndef AOM_CONFIG_H +#define AOM_CONFIG_H +#define RESTRICT +#define INLINE inline +#define ARCH_ARM 0 +#define ARCH_MIPS 0 +#define ARCH_X86 0 +#define ARCH_X86_64 1 +#define HAVE_NEON 0 +#define HAVE_NEON_ASM 0 +#define HAVE_MIPS32 0 +#define HAVE_DSPR2 0 +#define HAVE_MSA 0 +#define HAVE_MIPS64 0 +#define HAVE_MMX 1 +#define HAVE_SSE 1 +#define HAVE_SSE2 1 +#define HAVE_SSE3 1 +#define HAVE_SSSE3 1 +#define HAVE_SSE4_1 1 +#define HAVE_AVX 1 +#define HAVE_AVX2 1 +#define HAVE_AOM_PORTS 1 +#define HAVE_FEXCEPT 1 +#define HAVE_PTHREAD_H 1 +#define HAVE_WXWIDGETS 0 +#define CONFIG_DEPENDENCY_TRACKING 1 +#define CONFIG_EXTERNAL_BUILD 1 +#define CONFIG_INSTALL_DOCS 1 +#define CONFIG_INSTALL_BINS 1 +#define CONFIG_INSTALL_LIBS 1 +#define CONFIG_INSTALL_SRCS 0 +#define CONFIG_DEBUG 0 +#define CONFIG_GPROF 0 +#define CONFIG_GCOV 0 +#define CONFIG_RVCT 0 +#define CONFIG_GCC 1 +#define CONFIG_MSVS 0 +#define CONFIG_PIC 1 +#define CONFIG_BIG_ENDIAN 0 +#define CONFIG_CODEC_SRCS 0 +#define CONFIG_DEBUG_LIBS 0 +#define CONFIG_RUNTIME_CPU_DETECT 1 +#define CONFIG_POSTPROC 1 +#define CONFIG_MULTITHREAD 1 +#define CONFIG_INTERNAL_STATS 0 +#define CONFIG_AV1_ENCODER 1 +#define CONFIG_AV1_DECODER 1 +#define CONFIG_AV1 1 +#define CONFIG_STATIC_MSVCRT 0 +#define CONFIG_SPATIAL_RESAMPLING 1 +#define CONFIG_REALTIME_ONLY 0 +#define CONFIG_SHARED 0 +#define CONFIG_STATIC 1 +#define CONFIG_SMALL 0 +#define CONFIG_POSTPROC_VISUALIZER 0 +#define CONFIG_OS_SUPPORT 1 +#define CONFIG_UNIT_TESTS 0 +#define CONFIG_WEBM_IO 1 +#define CONFIG_LIBYUV 1 +#define CONFIG_ACCOUNTING 0 +#define CONFIG_INSPECTION 0 +#define CONFIG_DECODE_PERF_TESTS 0 +#define CONFIG_ENCODE_PERF_TESTS 0 +#define CONFIG_BITSTREAM_DEBUG 0 +#define CONFIG_SYMBOLRATE 0 +#define CONFIG_COEFFICIENT_RANGE_CHECKING 0 +#define CONFIG_LOWBITDEPTH 1 +#define CONFIG_HIGHBITDEPTH 1 +#define CONFIG_EXPERIMENTAL 0 +#define CONFIG_SIZE_LIMIT 1 +#define CONFIG_FP_MB_STATS 0 +#define CONFIG_CDEF 1 +#define CONFIG_CDEF_SINGLEPASS 1 +#define CONFIG_VAR_TX 1 +#define CONFIG_RECT_TX 1 +#define CONFIG_RECT_TX_EXT 0 +#define CONFIG_TPL_MV 0 +#define CONFIG_DUAL_FILTER 1 +#define CONFIG_CONVOLVE_ROUND 1 +#define CONFIG_COMPOUND_ROUND 0 +#define CONFIG_EXT_TX 1 +#define CONFIG_TX64X64 0 +#define CONFIG_EXT_INTRA 1 +#define CONFIG_INTRA_INTERP 0 +#define CONFIG_FILTER_INTRA 0 +#define CONFIG_INTRA_EDGE 1 +#define CONFIG_INTRABC 0 +#define CONFIG_INTERINTRA 1 +#define CONFIG_WEDGE 1 +#define CONFIG_COMPOUND_SEGMENT 1 +#define CONFIG_EXT_REFS 1 +#define CONFIG_GLOBAL_MOTION 1 +#define CONFIG_NEW_QUANT 0 +#define CONFIG_SUPERTX 0 +#define CONFIG_ANS 0 +#define CONFIG_LOOP_RESTORATION 1 +#define CONFIG_STRIPED_LOOP_RESTORATION 0 +#define CONFIG_EXT_PARTITION 0 +#define CONFIG_EXT_PARTITION_TYPES 0 +#define CONFIG_EXT_PARTITION_TYPES_AB 0 +#define CONFIG_UNPOISON_PARTITION_CTX 0 +#define CONFIG_EXT_TILE 0 +#define CONFIG_MOTION_VAR 1 +#define CONFIG_NCOBMC 0 +#define CONFIG_WARPED_MOTION 1 +#define CONFIG_Q_ADAPT_PROBS 0 +#define CONFIG_INTER_STATS_ONLY 0 +#define CONFIG_PALETTE_DELTA_ENCODING 0 +#define CONFIG_RAWBITS 0 +#define CONFIG_KF_CTX 0 +#define CONFIG_PVQ 0 +#define CONFIG_CFL 0 +#define CONFIG_XIPHRC 0 +#define CONFIG_DCT_ONLY 0 +#define CONFIG_DAALA_TX 0 +#define CONFIG_DAALA_DCT4 0 +#define CONFIG_DAALA_DCT8 0 +#define CONFIG_DAALA_DCT16 0 +#define CONFIG_DAALA_DCT32 0 +#define CONFIG_DAALA_DCT64 0 +#define CONFIG_CB4X4 1 +#define CONFIG_CHROMA_2X2 0 +#define CONFIG_CHROMA_SUB8X8 1 +#define CONFIG_FRAME_SIZE 0 +#define CONFIG_EXT_DELTA_Q 1 +#define CONFIG_ADAPT_SCAN 0 +#define CONFIG_PARALLEL_DEBLOCKING 1 +#define CONFIG_DEBLOCK_13TAP 0 +#define CONFIG_LOOPFILTERING_ACROSS_TILES 1 +#define CONFIG_TEMPMV_SIGNALING 1 +#define CONFIG_RD_DEBUG 0 +#define CONFIG_REFERENCE_BUFFER 1 +#define CONFIG_COEF_INTERLEAVE 0 +#define CONFIG_ENTROPY_STATS 0 +#define CONFIG_MASKED_TX 0 +#define CONFIG_DEPENDENT_HORZTILES 0 +#define CONFIG_DIST_8X8 1 +#define CONFIG_PALETTE_THROUGHPUT 1 +#define CONFIG_REF_ADAPT 0 +#define CONFIG_LV_MAP 0 +#define CONFIG_CTX1D 0 +#define CONFIG_TXK_SEL 0 +#define CONFIG_MV_COMPRESS 1 +#define CONFIG_SEGMENT_ZEROMV 0 +#define CONFIG_FRAME_SUPERRES 0 +#define CONFIG_NEW_MULTISYMBOL 0 +#define CONFIG_COMPOUND_SINGLEREF 0 +#define CONFIG_AOM_QM 1 +#define CONFIG_ONE_SIDED_COMPOUND 1 +#define CONFIG_EXT_COMP_REFS 1 +#define CONFIG_SMOOTH_HV 1 +#define CONFIG_VAR_REFS 0 +#define CONFIG_LGT 0 +#define CONFIG_LGT_FROM_PRED 0 +#define CONFIG_SBL_SYMBOL 0 +#define CONFIG_NCOBMC_ADAPT_WEIGHT 0 +#define CONFIG_BGSPRITE 0 +#define CONFIG_VAR_TX_NO_TX_MODE 0 +#define CONFIG_MRC_TX 0 +#define CONFIG_LPF_DIRECT 0 +#define CONFIG_LOOPFILTER_LEVEL 0 +#define CONFIG_NO_FRAME_CONTEXT_SIGNALING 0 +#define CONFIG_TXMG 1 +#define CONFIG_MAX_TILE 0 +#define CONFIG_HASH_ME 0 +#define CONFIG_COLORSPACE_HEADERS 0 +#define CONFIG_MFMV 0 +#define CONFIG_FRAME_MARKER 0 +#define CONFIG_JNT_COMP 0 +#define CONFIG_FRAME_SIGN_BIAS 0 +#define CONFIG_EXT_SKIP 0 +#define CONFIG_OBU 0 +#define CONFIG_AMVR 0 +#define CONFIG_LPF_SB 0 +#define CONFIG_OPT_REF_MV 0 +#define CONFIG_TMV 0 +#define CONFIG_RESTRICT_COMPRESSED_HDR 0 +#define CONFIG_HORZONLY_FRAME_SUPERRES 0 +#define CONFIG_ANALYZER 0 +#define DECODE_WIDTH_LIMIT 8192 +#define DECODE_HEIGHT_LIMIT 4608 +#endif /* AOM_CONFIG_H */ diff --git a/media/libaom/config/win/mingw64/aom_dsp_rtcd.h b/media/libaom/config/win/mingw64/aom_dsp_rtcd.h new file mode 100644 index 000000000000..d2bee385ff45 --- /dev/null +++ b/media/libaom/config/win/mingw64/aom_dsp_rtcd.h @@ -0,0 +1,4524 @@ +#ifndef AOM_DSP_RTCD_H_ +#define AOM_DSP_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +/* + * DSP + */ + +#include "aom/aom_integer.h" +#include "aom_dsp/aom_dsp_common.h" +#include "av1/common/enums.h" + + +#ifdef __cplusplus +extern "C" { +#endif + +void aom_blend_a64_d32_mask_c(int32_t *dst, uint32_t dst_stride, const int32_t *src0, uint32_t src0_stride, const int32_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx); +#define aom_blend_a64_d32_mask aom_blend_a64_d32_mask_c + +void aom_blend_a64_hmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w); +void aom_blend_a64_hmask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w); +RTCD_EXTERN void (*aom_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w); + +void aom_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx); +void aom_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx); +RTCD_EXTERN void (*aom_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx); + +void aom_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w); +void aom_blend_a64_vmask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w); +RTCD_EXTERN void (*aom_blend_a64_vmask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w); + +void aom_comp_avg_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, int height, const uint8_t *ref, int ref_stride); +#define aom_comp_avg_pred aom_comp_avg_pred_c + +void aom_comp_avg_upsampled_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref, int ref_stride); +void aom_comp_avg_upsampled_pred_sse2(uint8_t *comp_pred, const uint8_t *pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref, int ref_stride); +#define aom_comp_avg_upsampled_pred aom_comp_avg_upsampled_pred_sse2 + +void aom_comp_mask_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, int height, const uint8_t *ref, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask); +#define aom_comp_mask_pred aom_comp_mask_pred_c + +void aom_comp_mask_upsampled_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask); +#define aom_comp_mask_upsampled_pred aom_comp_mask_upsampled_pred_c + +void aom_convolve8_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_add_src_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_add_src_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_add_src)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_add_src_hip_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_add_src_hip_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_convolve8_add_src_hip aom_convolve8_add_src_hip_sse2 + +void aom_convolve8_add_src_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_add_src_horiz_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_add_src_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_add_src_horiz_hip_c(const uint8_t *src, ptrdiff_t src_stride, uint16_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_convolve8_add_src_horiz_hip aom_convolve8_add_src_horiz_hip_c + +void aom_convolve8_add_src_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_add_src_vert_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_add_src_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_add_src_vert_hip_c(const uint16_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_convolve8_add_src_vert_hip aom_convolve8_add_src_vert_hip_c + +void aom_convolve8_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avg_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_avg)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avg_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avg_horiz_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_avg_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_avg_horiz_scale_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int subpel_x, int x_step_q4, const int16_t *filter_y, int subpel_y, int y_step_q4, int w, int h); +#define aom_convolve8_avg_horiz_scale aom_convolve8_avg_horiz_scale_c + +void aom_convolve8_avg_scale_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int subpel_x, int x_step_q4, const int16_t *filter_y, int subpel_y, int y_step_q4, int w, int h); +#define aom_convolve8_avg_scale aom_convolve8_avg_scale_c + +void aom_convolve8_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avg_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_avg_vert_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_avg_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_avg_vert_scale_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int subpel_x, int x_step_q4, const int16_t *filter_y, int subpel_y, int y_step_q4, int w, int h); +#define aom_convolve8_avg_vert_scale aom_convolve8_avg_vert_scale_c + +void aom_convolve8_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_horiz_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_horiz_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_horiz_scale_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int subpel_x, int x_step_q4, const int16_t *filter_y, int subpel_y, int y_step_q4, int w, int h); +#define aom_convolve8_horiz_scale aom_convolve8_horiz_scale_c + +void aom_convolve8_scale_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int subpel_x, int x_step_q4, const int16_t *filter_y, int subpel_y, int y_step_q4, int w, int h); +#define aom_convolve8_scale aom_convolve8_scale_c + +void aom_convolve8_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_vert_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve8_vert_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_convolve8_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_convolve8_vert_scale_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int subpel_x, int x_step_q4, const int16_t *filter_y, int subpel_y, int y_step_q4, int w, int h); +#define aom_convolve8_vert_scale aom_convolve8_vert_scale_c + +void aom_convolve_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_convolve_avg aom_convolve_avg_sse2 + +void aom_convolve_copy_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_convolve_copy_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_convolve_copy aom_convolve_copy_sse2 + +void aom_d117_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_16x16 aom_d117_predictor_16x16_c + +void aom_d117_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_16x32 aom_d117_predictor_16x32_c + +void aom_d117_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_16x8 aom_d117_predictor_16x8_c + +void aom_d117_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_2x2 aom_d117_predictor_2x2_c + +void aom_d117_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_32x16 aom_d117_predictor_32x16_c + +void aom_d117_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_32x32 aom_d117_predictor_32x32_c + +void aom_d117_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_4x4 aom_d117_predictor_4x4_c + +void aom_d117_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_4x8 aom_d117_predictor_4x8_c + +void aom_d117_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_8x16 aom_d117_predictor_8x16_c + +void aom_d117_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_8x4 aom_d117_predictor_8x4_c + +void aom_d117_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d117_predictor_8x8 aom_d117_predictor_8x8_c + +void aom_d135_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_16x16 aom_d135_predictor_16x16_c + +void aom_d135_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_16x32 aom_d135_predictor_16x32_c + +void aom_d135_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_16x8 aom_d135_predictor_16x8_c + +void aom_d135_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_2x2 aom_d135_predictor_2x2_c + +void aom_d135_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_32x16 aom_d135_predictor_32x16_c + +void aom_d135_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_32x32 aom_d135_predictor_32x32_c + +void aom_d135_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_4x4 aom_d135_predictor_4x4_c + +void aom_d135_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_4x8 aom_d135_predictor_4x8_c + +void aom_d135_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_8x16 aom_d135_predictor_8x16_c + +void aom_d135_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_8x4 aom_d135_predictor_8x4_c + +void aom_d135_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d135_predictor_8x8 aom_d135_predictor_8x8_c + +void aom_d153_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_d153_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_d153_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_d153_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_16x32 aom_d153_predictor_16x32_c + +void aom_d153_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_16x8 aom_d153_predictor_16x8_c + +void aom_d153_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_2x2 aom_d153_predictor_2x2_c + +void aom_d153_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_32x16 aom_d153_predictor_32x16_c + +void aom_d153_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_d153_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_d153_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_d153_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_d153_predictor_4x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_d153_predictor_4x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_d153_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_4x8 aom_d153_predictor_4x8_c + +void aom_d153_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_8x16 aom_d153_predictor_8x16_c + +void aom_d153_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d153_predictor_8x4 aom_d153_predictor_8x4_c + +void aom_d153_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_d153_predictor_8x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_d153_predictor_8x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_d207e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_16x16 aom_d207e_predictor_16x16_c + +void aom_d207e_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_16x32 aom_d207e_predictor_16x32_c + +void aom_d207e_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_16x8 aom_d207e_predictor_16x8_c + +void aom_d207e_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_2x2 aom_d207e_predictor_2x2_c + +void aom_d207e_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_32x16 aom_d207e_predictor_32x16_c + +void aom_d207e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_32x32 aom_d207e_predictor_32x32_c + +void aom_d207e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_4x4 aom_d207e_predictor_4x4_c + +void aom_d207e_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_4x8 aom_d207e_predictor_4x8_c + +void aom_d207e_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_8x16 aom_d207e_predictor_8x16_c + +void aom_d207e_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_8x4 aom_d207e_predictor_8x4_c + +void aom_d207e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d207e_predictor_8x8 aom_d207e_predictor_8x8_c + +void aom_d45e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_16x16 aom_d45e_predictor_16x16_c + +void aom_d45e_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_16x32 aom_d45e_predictor_16x32_c + +void aom_d45e_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_16x8 aom_d45e_predictor_16x8_c + +void aom_d45e_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_2x2 aom_d45e_predictor_2x2_c + +void aom_d45e_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_32x16 aom_d45e_predictor_32x16_c + +void aom_d45e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_32x32 aom_d45e_predictor_32x32_c + +void aom_d45e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_4x4 aom_d45e_predictor_4x4_c + +void aom_d45e_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_4x8 aom_d45e_predictor_4x8_c + +void aom_d45e_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_8x16 aom_d45e_predictor_8x16_c + +void aom_d45e_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_8x4 aom_d45e_predictor_8x4_c + +void aom_d45e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d45e_predictor_8x8 aom_d45e_predictor_8x8_c + +void aom_d63e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_16x16 aom_d63e_predictor_16x16_c + +void aom_d63e_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_16x32 aom_d63e_predictor_16x32_c + +void aom_d63e_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_16x8 aom_d63e_predictor_16x8_c + +void aom_d63e_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_2x2 aom_d63e_predictor_2x2_c + +void aom_d63e_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_32x16 aom_d63e_predictor_32x16_c + +void aom_d63e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_32x32 aom_d63e_predictor_32x32_c + +void aom_d63e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_d63e_predictor_4x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_d63e_predictor_4x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_d63e_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_4x8 aom_d63e_predictor_4x8_c + +void aom_d63e_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_8x16 aom_d63e_predictor_8x16_c + +void aom_d63e_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_8x4 aom_d63e_predictor_8x4_c + +void aom_d63e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_d63e_predictor_8x8 aom_d63e_predictor_8x8_c + +void aom_dc_128_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_16x16 aom_dc_128_predictor_16x16_sse2 + +void aom_dc_128_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_16x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_16x32 aom_dc_128_predictor_16x32_sse2 + +void aom_dc_128_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_16x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_16x8 aom_dc_128_predictor_16x8_sse2 + +void aom_dc_128_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_2x2 aom_dc_128_predictor_2x2_c + +void aom_dc_128_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_32x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_32x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_128_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_128_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_128_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_128_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_4x4 aom_dc_128_predictor_4x4_sse2 + +void aom_dc_128_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_4x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_4x8 aom_dc_128_predictor_4x8_sse2 + +void aom_dc_128_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_8x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_8x16 aom_dc_128_predictor_8x16_sse2 + +void aom_dc_128_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_8x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_8x4 aom_dc_128_predictor_8x4_sse2 + +void aom_dc_128_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_128_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_128_predictor_8x8 aom_dc_128_predictor_8x8_sse2 + +void aom_dc_left_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_16x16 aom_dc_left_predictor_16x16_sse2 + +void aom_dc_left_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_16x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_16x32 aom_dc_left_predictor_16x32_sse2 + +void aom_dc_left_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_16x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_16x8 aom_dc_left_predictor_16x8_sse2 + +void aom_dc_left_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_2x2 aom_dc_left_predictor_2x2_c + +void aom_dc_left_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_32x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_32x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_left_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_left_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_left_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_left_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_4x4 aom_dc_left_predictor_4x4_sse2 + +void aom_dc_left_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_4x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_4x8 aom_dc_left_predictor_4x8_sse2 + +void aom_dc_left_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_8x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_8x16 aom_dc_left_predictor_8x16_sse2 + +void aom_dc_left_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_8x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_8x4 aom_dc_left_predictor_8x4_sse2 + +void aom_dc_left_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_left_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_left_predictor_8x8 aom_dc_left_predictor_8x8_sse2 + +void aom_dc_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_16x16 aom_dc_predictor_16x16_sse2 + +void aom_dc_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_16x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_16x32 aom_dc_predictor_16x32_sse2 + +void aom_dc_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_16x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_16x8 aom_dc_predictor_16x8_sse2 + +void aom_dc_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_2x2 aom_dc_predictor_2x2_c + +void aom_dc_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_32x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_32x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_4x4 aom_dc_predictor_4x4_sse2 + +void aom_dc_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_4x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_4x8 aom_dc_predictor_4x8_sse2 + +void aom_dc_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_8x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_8x16 aom_dc_predictor_8x16_sse2 + +void aom_dc_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_8x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_8x4 aom_dc_predictor_8x4_sse2 + +void aom_dc_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_predictor_8x8 aom_dc_predictor_8x8_sse2 + +void aom_dc_top_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_16x16 aom_dc_top_predictor_16x16_sse2 + +void aom_dc_top_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_16x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_16x32 aom_dc_top_predictor_16x32_sse2 + +void aom_dc_top_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_16x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_16x8 aom_dc_top_predictor_16x8_sse2 + +void aom_dc_top_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_2x2 aom_dc_top_predictor_2x2_c + +void aom_dc_top_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_32x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_32x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_top_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_top_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_dc_top_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_dc_top_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_4x4 aom_dc_top_predictor_4x4_sse2 + +void aom_dc_top_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_4x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_4x8 aom_dc_top_predictor_4x8_sse2 + +void aom_dc_top_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_8x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_8x16 aom_dc_top_predictor_8x16_sse2 + +void aom_dc_top_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_8x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_8x4 aom_dc_top_predictor_8x4_sse2 + +void aom_dc_top_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_dc_top_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_dc_top_predictor_8x8 aom_dc_top_predictor_8x8_sse2 + +void aom_fdct16x16_c(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct16x16_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_fdct16x16 aom_fdct16x16_sse2 + +void aom_fdct32x32_c(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct32x32_sse2(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct32x32_avx2(const int16_t *input, tran_low_t *output, int stride); +RTCD_EXTERN void (*aom_fdct32x32)(const int16_t *input, tran_low_t *output, int stride); + +void aom_fdct32x32_rd_c(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct32x32_rd_sse2(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct32x32_rd_avx2(const int16_t *input, tran_low_t *output, int stride); +RTCD_EXTERN void (*aom_fdct32x32_rd)(const int16_t *input, tran_low_t *output, int stride); + +void aom_fdct4x4_c(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct4x4_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_fdct4x4 aom_fdct4x4_sse2 + +void aom_fdct4x4_1_c(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct4x4_1_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_fdct4x4_1 aom_fdct4x4_1_sse2 + +void aom_fdct8x8_c(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct8x8_sse2(const int16_t *input, tran_low_t *output, int stride); +void aom_fdct8x8_ssse3(const int16_t *input, tran_low_t *output, int stride); +RTCD_EXTERN void (*aom_fdct8x8)(const int16_t *input, tran_low_t *output, int stride); + +void aom_get16x16var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +void aom_get16x16var_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +void aom_get16x16var_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +RTCD_EXTERN void (*aom_get16x16var)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); + +unsigned int aom_get4x4sse_cs_c(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride); +#define aom_get4x4sse_cs aom_get4x4sse_cs_c + +void aom_get8x8var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +void aom_get8x8var_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_get8x8var aom_get8x8var_sse2 + +unsigned int aom_get_mb_ss_c(const int16_t *); +unsigned int aom_get_mb_ss_sse2(const int16_t *); +#define aom_get_mb_ss aom_get_mb_ss_sse2 + +void aom_h_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_16x16 aom_h_predictor_16x16_sse2 + +void aom_h_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_16x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_16x32 aom_h_predictor_16x32_sse2 + +void aom_h_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_16x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_16x8 aom_h_predictor_16x8_sse2 + +void aom_h_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_2x2 aom_h_predictor_2x2_c + +void aom_h_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_32x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_32x16 aom_h_predictor_32x16_sse2 + +void aom_h_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_h_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_h_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_4x4 aom_h_predictor_4x4_sse2 + +void aom_h_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_4x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_4x8 aom_h_predictor_4x8_sse2 + +void aom_h_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_8x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_8x16 aom_h_predictor_8x16_sse2 + +void aom_h_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_8x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_8x4 aom_h_predictor_8x4_sse2 + +void aom_h_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_h_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_h_predictor_8x8 aom_h_predictor_8x8_sse2 + +void aom_hadamard_16x16_c(const int16_t *src_diff, int src_stride, int16_t *coeff); +void aom_hadamard_16x16_sse2(const int16_t *src_diff, int src_stride, int16_t *coeff); +#define aom_hadamard_16x16 aom_hadamard_16x16_sse2 + +void aom_hadamard_8x8_c(const int16_t *src_diff, int src_stride, int16_t *coeff); +void aom_hadamard_8x8_sse2(const int16_t *src_diff, int src_stride, int16_t *coeff); +void aom_hadamard_8x8_ssse3(const int16_t *src_diff, int src_stride, int16_t *coeff); +RTCD_EXTERN void (*aom_hadamard_8x8)(const int16_t *src_diff, int src_stride, int16_t *coeff); + +void aom_highbd_10_get16x16var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_highbd_10_get16x16var aom_highbd_10_get16x16var_c + +void aom_highbd_10_get8x8var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_highbd_10_get8x8var aom_highbd_10_get8x8var_c + +unsigned int aom_highbd_10_masked_sub_pixel_variance16x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance16x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance16x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance16x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance16x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance16x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance16x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance16x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance16x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance32x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance32x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance32x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance32x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance32x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance32x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance32x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance32x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance32x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance4x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance4x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance4x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance4x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance4x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance4x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance64x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance64x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance64x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance64x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance64x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance64x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance8x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance8x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance8x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance8x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance8x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance8x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_masked_sub_pixel_variance8x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_10_masked_sub_pixel_variance8x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_masked_sub_pixel_variance8x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_10_mse16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_highbd_10_mse16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_10_mse16x16 aom_highbd_10_mse16x16_sse2 + +unsigned int aom_highbd_10_mse16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_10_mse16x8 aom_highbd_10_mse16x8_c + +unsigned int aom_highbd_10_mse8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_10_mse8x16 aom_highbd_10_mse8x16_c + +unsigned int aom_highbd_10_mse8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_highbd_10_mse8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_10_mse8x8 aom_highbd_10_mse8x8_sse2 + +unsigned int aom_highbd_10_obmc_sub_pixel_variance16x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance16x16 aom_highbd_10_obmc_sub_pixel_variance16x16_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance16x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance16x32 aom_highbd_10_obmc_sub_pixel_variance16x32_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance16x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance16x8 aom_highbd_10_obmc_sub_pixel_variance16x8_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance32x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance32x16 aom_highbd_10_obmc_sub_pixel_variance32x16_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance32x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance32x32 aom_highbd_10_obmc_sub_pixel_variance32x32_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance32x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance32x64 aom_highbd_10_obmc_sub_pixel_variance32x64_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance4x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance4x4 aom_highbd_10_obmc_sub_pixel_variance4x4_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance4x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance4x8 aom_highbd_10_obmc_sub_pixel_variance4x8_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance64x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance64x32 aom_highbd_10_obmc_sub_pixel_variance64x32_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance64x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance64x64 aom_highbd_10_obmc_sub_pixel_variance64x64_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance8x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance8x16 aom_highbd_10_obmc_sub_pixel_variance8x16_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance8x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance8x4 aom_highbd_10_obmc_sub_pixel_variance8x4_c + +unsigned int aom_highbd_10_obmc_sub_pixel_variance8x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_10_obmc_sub_pixel_variance8x8 aom_highbd_10_obmc_sub_pixel_variance8x8_c + +unsigned int aom_highbd_10_obmc_variance16x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance16x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance16x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance16x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance16x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance16x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance16x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance16x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance16x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance32x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance32x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance32x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance32x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance32x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance32x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance32x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance32x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance32x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance4x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance4x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance4x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance4x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance4x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance4x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance64x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance64x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance64x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance64x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance64x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance64x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance8x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance8x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance8x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance8x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance8x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance8x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_10_obmc_variance8x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_10_obmc_variance8x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_obmc_variance8x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +uint32_t aom_highbd_10_sub_pixel_avg_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance16x16 aom_highbd_10_sub_pixel_avg_variance16x16_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance16x32 aom_highbd_10_sub_pixel_avg_variance16x32_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance16x8 aom_highbd_10_sub_pixel_avg_variance16x8_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance32x16 aom_highbd_10_sub_pixel_avg_variance32x16_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance32x32 aom_highbd_10_sub_pixel_avg_variance32x32_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance32x64 aom_highbd_10_sub_pixel_avg_variance32x64_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_highbd_10_sub_pixel_avg_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_highbd_10_sub_pixel_avg_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance4x8 aom_highbd_10_sub_pixel_avg_variance4x8_c + +uint32_t aom_highbd_10_sub_pixel_avg_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance64x32 aom_highbd_10_sub_pixel_avg_variance64x32_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance64x64 aom_highbd_10_sub_pixel_avg_variance64x64_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance8x16 aom_highbd_10_sub_pixel_avg_variance8x16_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance8x4 aom_highbd_10_sub_pixel_avg_variance8x4_sse2 + +uint32_t aom_highbd_10_sub_pixel_avg_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_10_sub_pixel_avg_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_10_sub_pixel_avg_variance8x8 aom_highbd_10_sub_pixel_avg_variance8x8_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance16x16 aom_highbd_10_sub_pixel_variance16x16_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance16x32 aom_highbd_10_sub_pixel_variance16x32_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance16x8 aom_highbd_10_sub_pixel_variance16x8_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance32x16 aom_highbd_10_sub_pixel_variance32x16_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance32x32 aom_highbd_10_sub_pixel_variance32x32_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance32x64 aom_highbd_10_sub_pixel_variance32x64_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_highbd_10_sub_pixel_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_highbd_10_sub_pixel_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance4x8 aom_highbd_10_sub_pixel_variance4x8_c + +uint32_t aom_highbd_10_sub_pixel_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance64x32 aom_highbd_10_sub_pixel_variance64x32_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance64x64 aom_highbd_10_sub_pixel_variance64x64_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance8x16 aom_highbd_10_sub_pixel_variance8x16_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance8x4 aom_highbd_10_sub_pixel_variance8x4_sse2 + +uint32_t aom_highbd_10_sub_pixel_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_10_sub_pixel_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_10_sub_pixel_variance8x8 aom_highbd_10_sub_pixel_variance8x8_sse2 + +unsigned int aom_highbd_10_variance16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance16x16 aom_highbd_10_variance16x16_sse2 + +unsigned int aom_highbd_10_variance16x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance16x32 aom_highbd_10_variance16x32_sse2 + +unsigned int aom_highbd_10_variance16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance16x8 aom_highbd_10_variance16x8_sse2 + +unsigned int aom_highbd_10_variance2x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance2x2 aom_highbd_10_variance2x2_c + +unsigned int aom_highbd_10_variance2x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance2x4 aom_highbd_10_variance2x4_c + +unsigned int aom_highbd_10_variance32x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance32x16 aom_highbd_10_variance32x16_sse2 + +unsigned int aom_highbd_10_variance32x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance32x32 aom_highbd_10_variance32x32_sse2 + +unsigned int aom_highbd_10_variance32x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance32x64 aom_highbd_10_variance32x64_sse2 + +unsigned int aom_highbd_10_variance4x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance4x2 aom_highbd_10_variance4x2_c + +unsigned int aom_highbd_10_variance4x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_10_variance4x4)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_highbd_10_variance4x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance4x8 aom_highbd_10_variance4x8_c + +unsigned int aom_highbd_10_variance64x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance64x32 aom_highbd_10_variance64x32_sse2 + +unsigned int aom_highbd_10_variance64x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance64x64 aom_highbd_10_variance64x64_sse2 + +unsigned int aom_highbd_10_variance8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance8x16 aom_highbd_10_variance8x16_sse2 + +unsigned int aom_highbd_10_variance8x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance8x4 aom_highbd_10_variance8x4_c + +unsigned int aom_highbd_10_variance8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_10_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_10_variance8x8 aom_highbd_10_variance8x8_sse2 + +void aom_highbd_12_get16x16var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_highbd_12_get16x16var aom_highbd_12_get16x16var_c + +void aom_highbd_12_get8x8var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_highbd_12_get8x8var aom_highbd_12_get8x8var_c + +unsigned int aom_highbd_12_masked_sub_pixel_variance16x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance16x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance16x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance16x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance16x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance16x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance16x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance16x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance16x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance32x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance32x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance32x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance32x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance32x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance32x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance32x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance32x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance32x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance4x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance4x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance4x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance4x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance4x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance4x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance64x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance64x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance64x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance64x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance64x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance64x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance8x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance8x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance8x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance8x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance8x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance8x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_masked_sub_pixel_variance8x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_12_masked_sub_pixel_variance8x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_masked_sub_pixel_variance8x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_12_mse16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_highbd_12_mse16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_12_mse16x16 aom_highbd_12_mse16x16_sse2 + +unsigned int aom_highbd_12_mse16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_12_mse16x8 aom_highbd_12_mse16x8_c + +unsigned int aom_highbd_12_mse8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_12_mse8x16 aom_highbd_12_mse8x16_c + +unsigned int aom_highbd_12_mse8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_highbd_12_mse8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_12_mse8x8 aom_highbd_12_mse8x8_sse2 + +unsigned int aom_highbd_12_obmc_sub_pixel_variance16x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance16x16 aom_highbd_12_obmc_sub_pixel_variance16x16_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance16x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance16x32 aom_highbd_12_obmc_sub_pixel_variance16x32_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance16x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance16x8 aom_highbd_12_obmc_sub_pixel_variance16x8_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance32x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance32x16 aom_highbd_12_obmc_sub_pixel_variance32x16_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance32x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance32x32 aom_highbd_12_obmc_sub_pixel_variance32x32_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance32x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance32x64 aom_highbd_12_obmc_sub_pixel_variance32x64_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance4x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance4x4 aom_highbd_12_obmc_sub_pixel_variance4x4_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance4x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance4x8 aom_highbd_12_obmc_sub_pixel_variance4x8_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance64x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance64x32 aom_highbd_12_obmc_sub_pixel_variance64x32_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance64x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance64x64 aom_highbd_12_obmc_sub_pixel_variance64x64_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance8x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance8x16 aom_highbd_12_obmc_sub_pixel_variance8x16_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance8x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance8x4 aom_highbd_12_obmc_sub_pixel_variance8x4_c + +unsigned int aom_highbd_12_obmc_sub_pixel_variance8x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_12_obmc_sub_pixel_variance8x8 aom_highbd_12_obmc_sub_pixel_variance8x8_c + +unsigned int aom_highbd_12_obmc_variance16x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance16x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance16x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance16x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance16x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance16x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance16x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance16x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance16x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance32x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance32x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance32x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance32x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance32x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance32x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance32x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance32x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance32x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance4x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance4x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance4x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance4x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance4x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance4x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance64x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance64x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance64x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance64x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance64x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance64x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance8x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance8x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance8x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance8x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance8x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance8x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_12_obmc_variance8x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_12_obmc_variance8x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_obmc_variance8x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +uint32_t aom_highbd_12_sub_pixel_avg_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance16x16 aom_highbd_12_sub_pixel_avg_variance16x16_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance16x32 aom_highbd_12_sub_pixel_avg_variance16x32_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance16x8 aom_highbd_12_sub_pixel_avg_variance16x8_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance32x16 aom_highbd_12_sub_pixel_avg_variance32x16_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance32x32 aom_highbd_12_sub_pixel_avg_variance32x32_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance32x64 aom_highbd_12_sub_pixel_avg_variance32x64_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_highbd_12_sub_pixel_avg_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_highbd_12_sub_pixel_avg_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance4x8 aom_highbd_12_sub_pixel_avg_variance4x8_c + +uint32_t aom_highbd_12_sub_pixel_avg_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance64x32 aom_highbd_12_sub_pixel_avg_variance64x32_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance64x64 aom_highbd_12_sub_pixel_avg_variance64x64_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance8x16 aom_highbd_12_sub_pixel_avg_variance8x16_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance8x4 aom_highbd_12_sub_pixel_avg_variance8x4_sse2 + +uint32_t aom_highbd_12_sub_pixel_avg_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_12_sub_pixel_avg_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_12_sub_pixel_avg_variance8x8 aom_highbd_12_sub_pixel_avg_variance8x8_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance16x16 aom_highbd_12_sub_pixel_variance16x16_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance16x32 aom_highbd_12_sub_pixel_variance16x32_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance16x8 aom_highbd_12_sub_pixel_variance16x8_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance32x16 aom_highbd_12_sub_pixel_variance32x16_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance32x32 aom_highbd_12_sub_pixel_variance32x32_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance32x64 aom_highbd_12_sub_pixel_variance32x64_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_highbd_12_sub_pixel_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_highbd_12_sub_pixel_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance4x8 aom_highbd_12_sub_pixel_variance4x8_c + +uint32_t aom_highbd_12_sub_pixel_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance64x32 aom_highbd_12_sub_pixel_variance64x32_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance64x64 aom_highbd_12_sub_pixel_variance64x64_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance8x16 aom_highbd_12_sub_pixel_variance8x16_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance8x4 aom_highbd_12_sub_pixel_variance8x4_sse2 + +uint32_t aom_highbd_12_sub_pixel_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_12_sub_pixel_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_12_sub_pixel_variance8x8 aom_highbd_12_sub_pixel_variance8x8_sse2 + +unsigned int aom_highbd_12_variance16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance16x16 aom_highbd_12_variance16x16_sse2 + +unsigned int aom_highbd_12_variance16x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance16x32 aom_highbd_12_variance16x32_sse2 + +unsigned int aom_highbd_12_variance16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance16x8 aom_highbd_12_variance16x8_sse2 + +unsigned int aom_highbd_12_variance2x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance2x2 aom_highbd_12_variance2x2_c + +unsigned int aom_highbd_12_variance2x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance2x4 aom_highbd_12_variance2x4_c + +unsigned int aom_highbd_12_variance32x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance32x16 aom_highbd_12_variance32x16_sse2 + +unsigned int aom_highbd_12_variance32x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance32x32 aom_highbd_12_variance32x32_sse2 + +unsigned int aom_highbd_12_variance32x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance32x64 aom_highbd_12_variance32x64_sse2 + +unsigned int aom_highbd_12_variance4x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance4x2 aom_highbd_12_variance4x2_c + +unsigned int aom_highbd_12_variance4x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_12_variance4x4)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_highbd_12_variance4x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance4x8 aom_highbd_12_variance4x8_c + +unsigned int aom_highbd_12_variance64x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance64x32 aom_highbd_12_variance64x32_sse2 + +unsigned int aom_highbd_12_variance64x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance64x64 aom_highbd_12_variance64x64_sse2 + +unsigned int aom_highbd_12_variance8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance8x16 aom_highbd_12_variance8x16_sse2 + +unsigned int aom_highbd_12_variance8x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance8x4 aom_highbd_12_variance8x4_c + +unsigned int aom_highbd_12_variance8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_12_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_12_variance8x8 aom_highbd_12_variance8x8_sse2 + +void aom_highbd_8_get16x16var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_highbd_8_get16x16var aom_highbd_8_get16x16var_c + +void aom_highbd_8_get8x8var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define aom_highbd_8_get8x8var aom_highbd_8_get8x8var_c + +unsigned int aom_highbd_8_masked_sub_pixel_variance16x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance16x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance16x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance16x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance16x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance16x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance16x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance16x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance16x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance32x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance32x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance32x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance32x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance32x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance32x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance32x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance32x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance32x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance4x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance4x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance4x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance4x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance4x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance4x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance64x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance64x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance64x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance64x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance64x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance64x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance8x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance8x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance8x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance8x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance8x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance8x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_masked_sub_pixel_variance8x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_highbd_8_masked_sub_pixel_variance8x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_masked_sub_pixel_variance8x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_highbd_8_mse16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_highbd_8_mse16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_8_mse16x16 aom_highbd_8_mse16x16_sse2 + +unsigned int aom_highbd_8_mse16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_8_mse16x8 aom_highbd_8_mse16x8_c + +unsigned int aom_highbd_8_mse8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_8_mse8x16 aom_highbd_8_mse8x16_c + +unsigned int aom_highbd_8_mse8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_highbd_8_mse8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_highbd_8_mse8x8 aom_highbd_8_mse8x8_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance16x16 aom_highbd_8_sub_pixel_avg_variance16x16_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance16x32 aom_highbd_8_sub_pixel_avg_variance16x32_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance16x8 aom_highbd_8_sub_pixel_avg_variance16x8_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance32x16 aom_highbd_8_sub_pixel_avg_variance32x16_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance32x32 aom_highbd_8_sub_pixel_avg_variance32x32_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance32x64 aom_highbd_8_sub_pixel_avg_variance32x64_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_highbd_8_sub_pixel_avg_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_highbd_8_sub_pixel_avg_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance4x8 aom_highbd_8_sub_pixel_avg_variance4x8_c + +uint32_t aom_highbd_8_sub_pixel_avg_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance64x32 aom_highbd_8_sub_pixel_avg_variance64x32_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance64x64 aom_highbd_8_sub_pixel_avg_variance64x64_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance8x16 aom_highbd_8_sub_pixel_avg_variance8x16_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance8x4 aom_highbd_8_sub_pixel_avg_variance8x4_sse2 + +uint32_t aom_highbd_8_sub_pixel_avg_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_highbd_8_sub_pixel_avg_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +#define aom_highbd_8_sub_pixel_avg_variance8x8 aom_highbd_8_sub_pixel_avg_variance8x8_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance16x16 aom_highbd_8_sub_pixel_variance16x16_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance16x32 aom_highbd_8_sub_pixel_variance16x32_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance16x8 aom_highbd_8_sub_pixel_variance16x8_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance32x16 aom_highbd_8_sub_pixel_variance32x16_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance32x32 aom_highbd_8_sub_pixel_variance32x32_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance32x64 aom_highbd_8_sub_pixel_variance32x64_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_highbd_8_sub_pixel_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_highbd_8_sub_pixel_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance4x8 aom_highbd_8_sub_pixel_variance4x8_c + +uint32_t aom_highbd_8_sub_pixel_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance64x32 aom_highbd_8_sub_pixel_variance64x32_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance64x64 aom_highbd_8_sub_pixel_variance64x64_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance8x16 aom_highbd_8_sub_pixel_variance8x16_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance8x4 aom_highbd_8_sub_pixel_variance8x4_sse2 + +uint32_t aom_highbd_8_sub_pixel_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_highbd_8_sub_pixel_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_highbd_8_sub_pixel_variance8x8 aom_highbd_8_sub_pixel_variance8x8_sse2 + +unsigned int aom_highbd_8_variance16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance16x16 aom_highbd_8_variance16x16_sse2 + +unsigned int aom_highbd_8_variance16x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance16x32 aom_highbd_8_variance16x32_sse2 + +unsigned int aom_highbd_8_variance16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance16x8 aom_highbd_8_variance16x8_sse2 + +unsigned int aom_highbd_8_variance2x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance2x2 aom_highbd_8_variance2x2_c + +unsigned int aom_highbd_8_variance2x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance2x4 aom_highbd_8_variance2x4_c + +unsigned int aom_highbd_8_variance32x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance32x16 aom_highbd_8_variance32x16_sse2 + +unsigned int aom_highbd_8_variance32x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance32x32 aom_highbd_8_variance32x32_sse2 + +unsigned int aom_highbd_8_variance32x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance32x64 aom_highbd_8_variance32x64_sse2 + +unsigned int aom_highbd_8_variance4x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance4x2 aom_highbd_8_variance4x2_c + +unsigned int aom_highbd_8_variance4x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance4x4_sse4_1(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_8_variance4x4)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_highbd_8_variance4x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance4x8 aom_highbd_8_variance4x8_c + +unsigned int aom_highbd_8_variance64x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance64x32 aom_highbd_8_variance64x32_sse2 + +unsigned int aom_highbd_8_variance64x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance64x64 aom_highbd_8_variance64x64_sse2 + +unsigned int aom_highbd_8_variance8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance8x16 aom_highbd_8_variance8x16_sse2 + +unsigned int aom_highbd_8_variance8x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance8x4 aom_highbd_8_variance8x4_c + +unsigned int aom_highbd_8_variance8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_highbd_8_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_highbd_8_variance8x8 aom_highbd_8_variance8x8_sse2 + +void aom_highbd_blend_a64_hmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w, int bd); +void aom_highbd_blend_a64_hmask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w, int bd); +RTCD_EXTERN void (*aom_highbd_blend_a64_hmask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w, int bd); + +void aom_highbd_blend_a64_mask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx, int bd); +void aom_highbd_blend_a64_mask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx, int bd); +RTCD_EXTERN void (*aom_highbd_blend_a64_mask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, uint32_t mask_stride, int h, int w, int suby, int subx, int bd); + +void aom_highbd_blend_a64_vmask_c(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w, int bd); +void aom_highbd_blend_a64_vmask_sse4_1(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w, int bd); +RTCD_EXTERN void (*aom_highbd_blend_a64_vmask)(uint8_t *dst, uint32_t dst_stride, const uint8_t *src0, uint32_t src0_stride, const uint8_t *src1, uint32_t src1_stride, const uint8_t *mask, int h, int w, int bd); + +void aom_highbd_comp_avg_pred_c(uint16_t *comp_pred, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride); +#define aom_highbd_comp_avg_pred aom_highbd_comp_avg_pred_c + +void aom_highbd_comp_avg_upsampled_pred_c(uint16_t *comp_pred, const uint8_t *pred8, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref8, int ref_stride, int bd); +void aom_highbd_comp_avg_upsampled_pred_sse2(uint16_t *comp_pred, const uint8_t *pred8, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref8, int ref_stride, int bd); +#define aom_highbd_comp_avg_upsampled_pred aom_highbd_comp_avg_upsampled_pred_sse2 + +void aom_highbd_comp_mask_pred_c(uint16_t *comp_pred, const uint8_t *pred8, int width, int height, const uint8_t *ref8, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask); +#define aom_highbd_comp_mask_pred aom_highbd_comp_mask_pred_c + +void aom_highbd_comp_mask_upsampled_pred_c(uint16_t *comp_pred, const uint8_t *pred8, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref8, int ref_stride, const uint8_t *mask, int mask_stride, int invert_mask, int bd); +#define aom_highbd_comp_mask_upsampled_pred aom_highbd_comp_mask_upsampled_pred_c + +void aom_highbd_convolve8_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve8_add_src_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_add_src_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define aom_highbd_convolve8_add_src aom_highbd_convolve8_add_src_sse2 + +void aom_highbd_convolve8_add_src_hip_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_add_src_hip_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8_add_src_hip)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve8_add_src_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define aom_highbd_convolve8_add_src_horiz aom_highbd_convolve8_add_src_horiz_c + +void aom_highbd_convolve8_add_src_horiz_hip_c(const uint8_t *src, ptrdiff_t src_stride, uint16_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define aom_highbd_convolve8_add_src_horiz_hip aom_highbd_convolve8_add_src_horiz_hip_c + +void aom_highbd_convolve8_add_src_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define aom_highbd_convolve8_add_src_vert aom_highbd_convolve8_add_src_vert_c + +void aom_highbd_convolve8_add_src_vert_hip_c(const uint16_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define aom_highbd_convolve8_add_src_vert_hip aom_highbd_convolve8_add_src_vert_hip_c + +void aom_highbd_convolve8_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avg_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8_avg)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve8_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avg_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avg_horiz_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8_avg_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve8_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avg_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_avg_vert_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8_avg_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve8_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_horiz_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve8_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve8_vert_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve8_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve_avg_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve_avg)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_convolve_copy_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve_copy_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void aom_highbd_convolve_copy_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +RTCD_EXTERN void (*aom_highbd_convolve_copy)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); + +void aom_highbd_d117_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d117_predictor_16x16_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d117_predictor_16x16)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d117_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_16x32 aom_highbd_d117_predictor_16x32_c + +void aom_highbd_d117_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_16x8 aom_highbd_d117_predictor_16x8_c + +void aom_highbd_d117_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_2x2 aom_highbd_d117_predictor_2x2_c + +void aom_highbd_d117_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_32x16 aom_highbd_d117_predictor_32x16_c + +void aom_highbd_d117_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d117_predictor_32x32_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d117_predictor_32x32)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d117_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d117_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_4x4 aom_highbd_d117_predictor_4x4_sse2 + +void aom_highbd_d117_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_4x8 aom_highbd_d117_predictor_4x8_c + +void aom_highbd_d117_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_8x16 aom_highbd_d117_predictor_8x16_c + +void aom_highbd_d117_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d117_predictor_8x4 aom_highbd_d117_predictor_8x4_c + +void aom_highbd_d117_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d117_predictor_8x8_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d117_predictor_8x8)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d135_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d135_predictor_16x16_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d135_predictor_16x16)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d135_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_16x32 aom_highbd_d135_predictor_16x32_c + +void aom_highbd_d135_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_16x8 aom_highbd_d135_predictor_16x8_c + +void aom_highbd_d135_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_2x2 aom_highbd_d135_predictor_2x2_c + +void aom_highbd_d135_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_32x16 aom_highbd_d135_predictor_32x16_c + +void aom_highbd_d135_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d135_predictor_32x32_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d135_predictor_32x32)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d135_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d135_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_4x4 aom_highbd_d135_predictor_4x4_sse2 + +void aom_highbd_d135_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_4x8 aom_highbd_d135_predictor_4x8_c + +void aom_highbd_d135_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_8x16 aom_highbd_d135_predictor_8x16_c + +void aom_highbd_d135_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d135_predictor_8x4 aom_highbd_d135_predictor_8x4_c + +void aom_highbd_d135_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d135_predictor_8x8_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d135_predictor_8x8)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d153_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d153_predictor_16x16_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d153_predictor_16x16)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d153_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_16x32 aom_highbd_d153_predictor_16x32_c + +void aom_highbd_d153_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_16x8 aom_highbd_d153_predictor_16x8_c + +void aom_highbd_d153_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_2x2 aom_highbd_d153_predictor_2x2_c + +void aom_highbd_d153_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_32x16 aom_highbd_d153_predictor_32x16_c + +void aom_highbd_d153_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d153_predictor_32x32_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d153_predictor_32x32)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d153_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d153_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_4x4 aom_highbd_d153_predictor_4x4_sse2 + +void aom_highbd_d153_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_4x8 aom_highbd_d153_predictor_4x8_c + +void aom_highbd_d153_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_8x16 aom_highbd_d153_predictor_8x16_c + +void aom_highbd_d153_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d153_predictor_8x4 aom_highbd_d153_predictor_8x4_c + +void aom_highbd_d153_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d153_predictor_8x8_ssse3(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d153_predictor_8x8)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d207e_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_16x16 aom_highbd_d207e_predictor_16x16_c + +void aom_highbd_d207e_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_16x32 aom_highbd_d207e_predictor_16x32_c + +void aom_highbd_d207e_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_16x8 aom_highbd_d207e_predictor_16x8_c + +void aom_highbd_d207e_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_2x2 aom_highbd_d207e_predictor_2x2_c + +void aom_highbd_d207e_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_32x16 aom_highbd_d207e_predictor_32x16_c + +void aom_highbd_d207e_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_32x32 aom_highbd_d207e_predictor_32x32_c + +void aom_highbd_d207e_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_4x4 aom_highbd_d207e_predictor_4x4_c + +void aom_highbd_d207e_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_4x8 aom_highbd_d207e_predictor_4x8_c + +void aom_highbd_d207e_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_8x16 aom_highbd_d207e_predictor_8x16_c + +void aom_highbd_d207e_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_8x4 aom_highbd_d207e_predictor_8x4_c + +void aom_highbd_d207e_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d207e_predictor_8x8 aom_highbd_d207e_predictor_8x8_c + +void aom_highbd_d45e_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_16x16_avx2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d45e_predictor_16x16)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d45e_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_16x32_avx2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d45e_predictor_16x32)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d45e_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_16x8_avx2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d45e_predictor_16x8)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d45e_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d45e_predictor_2x2 aom_highbd_d45e_predictor_2x2_c + +void aom_highbd_d45e_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_32x16_avx2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d45e_predictor_32x16)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d45e_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_32x32_avx2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +RTCD_EXTERN void (*aom_highbd_d45e_predictor_32x32)(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); + +void aom_highbd_d45e_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d45e_predictor_4x4 aom_highbd_d45e_predictor_4x4_sse2 + +void aom_highbd_d45e_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d45e_predictor_4x8 aom_highbd_d45e_predictor_4x8_sse2 + +void aom_highbd_d45e_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d45e_predictor_8x16 aom_highbd_d45e_predictor_8x16_sse2 + +void aom_highbd_d45e_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d45e_predictor_8x4 aom_highbd_d45e_predictor_8x4_sse2 + +void aom_highbd_d45e_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_d45e_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d45e_predictor_8x8 aom_highbd_d45e_predictor_8x8_sse2 + +void aom_highbd_d63e_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_16x16 aom_highbd_d63e_predictor_16x16_c + +void aom_highbd_d63e_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_16x32 aom_highbd_d63e_predictor_16x32_c + +void aom_highbd_d63e_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_16x8 aom_highbd_d63e_predictor_16x8_c + +void aom_highbd_d63e_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_2x2 aom_highbd_d63e_predictor_2x2_c + +void aom_highbd_d63e_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_32x16 aom_highbd_d63e_predictor_32x16_c + +void aom_highbd_d63e_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_32x32 aom_highbd_d63e_predictor_32x32_c + +void aom_highbd_d63e_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_4x4 aom_highbd_d63e_predictor_4x4_c + +void aom_highbd_d63e_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_4x8 aom_highbd_d63e_predictor_4x8_c + +void aom_highbd_d63e_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_8x16 aom_highbd_d63e_predictor_8x16_c + +void aom_highbd_d63e_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_8x4 aom_highbd_d63e_predictor_8x4_c + +void aom_highbd_d63e_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_d63e_predictor_8x8 aom_highbd_d63e_predictor_8x8_c + +void aom_highbd_dc_128_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_16x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_16x16 aom_highbd_dc_128_predictor_16x16_sse2 + +void aom_highbd_dc_128_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_16x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_16x32 aom_highbd_dc_128_predictor_16x32_sse2 + +void aom_highbd_dc_128_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_16x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_16x8 aom_highbd_dc_128_predictor_16x8_sse2 + +void aom_highbd_dc_128_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_2x2 aom_highbd_dc_128_predictor_2x2_c + +void aom_highbd_dc_128_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_32x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_32x16 aom_highbd_dc_128_predictor_32x16_sse2 + +void aom_highbd_dc_128_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_32x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_32x32 aom_highbd_dc_128_predictor_32x32_sse2 + +void aom_highbd_dc_128_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_4x4 aom_highbd_dc_128_predictor_4x4_sse2 + +void aom_highbd_dc_128_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_4x8 aom_highbd_dc_128_predictor_4x8_sse2 + +void aom_highbd_dc_128_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_8x16 aom_highbd_dc_128_predictor_8x16_sse2 + +void aom_highbd_dc_128_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_8x4 aom_highbd_dc_128_predictor_8x4_sse2 + +void aom_highbd_dc_128_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_128_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_128_predictor_8x8 aom_highbd_dc_128_predictor_8x8_sse2 + +void aom_highbd_dc_left_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_16x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_16x16 aom_highbd_dc_left_predictor_16x16_sse2 + +void aom_highbd_dc_left_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_16x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_16x32 aom_highbd_dc_left_predictor_16x32_sse2 + +void aom_highbd_dc_left_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_16x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_16x8 aom_highbd_dc_left_predictor_16x8_sse2 + +void aom_highbd_dc_left_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_2x2 aom_highbd_dc_left_predictor_2x2_c + +void aom_highbd_dc_left_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_32x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_32x16 aom_highbd_dc_left_predictor_32x16_sse2 + +void aom_highbd_dc_left_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_32x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_32x32 aom_highbd_dc_left_predictor_32x32_sse2 + +void aom_highbd_dc_left_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_4x4 aom_highbd_dc_left_predictor_4x4_sse2 + +void aom_highbd_dc_left_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_4x8 aom_highbd_dc_left_predictor_4x8_sse2 + +void aom_highbd_dc_left_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_8x16 aom_highbd_dc_left_predictor_8x16_sse2 + +void aom_highbd_dc_left_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_8x4 aom_highbd_dc_left_predictor_8x4_sse2 + +void aom_highbd_dc_left_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_left_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_left_predictor_8x8 aom_highbd_dc_left_predictor_8x8_sse2 + +void aom_highbd_dc_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_16x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_16x16 aom_highbd_dc_predictor_16x16_sse2 + +void aom_highbd_dc_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_16x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_16x32 aom_highbd_dc_predictor_16x32_sse2 + +void aom_highbd_dc_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_16x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_16x8 aom_highbd_dc_predictor_16x8_sse2 + +void aom_highbd_dc_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_2x2 aom_highbd_dc_predictor_2x2_c + +void aom_highbd_dc_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_32x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_32x16 aom_highbd_dc_predictor_32x16_sse2 + +void aom_highbd_dc_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_32x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_32x32 aom_highbd_dc_predictor_32x32_sse2 + +void aom_highbd_dc_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_4x4 aom_highbd_dc_predictor_4x4_sse2 + +void aom_highbd_dc_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_4x8 aom_highbd_dc_predictor_4x8_sse2 + +void aom_highbd_dc_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_8x16 aom_highbd_dc_predictor_8x16_sse2 + +void aom_highbd_dc_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_8x4 aom_highbd_dc_predictor_8x4_sse2 + +void aom_highbd_dc_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_predictor_8x8 aom_highbd_dc_predictor_8x8_sse2 + +void aom_highbd_dc_top_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_16x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_16x16 aom_highbd_dc_top_predictor_16x16_sse2 + +void aom_highbd_dc_top_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_16x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_16x32 aom_highbd_dc_top_predictor_16x32_sse2 + +void aom_highbd_dc_top_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_16x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_16x8 aom_highbd_dc_top_predictor_16x8_sse2 + +void aom_highbd_dc_top_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_2x2 aom_highbd_dc_top_predictor_2x2_c + +void aom_highbd_dc_top_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_32x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_32x16 aom_highbd_dc_top_predictor_32x16_sse2 + +void aom_highbd_dc_top_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_32x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_32x32 aom_highbd_dc_top_predictor_32x32_sse2 + +void aom_highbd_dc_top_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_4x4 aom_highbd_dc_top_predictor_4x4_sse2 + +void aom_highbd_dc_top_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_4x8 aom_highbd_dc_top_predictor_4x8_sse2 + +void aom_highbd_dc_top_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_8x16 aom_highbd_dc_top_predictor_8x16_sse2 + +void aom_highbd_dc_top_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_8x4 aom_highbd_dc_top_predictor_8x4_sse2 + +void aom_highbd_dc_top_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_dc_top_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_dc_top_predictor_8x8 aom_highbd_dc_top_predictor_8x8_sse2 + +void aom_highbd_fdct16x16_c(const int16_t *input, tran_low_t *output, int stride); +void aom_highbd_fdct16x16_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_highbd_fdct16x16 aom_highbd_fdct16x16_sse2 + +void aom_highbd_fdct32x32_c(const int16_t *input, tran_low_t *output, int stride); +void aom_highbd_fdct32x32_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_highbd_fdct32x32 aom_highbd_fdct32x32_sse2 + +void aom_highbd_fdct32x32_rd_c(const int16_t *input, tran_low_t *output, int stride); +void aom_highbd_fdct32x32_rd_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_highbd_fdct32x32_rd aom_highbd_fdct32x32_rd_sse2 + +void aom_highbd_fdct4x4_c(const int16_t *input, tran_low_t *output, int stride); +void aom_highbd_fdct4x4_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_highbd_fdct4x4 aom_highbd_fdct4x4_sse2 + +void aom_highbd_fdct8x8_c(const int16_t *input, tran_low_t *output, int stride); +void aom_highbd_fdct8x8_sse2(const int16_t *input, tran_low_t *output, int stride); +#define aom_highbd_fdct8x8 aom_highbd_fdct8x8_sse2 + +void aom_highbd_h_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_16x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_16x16 aom_highbd_h_predictor_16x16_sse2 + +void aom_highbd_h_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_16x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_16x32 aom_highbd_h_predictor_16x32_sse2 + +void aom_highbd_h_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_16x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_16x8 aom_highbd_h_predictor_16x8_sse2 + +void aom_highbd_h_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_2x2 aom_highbd_h_predictor_2x2_c + +void aom_highbd_h_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_32x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_32x16 aom_highbd_h_predictor_32x16_sse2 + +void aom_highbd_h_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_32x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_32x32 aom_highbd_h_predictor_32x32_sse2 + +void aom_highbd_h_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_4x4 aom_highbd_h_predictor_4x4_sse2 + +void aom_highbd_h_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_4x8 aom_highbd_h_predictor_4x8_sse2 + +void aom_highbd_h_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_8x16 aom_highbd_h_predictor_8x16_sse2 + +void aom_highbd_h_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_8x4 aom_highbd_h_predictor_8x4_sse2 + +void aom_highbd_h_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_h_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_h_predictor_8x8 aom_highbd_h_predictor_8x8_sse2 + +void aom_highbd_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd); +#define aom_highbd_iwht4x4_16_add aom_highbd_iwht4x4_16_add_c + +void aom_highbd_iwht4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, int bd); +#define aom_highbd_iwht4x4_1_add aom_highbd_iwht4x4_1_add_c + +void aom_highbd_lpf_horizontal_4_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_horizontal_4_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +#define aom_highbd_lpf_horizontal_4 aom_highbd_lpf_horizontal_4_sse2 + +void aom_highbd_lpf_horizontal_4_dual_c(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_horizontal_4_dual_sse2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_horizontal_4_dual_avx2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +RTCD_EXTERN void (*aom_highbd_lpf_horizontal_4_dual)(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); + +void aom_highbd_lpf_horizontal_8_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_horizontal_8_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +#define aom_highbd_lpf_horizontal_8 aom_highbd_lpf_horizontal_8_sse2 + +void aom_highbd_lpf_horizontal_8_dual_c(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_horizontal_8_dual_sse2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_horizontal_8_dual_avx2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +RTCD_EXTERN void (*aom_highbd_lpf_horizontal_8_dual)(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); + +void aom_highbd_lpf_horizontal_edge_16_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_horizontal_edge_16_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_horizontal_edge_16_avx2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +RTCD_EXTERN void (*aom_highbd_lpf_horizontal_edge_16)(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); + +void aom_highbd_lpf_horizontal_edge_8_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_horizontal_edge_8_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +#define aom_highbd_lpf_horizontal_edge_8 aom_highbd_lpf_horizontal_edge_8_sse2 + +void aom_highbd_lpf_vertical_16_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_vertical_16_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +#define aom_highbd_lpf_vertical_16 aom_highbd_lpf_vertical_16_sse2 + +void aom_highbd_lpf_vertical_16_dual_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_vertical_16_dual_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_vertical_16_dual_avx2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +RTCD_EXTERN void (*aom_highbd_lpf_vertical_16_dual)(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); + +void aom_highbd_lpf_vertical_4_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_vertical_4_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +#define aom_highbd_lpf_vertical_4 aom_highbd_lpf_vertical_4_sse2 + +void aom_highbd_lpf_vertical_4_dual_c(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_vertical_4_dual_sse2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_vertical_4_dual_avx2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +RTCD_EXTERN void (*aom_highbd_lpf_vertical_4_dual)(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); + +void aom_highbd_lpf_vertical_8_c(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +void aom_highbd_lpf_vertical_8_sse2(uint16_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh, int bd); +#define aom_highbd_lpf_vertical_8 aom_highbd_lpf_vertical_8_sse2 + +void aom_highbd_lpf_vertical_8_dual_c(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_vertical_8_dual_sse2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +void aom_highbd_lpf_vertical_8_dual_avx2(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); +RTCD_EXTERN void (*aom_highbd_lpf_vertical_8_dual)(uint16_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1, int bd); + +unsigned int aom_highbd_masked_sad16x16_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad16x16_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad16x16)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad16x32_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad16x32_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad16x32)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad16x8_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad16x8_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad16x8)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad32x16_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad32x16_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad32x16)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad32x32_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad32x32_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad32x32)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad32x64_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad32x64_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad32x64)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad4x4_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad4x4_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad4x4)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad4x8_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad4x8_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad4x8)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad64x32_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad64x32_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad64x32)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad64x64_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad64x64_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad64x64)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad8x16_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad8x16_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad8x16)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad8x4_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad8x4_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad8x4)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_highbd_masked_sad8x8_c(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_highbd_masked_sad8x8_ssse3(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_highbd_masked_sad8x8)(const uint8_t *src8, int src_stride, const uint8_t *ref8, int ref_stride, const uint8_t *second_pred8, const uint8_t *msk, int msk_stride, int invert_mask); + +void aom_highbd_minmax_8x8_c(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max); +#define aom_highbd_minmax_8x8 aom_highbd_minmax_8x8_c + +unsigned int aom_highbd_obmc_sad16x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad16x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad16x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad16x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad16x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad16x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad16x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad16x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad16x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad32x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad32x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad32x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad32x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad32x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad32x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad32x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad32x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad32x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad4x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad4x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad4x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad4x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad4x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad4x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad64x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad64x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad64x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad64x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad64x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad64x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad8x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad8x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad8x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad8x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad8x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad8x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sad8x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_highbd_obmc_sad8x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_sad8x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_highbd_obmc_sub_pixel_variance16x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance16x16 aom_highbd_obmc_sub_pixel_variance16x16_c + +unsigned int aom_highbd_obmc_sub_pixel_variance16x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance16x32 aom_highbd_obmc_sub_pixel_variance16x32_c + +unsigned int aom_highbd_obmc_sub_pixel_variance16x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance16x8 aom_highbd_obmc_sub_pixel_variance16x8_c + +unsigned int aom_highbd_obmc_sub_pixel_variance32x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance32x16 aom_highbd_obmc_sub_pixel_variance32x16_c + +unsigned int aom_highbd_obmc_sub_pixel_variance32x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance32x32 aom_highbd_obmc_sub_pixel_variance32x32_c + +unsigned int aom_highbd_obmc_sub_pixel_variance32x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance32x64 aom_highbd_obmc_sub_pixel_variance32x64_c + +unsigned int aom_highbd_obmc_sub_pixel_variance4x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance4x4 aom_highbd_obmc_sub_pixel_variance4x4_c + +unsigned int aom_highbd_obmc_sub_pixel_variance4x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance4x8 aom_highbd_obmc_sub_pixel_variance4x8_c + +unsigned int aom_highbd_obmc_sub_pixel_variance64x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance64x32 aom_highbd_obmc_sub_pixel_variance64x32_c + +unsigned int aom_highbd_obmc_sub_pixel_variance64x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance64x64 aom_highbd_obmc_sub_pixel_variance64x64_c + +unsigned int aom_highbd_obmc_sub_pixel_variance8x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance8x16 aom_highbd_obmc_sub_pixel_variance8x16_c + +unsigned int aom_highbd_obmc_sub_pixel_variance8x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance8x4 aom_highbd_obmc_sub_pixel_variance8x4_c + +unsigned int aom_highbd_obmc_sub_pixel_variance8x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_highbd_obmc_sub_pixel_variance8x8 aom_highbd_obmc_sub_pixel_variance8x8_c + +unsigned int aom_highbd_obmc_variance16x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance16x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance16x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance16x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance16x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance16x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance16x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance16x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance16x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance32x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance32x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance32x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance32x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance32x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance32x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance32x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance32x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance32x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance4x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance4x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance4x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance4x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance4x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance4x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance64x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance64x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance64x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance64x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance64x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance64x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance8x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance8x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance8x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance8x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance8x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance8x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_highbd_obmc_variance8x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_highbd_obmc_variance8x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_highbd_obmc_variance8x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +void aom_highbd_paeth_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_16x16 aom_highbd_paeth_predictor_16x16_c + +void aom_highbd_paeth_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_16x32 aom_highbd_paeth_predictor_16x32_c + +void aom_highbd_paeth_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_16x8 aom_highbd_paeth_predictor_16x8_c + +void aom_highbd_paeth_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_2x2 aom_highbd_paeth_predictor_2x2_c + +void aom_highbd_paeth_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_32x16 aom_highbd_paeth_predictor_32x16_c + +void aom_highbd_paeth_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_32x32 aom_highbd_paeth_predictor_32x32_c + +void aom_highbd_paeth_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_4x4 aom_highbd_paeth_predictor_4x4_c + +void aom_highbd_paeth_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_4x8 aom_highbd_paeth_predictor_4x8_c + +void aom_highbd_paeth_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_8x16 aom_highbd_paeth_predictor_8x16_c + +void aom_highbd_paeth_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_8x4 aom_highbd_paeth_predictor_8x4_c + +void aom_highbd_paeth_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_paeth_predictor_8x8 aom_highbd_paeth_predictor_8x8_c + +void aom_highbd_quantize_b_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_highbd_quantize_b_sse2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_highbd_quantize_b_avx2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*aom_highbd_quantize_b)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void aom_highbd_quantize_b_32x32_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_highbd_quantize_b_32x32_sse2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +#define aom_highbd_quantize_b_32x32 aom_highbd_quantize_b_32x32_sse2 + +void aom_highbd_quantize_b_64x64_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +#define aom_highbd_quantize_b_64x64 aom_highbd_quantize_b_64x64_c + +unsigned int aom_highbd_sad16x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad16x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad16x16_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad16x16)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad16x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad16x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad16x16_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad16x16_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad16x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad16x16x3 aom_highbd_sad16x16x3_c + +void aom_highbd_sad16x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad16x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad16x16x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad16x16x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void aom_highbd_sad16x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad16x16x8 aom_highbd_sad16x16x8_c + +unsigned int aom_highbd_sad16x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad16x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad16x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad16x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad16x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad16x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad16x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad16x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad16x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad16x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad16x32x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad16x32x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +unsigned int aom_highbd_sad16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad16x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad16x8_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad16x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad16x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad16x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad16x8_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad16x8_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad16x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad16x8x3 aom_highbd_sad16x8x3_c + +void aom_highbd_sad16x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad16x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad16x8x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad16x8x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void aom_highbd_sad16x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad16x8x8 aom_highbd_sad16x8x8_c + +unsigned int aom_highbd_sad32x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad32x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad32x16_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad32x16)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad32x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad32x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad32x16_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad32x16_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad32x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad32x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad32x16x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad32x16x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +unsigned int aom_highbd_sad32x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad32x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad32x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad32x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad32x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad32x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad32x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad32x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad32x32x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad32x32x3 aom_highbd_sad32x32x3_c + +void aom_highbd_sad32x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad32x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad32x32x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad32x32x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void aom_highbd_sad32x32x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad32x32x8 aom_highbd_sad32x32x8_c + +unsigned int aom_highbd_sad32x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad32x64_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad32x64_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad32x64)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad32x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad32x64_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad32x64_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad32x64_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad32x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad32x64x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad32x64x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad32x64x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +unsigned int aom_highbd_sad4x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_highbd_sad4x4 aom_highbd_sad4x4_c + +unsigned int aom_highbd_sad4x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_highbd_sad4x4_avg aom_highbd_sad4x4_avg_c + +void aom_highbd_sad4x4x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad4x4x3 aom_highbd_sad4x4x3_c + +void aom_highbd_sad4x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad4x4x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad4x4x4d aom_highbd_sad4x4x4d_sse2 + +void aom_highbd_sad4x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad4x4x8 aom_highbd_sad4x4x8_c + +unsigned int aom_highbd_sad4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_highbd_sad4x8 aom_highbd_sad4x8_c + +unsigned int aom_highbd_sad4x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_highbd_sad4x8_avg aom_highbd_sad4x8_avg_c + +void aom_highbd_sad4x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad4x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad4x8x4d aom_highbd_sad4x8x4d_sse2 + +void aom_highbd_sad4x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad4x8x8 aom_highbd_sad4x8x8_c + +unsigned int aom_highbd_sad64x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad64x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad64x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad64x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad64x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad64x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad64x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad64x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad64x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad64x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad64x32x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad64x32x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +unsigned int aom_highbd_sad64x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad64x64_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad64x64_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_highbd_sad64x64)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_highbd_sad64x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad64x64_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad64x64_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_highbd_sad64x64_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_highbd_sad64x64x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad64x64x3 aom_highbd_sad64x64x3_c + +void aom_highbd_sad64x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad64x64x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad64x64x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_highbd_sad64x64x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void aom_highbd_sad64x64x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad64x64x8 aom_highbd_sad64x64x8_c + +unsigned int aom_highbd_sad8x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad8x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_highbd_sad8x16 aom_highbd_sad8x16_sse2 + +unsigned int aom_highbd_sad8x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad8x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_highbd_sad8x16_avg aom_highbd_sad8x16_avg_sse2 + +void aom_highbd_sad8x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x16x3 aom_highbd_sad8x16x3_c + +void aom_highbd_sad8x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad8x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x16x4d aom_highbd_sad8x16x4d_sse2 + +void aom_highbd_sad8x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x16x8 aom_highbd_sad8x16x8_c + +unsigned int aom_highbd_sad8x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad8x4_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_highbd_sad8x4 aom_highbd_sad8x4_sse2 + +unsigned int aom_highbd_sad8x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad8x4_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_highbd_sad8x4_avg aom_highbd_sad8x4_avg_sse2 + +void aom_highbd_sad8x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad8x4x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x4x4d aom_highbd_sad8x4x4d_sse2 + +void aom_highbd_sad8x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x4x8 aom_highbd_sad8x4x8_c + +unsigned int aom_highbd_sad8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_highbd_sad8x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_highbd_sad8x8 aom_highbd_sad8x8_sse2 + +unsigned int aom_highbd_sad8x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_highbd_sad8x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_highbd_sad8x8_avg aom_highbd_sad8x8_avg_sse2 + +void aom_highbd_sad8x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x8x3 aom_highbd_sad8x8x3_c + +void aom_highbd_sad8x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_highbd_sad8x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x8x4d aom_highbd_sad8x8x4d_sse2 + +void aom_highbd_sad8x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_highbd_sad8x8x8 aom_highbd_sad8x8x8_c + +void aom_highbd_smooth_h_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_16x16 aom_highbd_smooth_h_predictor_16x16_c + +void aom_highbd_smooth_h_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_16x32 aom_highbd_smooth_h_predictor_16x32_c + +void aom_highbd_smooth_h_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_16x8 aom_highbd_smooth_h_predictor_16x8_c + +void aom_highbd_smooth_h_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_2x2 aom_highbd_smooth_h_predictor_2x2_c + +void aom_highbd_smooth_h_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_32x16 aom_highbd_smooth_h_predictor_32x16_c + +void aom_highbd_smooth_h_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_32x32 aom_highbd_smooth_h_predictor_32x32_c + +void aom_highbd_smooth_h_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_4x4 aom_highbd_smooth_h_predictor_4x4_c + +void aom_highbd_smooth_h_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_4x8 aom_highbd_smooth_h_predictor_4x8_c + +void aom_highbd_smooth_h_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_8x16 aom_highbd_smooth_h_predictor_8x16_c + +void aom_highbd_smooth_h_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_8x4 aom_highbd_smooth_h_predictor_8x4_c + +void aom_highbd_smooth_h_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_h_predictor_8x8 aom_highbd_smooth_h_predictor_8x8_c + +void aom_highbd_smooth_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_16x16 aom_highbd_smooth_predictor_16x16_c + +void aom_highbd_smooth_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_16x32 aom_highbd_smooth_predictor_16x32_c + +void aom_highbd_smooth_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_16x8 aom_highbd_smooth_predictor_16x8_c + +void aom_highbd_smooth_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_2x2 aom_highbd_smooth_predictor_2x2_c + +void aom_highbd_smooth_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_32x16 aom_highbd_smooth_predictor_32x16_c + +void aom_highbd_smooth_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_32x32 aom_highbd_smooth_predictor_32x32_c + +void aom_highbd_smooth_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_4x4 aom_highbd_smooth_predictor_4x4_c + +void aom_highbd_smooth_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_4x8 aom_highbd_smooth_predictor_4x8_c + +void aom_highbd_smooth_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_8x16 aom_highbd_smooth_predictor_8x16_c + +void aom_highbd_smooth_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_8x4 aom_highbd_smooth_predictor_8x4_c + +void aom_highbd_smooth_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_predictor_8x8 aom_highbd_smooth_predictor_8x8_c + +void aom_highbd_smooth_v_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_16x16 aom_highbd_smooth_v_predictor_16x16_c + +void aom_highbd_smooth_v_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_16x32 aom_highbd_smooth_v_predictor_16x32_c + +void aom_highbd_smooth_v_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_16x8 aom_highbd_smooth_v_predictor_16x8_c + +void aom_highbd_smooth_v_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_2x2 aom_highbd_smooth_v_predictor_2x2_c + +void aom_highbd_smooth_v_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_32x16 aom_highbd_smooth_v_predictor_32x16_c + +void aom_highbd_smooth_v_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_32x32 aom_highbd_smooth_v_predictor_32x32_c + +void aom_highbd_smooth_v_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_4x4 aom_highbd_smooth_v_predictor_4x4_c + +void aom_highbd_smooth_v_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_4x8 aom_highbd_smooth_v_predictor_4x8_c + +void aom_highbd_smooth_v_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_8x16 aom_highbd_smooth_v_predictor_8x16_c + +void aom_highbd_smooth_v_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_8x4 aom_highbd_smooth_v_predictor_8x4_c + +void aom_highbd_smooth_v_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_smooth_v_predictor_8x8 aom_highbd_smooth_v_predictor_8x8_c + +void aom_highbd_subtract_block_c(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride, int bd); +void aom_highbd_subtract_block_sse2(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride, int bd); +#define aom_highbd_subtract_block aom_highbd_subtract_block_sse2 + +void aom_highbd_upsampled_pred_c(uint16_t *comp_pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref8, int ref_stride, int bd); +void aom_highbd_upsampled_pred_sse2(uint16_t *comp_pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref8, int ref_stride, int bd); +#define aom_highbd_upsampled_pred aom_highbd_upsampled_pred_sse2 + +void aom_highbd_v_predictor_16x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_16x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_16x16 aom_highbd_v_predictor_16x16_sse2 + +void aom_highbd_v_predictor_16x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_16x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_16x32 aom_highbd_v_predictor_16x32_sse2 + +void aom_highbd_v_predictor_16x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_16x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_16x8 aom_highbd_v_predictor_16x8_sse2 + +void aom_highbd_v_predictor_2x2_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_2x2 aom_highbd_v_predictor_2x2_c + +void aom_highbd_v_predictor_32x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_32x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_32x16 aom_highbd_v_predictor_32x16_sse2 + +void aom_highbd_v_predictor_32x32_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_32x32_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_32x32 aom_highbd_v_predictor_32x32_sse2 + +void aom_highbd_v_predictor_4x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_4x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_4x4 aom_highbd_v_predictor_4x4_sse2 + +void aom_highbd_v_predictor_4x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_4x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_4x8 aom_highbd_v_predictor_4x8_sse2 + +void aom_highbd_v_predictor_8x16_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_8x16_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_8x16 aom_highbd_v_predictor_8x16_sse2 + +void aom_highbd_v_predictor_8x4_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_8x4_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_8x4 aom_highbd_v_predictor_8x4_sse2 + +void aom_highbd_v_predictor_8x8_c(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +void aom_highbd_v_predictor_8x8_sse2(uint16_t *dst, ptrdiff_t y_stride, const uint16_t *above, const uint16_t *left, int bd); +#define aom_highbd_v_predictor_8x8 aom_highbd_v_predictor_8x8_sse2 + +void aom_idct16x16_10_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_10_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_10_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct16x16_10_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct16x16_1_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_1_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_1_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct16x16_1_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct16x16_256_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_256_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_256_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct16x16_256_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct16x16_38_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct16x16_38_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct16x16_38_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct32x32_1024_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_1024_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_1024_add_ssse3(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_1024_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct32x32_1024_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct32x32_135_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_1024_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_135_add_ssse3(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_135_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct32x32_135_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct32x32_1_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_1_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_1_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct32x32_1_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct32x32_34_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_34_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_34_add_ssse3(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct32x32_34_add_avx2(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct32x32_34_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct4x4_16_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +#define aom_idct4x4_16_add aom_idct4x4_16_add_sse2 + +void aom_idct4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct4x4_1_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +#define aom_idct4x4_1_add aom_idct4x4_1_add_sse2 + +void aom_idct8x8_12_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct8x8_12_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct8x8_12_add_ssse3(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct8x8_12_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +void aom_idct8x8_1_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct8x8_1_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +#define aom_idct8x8_1_add aom_idct8x8_1_add_sse2 + +void aom_idct8x8_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct8x8_64_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_idct8x8_64_add_ssse3(const tran_low_t *input, uint8_t *dest, int dest_stride); +RTCD_EXTERN void (*aom_idct8x8_64_add)(const tran_low_t *input, uint8_t *dest, int dest_stride); + +int16_t aom_int_pro_col_c(const uint8_t *ref, int width); +int16_t aom_int_pro_col_sse2(const uint8_t *ref, int width); +#define aom_int_pro_col aom_int_pro_col_sse2 + +void aom_int_pro_row_c(int16_t *hbuf, const uint8_t *ref, int ref_stride, int height); +void aom_int_pro_row_sse2(int16_t *hbuf, const uint8_t *ref, int ref_stride, int height); +#define aom_int_pro_row aom_int_pro_row_sse2 + +void aom_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +void aom_iwht4x4_16_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride); +#define aom_iwht4x4_16_add aom_iwht4x4_16_add_sse2 + +void aom_iwht4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride); +#define aom_iwht4x4_1_add aom_iwht4x4_1_add_c + +void aom_lpf_horizontal_4_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_horizontal_4_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_horizontal_4 aom_lpf_horizontal_4_sse2 + +void aom_lpf_horizontal_4_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define aom_lpf_horizontal_4_dual aom_lpf_horizontal_4_dual_c + +void aom_lpf_horizontal_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_horizontal_8_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_horizontal_8 aom_lpf_horizontal_8_sse2 + +void aom_lpf_horizontal_8_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define aom_lpf_horizontal_8_dual aom_lpf_horizontal_8_dual_c + +void aom_lpf_horizontal_edge_16_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_horizontal_edge_16_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_horizontal_edge_16 aom_lpf_horizontal_edge_16_sse2 + +void aom_lpf_horizontal_edge_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_horizontal_edge_8_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_horizontal_edge_8 aom_lpf_horizontal_edge_8_sse2 + +void aom_lpf_vertical_16_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_vertical_16_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_vertical_16 aom_lpf_vertical_16_sse2 + +void aom_lpf_vertical_16_dual_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_vertical_16_dual aom_lpf_vertical_16_dual_c + +void aom_lpf_vertical_4_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_vertical_4_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_vertical_4 aom_lpf_vertical_4_sse2 + +void aom_lpf_vertical_4_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define aom_lpf_vertical_4_dual aom_lpf_vertical_4_dual_c + +void aom_lpf_vertical_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void aom_lpf_vertical_8_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define aom_lpf_vertical_8 aom_lpf_vertical_8_sse2 + +void aom_lpf_vertical_8_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define aom_lpf_vertical_8_dual aom_lpf_vertical_8_dual_c + +unsigned int aom_masked_sad16x16_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad16x16_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad16x16)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad16x32_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad16x32_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad16x32)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad16x8_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad16x8_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad16x8)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad32x16_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad32x16_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad32x16)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad32x32_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad32x32_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad32x32)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad32x64_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad32x64_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad32x64)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad4x4_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad4x4_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad4x4)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad4x8_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad4x8_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad4x8)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad64x32_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad64x32_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad64x32)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad64x64_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad64x64_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad64x64)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad8x16_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad8x16_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad8x16)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad8x4_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad8x4_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad8x4)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sad8x8_c(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +unsigned int aom_masked_sad8x8_ssse3(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); +RTCD_EXTERN unsigned int (*aom_masked_sad8x8)(const uint8_t *src, int src_stride, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask); + +unsigned int aom_masked_sub_pixel_variance16x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance16x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance16x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance16x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance16x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance16x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance16x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance16x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance16x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance32x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance32x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance32x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance32x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance32x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance32x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance32x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance32x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance32x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance4x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance4x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance4x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance4x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance4x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance4x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance64x32_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance64x32_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance64x32)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance64x64_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance64x64_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance64x64)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance8x16_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance8x16_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance8x16)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance8x4_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance8x4_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance8x4)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +unsigned int aom_masked_sub_pixel_variance8x8_c(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +unsigned int aom_masked_sub_pixel_variance8x8_ssse3(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_masked_sub_pixel_variance8x8)(const uint8_t *src, int src_stride, int xoffset, int yoffset, const uint8_t *ref, int ref_stride, const uint8_t *second_pred, const uint8_t *msk, int msk_stride, int invert_mask, unsigned int *sse); + +void aom_minmax_8x8_c(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max); +void aom_minmax_8x8_sse2(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max); +#define aom_minmax_8x8 aom_minmax_8x8_sse2 + +unsigned int aom_mse16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_mse16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_mse16x16_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_mse16x16)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); + +unsigned int aom_mse16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_mse16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_mse16x8 aom_mse16x8_sse2 + +unsigned int aom_mse8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_mse8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_mse8x16 aom_mse8x16_sse2 + +unsigned int aom_mse8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int aom_mse8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define aom_mse8x8 aom_mse8x8_sse2 + +unsigned int aom_obmc_sad16x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad16x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad16x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad16x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad16x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad16x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad16x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad16x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad16x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad32x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad32x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad32x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad32x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad32x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad32x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad32x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad32x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad32x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad4x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad4x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad4x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad4x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad4x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad4x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad64x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad64x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad64x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad64x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad64x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad64x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad8x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad8x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad8x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad8x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad8x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad8x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sad8x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +unsigned int aom_obmc_sad8x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); +RTCD_EXTERN unsigned int (*aom_obmc_sad8x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask); + +unsigned int aom_obmc_sub_pixel_variance16x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance16x16 aom_obmc_sub_pixel_variance16x16_c + +unsigned int aom_obmc_sub_pixel_variance16x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance16x32 aom_obmc_sub_pixel_variance16x32_c + +unsigned int aom_obmc_sub_pixel_variance16x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance16x8 aom_obmc_sub_pixel_variance16x8_c + +unsigned int aom_obmc_sub_pixel_variance32x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance32x16 aom_obmc_sub_pixel_variance32x16_c + +unsigned int aom_obmc_sub_pixel_variance32x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance32x32 aom_obmc_sub_pixel_variance32x32_c + +unsigned int aom_obmc_sub_pixel_variance32x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance32x64 aom_obmc_sub_pixel_variance32x64_c + +unsigned int aom_obmc_sub_pixel_variance4x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance4x4 aom_obmc_sub_pixel_variance4x4_c + +unsigned int aom_obmc_sub_pixel_variance4x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance4x8 aom_obmc_sub_pixel_variance4x8_c + +unsigned int aom_obmc_sub_pixel_variance64x32_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance64x32 aom_obmc_sub_pixel_variance64x32_c + +unsigned int aom_obmc_sub_pixel_variance64x64_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance64x64 aom_obmc_sub_pixel_variance64x64_c + +unsigned int aom_obmc_sub_pixel_variance8x16_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance8x16 aom_obmc_sub_pixel_variance8x16_c + +unsigned int aom_obmc_sub_pixel_variance8x4_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance8x4 aom_obmc_sub_pixel_variance8x4_c + +unsigned int aom_obmc_sub_pixel_variance8x8_c(const uint8_t *pre, int pre_stride, int xoffset, int yoffset, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +#define aom_obmc_sub_pixel_variance8x8 aom_obmc_sub_pixel_variance8x8_c + +unsigned int aom_obmc_variance16x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance16x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance16x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance16x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance16x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance16x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance16x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance16x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance16x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance32x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance32x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance32x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance32x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance32x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance32x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance32x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance32x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance32x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance4x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance4x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance4x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance4x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance4x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance4x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance64x32_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance64x32_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance64x32)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance64x64_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance64x64_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance64x64)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance8x16_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance8x16_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance8x16)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance8x4_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance8x4_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance8x4)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +unsigned int aom_obmc_variance8x8_c(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +unsigned int aom_obmc_variance8x8_sse4_1(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_obmc_variance8x8)(const uint8_t *pre, int pre_stride, const int32_t *wsrc, const int32_t *mask, unsigned int *sse); + +void aom_paeth_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_16x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_16x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_16x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_16x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_16x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_16x8_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_16x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_paeth_predictor_2x2 aom_paeth_predictor_2x2_c + +void aom_paeth_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_32x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_32x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_4x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_4x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_4x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_4x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_8x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_8x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_8x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_8x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_paeth_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_paeth_predictor_8x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_paeth_predictor_8x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_quantize_b_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_quantize_b_sse2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_quantize_b_ssse3(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_quantize_b_avx(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*aom_quantize_b)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void aom_quantize_b_32x32_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_quantize_b_32x32_ssse3(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void aom_quantize_b_32x32_avx(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*aom_quantize_b_32x32)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void aom_quantize_b_64x64_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +#define aom_quantize_b_64x64 aom_quantize_b_64x64_c + +unsigned int aom_sad16x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad16x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad16x16 aom_sad16x16_sse2 + +unsigned int aom_sad16x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad16x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad16x16_avg aom_sad16x16_avg_sse2 + +void aom_sad16x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad16x16x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad16x16x3_ssse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad16x16x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void aom_sad16x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad16x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad16x16x4d aom_sad16x16x4d_sse2 + +void aom_sad16x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad16x16x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad16x16x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int aom_sad16x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad16x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad16x32 aom_sad16x32_sse2 + +unsigned int aom_sad16x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad16x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad16x32_avg aom_sad16x32_avg_sse2 + +void aom_sad16x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad16x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad16x32x4d aom_sad16x32x4d_sse2 + +unsigned int aom_sad16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad16x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad16x8 aom_sad16x8_sse2 + +unsigned int aom_sad16x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad16x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad16x8_avg aom_sad16x8_avg_sse2 + +void aom_sad16x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad16x8x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad16x8x3_ssse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad16x8x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void aom_sad16x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad16x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad16x8x4d aom_sad16x8x4d_sse2 + +void aom_sad16x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad16x8x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad16x8x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int aom_sad32x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad32x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad32x16_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_sad32x16)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_sad32x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad32x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad32x16_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_sad32x16_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_sad32x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad32x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad32x16x4d aom_sad32x16x4d_sse2 + +unsigned int aom_sad32x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad32x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad32x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_sad32x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_sad32x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad32x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad32x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_sad32x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_sad32x32x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_sad32x32x3 aom_sad32x32x3_c + +void aom_sad32x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad32x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad32x32x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad32x32x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void aom_sad32x32x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_sad32x32x8 aom_sad32x32x8_c + +unsigned int aom_sad32x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad32x64_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad32x64_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_sad32x64)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_sad32x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad32x64_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad32x64_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_sad32x64_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_sad32x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad32x64x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad32x64x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad32x64x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +unsigned int aom_sad4x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad4x4_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad4x4 aom_sad4x4_sse2 + +unsigned int aom_sad4x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad4x4_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad4x4_avg aom_sad4x4_avg_sse2 + +void aom_sad4x4x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad4x4x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad4x4x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void aom_sad4x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad4x4x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad4x4x4d aom_sad4x4x4d_sse2 + +void aom_sad4x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad4x4x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad4x4x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int aom_sad4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad4x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad4x8 aom_sad4x8_sse2 + +unsigned int aom_sad4x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad4x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad4x8_avg aom_sad4x8_avg_sse2 + +void aom_sad4x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad4x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad4x8x4d aom_sad4x8x4d_sse2 + +void aom_sad4x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_sad4x8x8 aom_sad4x8x8_c + +unsigned int aom_sad64x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad64x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad64x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_sad64x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_sad64x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad64x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad64x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_sad64x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_sad64x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad64x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad64x32x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad64x32x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +unsigned int aom_sad64x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad64x64_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad64x64_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*aom_sad64x64)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int aom_sad64x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad64x64_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad64x64_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*aom_sad64x64_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void aom_sad64x64x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_sad64x64x3 aom_sad64x64x3_c + +void aom_sad64x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad64x64x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad64x64x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad64x64x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void aom_sad64x64x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_sad64x64x8 aom_sad64x64x8_c + +unsigned int aom_sad8x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad8x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad8x16 aom_sad8x16_sse2 + +unsigned int aom_sad8x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad8x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad8x16_avg aom_sad8x16_avg_sse2 + +void aom_sad8x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad8x16x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad8x16x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void aom_sad8x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad8x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad8x16x4d aom_sad8x16x4d_sse2 + +void aom_sad8x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad8x16x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad8x16x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int aom_sad8x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad8x4_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad8x4 aom_sad8x4_sse2 + +unsigned int aom_sad8x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad8x4_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad8x4_avg aom_sad8x4_avg_sse2 + +void aom_sad8x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad8x4x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad8x4x4d aom_sad8x4x4d_sse2 + +void aom_sad8x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define aom_sad8x4x8 aom_sad8x4x8_c + +unsigned int aom_sad8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int aom_sad8x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define aom_sad8x8 aom_sad8x8_sse2 + +unsigned int aom_sad8x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int aom_sad8x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define aom_sad8x8_avg aom_sad8x8_avg_sse2 + +void aom_sad8x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad8x8x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad8x8x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void aom_sad8x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void aom_sad8x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define aom_sad8x8x4d aom_sad8x8x4d_sse2 + +void aom_sad8x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void aom_sad8x8x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*aom_sad8x8x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +int aom_satd_c(const int16_t *coeff, int length); +int aom_satd_sse2(const int16_t *coeff, int length); +#define aom_satd aom_satd_sse2 + +void aom_scaled_2d_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void aom_scaled_2d_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*aom_scaled_2d)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void aom_scaled_avg_2d_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_scaled_avg_2d aom_scaled_avg_2d_c + +void aom_scaled_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_scaled_avg_horiz aom_scaled_avg_horiz_c + +void aom_scaled_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_scaled_avg_vert aom_scaled_avg_vert_c + +void aom_scaled_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_scaled_horiz aom_scaled_horiz_c + +void aom_scaled_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define aom_scaled_vert aom_scaled_vert_c + +void aom_smooth_h_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_16x16 aom_smooth_h_predictor_16x16_c + +void aom_smooth_h_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_16x32 aom_smooth_h_predictor_16x32_c + +void aom_smooth_h_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_16x8 aom_smooth_h_predictor_16x8_c + +void aom_smooth_h_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_2x2 aom_smooth_h_predictor_2x2_c + +void aom_smooth_h_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_32x16 aom_smooth_h_predictor_32x16_c + +void aom_smooth_h_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_32x32 aom_smooth_h_predictor_32x32_c + +void aom_smooth_h_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_4x4 aom_smooth_h_predictor_4x4_c + +void aom_smooth_h_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_4x8 aom_smooth_h_predictor_4x8_c + +void aom_smooth_h_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_8x16 aom_smooth_h_predictor_8x16_c + +void aom_smooth_h_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_8x4 aom_smooth_h_predictor_8x4_c + +void aom_smooth_h_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_h_predictor_8x8 aom_smooth_h_predictor_8x8_c + +void aom_smooth_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_16x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_16x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_16x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_16x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_predictor_2x2 aom_smooth_predictor_2x2_c + +void aom_smooth_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_32x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_4x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_4x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_4x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_4x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_8x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_8x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_8x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_8x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_smooth_predictor_8x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_smooth_predictor_8x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_smooth_v_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_16x16 aom_smooth_v_predictor_16x16_c + +void aom_smooth_v_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_16x32 aom_smooth_v_predictor_16x32_c + +void aom_smooth_v_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_16x8 aom_smooth_v_predictor_16x8_c + +void aom_smooth_v_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_2x2 aom_smooth_v_predictor_2x2_c + +void aom_smooth_v_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_32x16 aom_smooth_v_predictor_32x16_c + +void aom_smooth_v_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_32x32 aom_smooth_v_predictor_32x32_c + +void aom_smooth_v_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_4x4 aom_smooth_v_predictor_4x4_c + +void aom_smooth_v_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_4x8 aom_smooth_v_predictor_4x8_c + +void aom_smooth_v_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_8x16 aom_smooth_v_predictor_8x16_c + +void aom_smooth_v_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_8x4 aom_smooth_v_predictor_8x4_c + +void aom_smooth_v_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_smooth_v_predictor_8x8 aom_smooth_v_predictor_8x8_c + +uint32_t aom_sub_pixel_avg_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance16x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance16x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance16x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance16x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance16x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance16x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance32x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x32_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance32x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance32x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance32x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance4x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance4x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance4x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance4x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance4x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance64x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance64x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance64x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance64x64_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance64x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance8x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance8x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance8x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance8x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_avg_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t aom_sub_pixel_avg_variance8x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*aom_sub_pixel_avg_variance8x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t aom_sub_pixel_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance16x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance16x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance16x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance16x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance16x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance16x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance32x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x32_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance32x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance32x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance32x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance4x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance4x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance4x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance4x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance4x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance64x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance64x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance64x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance64x64_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance64x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance8x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance8x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance8x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance8x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t aom_sub_pixel_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_sub_pixel_variance8x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*aom_sub_pixel_variance8x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +void aom_subtract_block_c(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride); +void aom_subtract_block_sse2(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride); +#define aom_subtract_block aom_subtract_block_sse2 + +uint64_t aom_sum_squares_2d_i16_c(const int16_t *src, int stride, int width, int height); +uint64_t aom_sum_squares_2d_i16_sse2(const int16_t *src, int stride, int width, int height); +#define aom_sum_squares_2d_i16 aom_sum_squares_2d_i16_sse2 + +uint64_t aom_sum_squares_i16_c(const int16_t *src, uint32_t N); +uint64_t aom_sum_squares_i16_sse2(const int16_t *src, uint32_t N); +#define aom_sum_squares_i16 aom_sum_squares_i16_sse2 + +void aom_upsampled_pred_c(uint8_t *comp_pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref, int ref_stride); +void aom_upsampled_pred_sse2(uint8_t *comp_pred, int width, int height, int subsample_x_q3, int subsample_y_q3, const uint8_t *ref, int ref_stride); +#define aom_upsampled_pred aom_upsampled_pred_sse2 + +void aom_v_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_16x16 aom_v_predictor_16x16_sse2 + +void aom_v_predictor_16x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_16x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_16x32 aom_v_predictor_16x32_sse2 + +void aom_v_predictor_16x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_16x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_16x8 aom_v_predictor_16x8_sse2 + +void aom_v_predictor_2x2_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_2x2 aom_v_predictor_2x2_c + +void aom_v_predictor_32x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_32x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_32x16_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_v_predictor_32x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_v_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_32x32_avx2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*aom_v_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void aom_v_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_4x4 aom_v_predictor_4x4_sse2 + +void aom_v_predictor_4x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_4x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_4x8 aom_v_predictor_4x8_sse2 + +void aom_v_predictor_8x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_8x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_8x16 aom_v_predictor_8x16_sse2 + +void aom_v_predictor_8x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_8x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_8x4 aom_v_predictor_8x4_sse2 + +void aom_v_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void aom_v_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define aom_v_predictor_8x8 aom_v_predictor_8x8_sse2 + +unsigned int aom_variance16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance16x16_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_variance16x16)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_variance16x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance16x32 aom_variance16x32_sse2 + +unsigned int aom_variance16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance16x8 aom_variance16x8_sse2 + +unsigned int aom_variance2x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance2x2 aom_variance2x2_c + +unsigned int aom_variance2x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance2x4 aom_variance2x4_c + +unsigned int aom_variance32x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance32x16_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_variance32x16)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_variance32x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance32x32_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_variance32x32)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_variance32x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance32x64 aom_variance32x64_sse2 + +unsigned int aom_variance4x2_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance4x2 aom_variance4x2_c + +unsigned int aom_variance4x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance4x4_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance4x4 aom_variance4x4_sse2 + +unsigned int aom_variance4x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance4x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance4x8 aom_variance4x8_sse2 + +unsigned int aom_variance64x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance64x32_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_variance64x32)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_variance64x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance64x64_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*aom_variance64x64)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int aom_variance8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance8x16 aom_variance8x16_sse2 + +unsigned int aom_variance8x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance8x4 aom_variance8x4_sse2 + +unsigned int aom_variance8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int aom_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define aom_variance8x8 aom_variance8x8_sse2 + +uint32_t aom_variance_halfpixvar16x16_h_c(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_variance_halfpixvar16x16_h_sse2(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_variance_halfpixvar16x16_h aom_variance_halfpixvar16x16_h_sse2 + +uint32_t aom_variance_halfpixvar16x16_hv_c(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_variance_halfpixvar16x16_hv_sse2(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_variance_halfpixvar16x16_hv aom_variance_halfpixvar16x16_hv_sse2 + +uint32_t aom_variance_halfpixvar16x16_v_c(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t aom_variance_halfpixvar16x16_v_sse2(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride, uint32_t *sse); +#define aom_variance_halfpixvar16x16_v aom_variance_halfpixvar16x16_v_sse2 + +int aom_vector_var_c(const int16_t *ref, const int16_t *src, int bwl); +int aom_vector_var_sse2(const int16_t *ref, const int16_t *src, int bwl); +#define aom_vector_var aom_vector_var_sse2 + +void aom_dsp_rtcd(void); + +#ifdef RTCD_C +#include "aom_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + + aom_blend_a64_hmask = aom_blend_a64_hmask_c; + if (flags & HAS_SSE4_1) aom_blend_a64_hmask = aom_blend_a64_hmask_sse4_1; + aom_blend_a64_mask = aom_blend_a64_mask_c; + if (flags & HAS_SSE4_1) aom_blend_a64_mask = aom_blend_a64_mask_sse4_1; + aom_blend_a64_vmask = aom_blend_a64_vmask_c; + if (flags & HAS_SSE4_1) aom_blend_a64_vmask = aom_blend_a64_vmask_sse4_1; + aom_convolve8 = aom_convolve8_sse2; + if (flags & HAS_SSSE3) aom_convolve8 = aom_convolve8_ssse3; + if (flags & HAS_AVX2) aom_convolve8 = aom_convolve8_avx2; + aom_convolve8_add_src = aom_convolve8_add_src_c; + if (flags & HAS_SSSE3) aom_convolve8_add_src = aom_convolve8_add_src_ssse3; + aom_convolve8_add_src_horiz = aom_convolve8_add_src_horiz_c; + if (flags & HAS_SSSE3) aom_convolve8_add_src_horiz = aom_convolve8_add_src_horiz_ssse3; + aom_convolve8_add_src_vert = aom_convolve8_add_src_vert_c; + if (flags & HAS_SSSE3) aom_convolve8_add_src_vert = aom_convolve8_add_src_vert_ssse3; + aom_convolve8_avg = aom_convolve8_avg_sse2; + if (flags & HAS_SSSE3) aom_convolve8_avg = aom_convolve8_avg_ssse3; + aom_convolve8_avg_horiz = aom_convolve8_avg_horiz_sse2; + if (flags & HAS_SSSE3) aom_convolve8_avg_horiz = aom_convolve8_avg_horiz_ssse3; + aom_convolve8_avg_vert = aom_convolve8_avg_vert_sse2; + if (flags & HAS_SSSE3) aom_convolve8_avg_vert = aom_convolve8_avg_vert_ssse3; + aom_convolve8_horiz = aom_convolve8_horiz_sse2; + if (flags & HAS_SSSE3) aom_convolve8_horiz = aom_convolve8_horiz_ssse3; + if (flags & HAS_AVX2) aom_convolve8_horiz = aom_convolve8_horiz_avx2; + aom_convolve8_vert = aom_convolve8_vert_sse2; + if (flags & HAS_SSSE3) aom_convolve8_vert = aom_convolve8_vert_ssse3; + if (flags & HAS_AVX2) aom_convolve8_vert = aom_convolve8_vert_avx2; + aom_d153_predictor_16x16 = aom_d153_predictor_16x16_c; + if (flags & HAS_SSSE3) aom_d153_predictor_16x16 = aom_d153_predictor_16x16_ssse3; + aom_d153_predictor_32x32 = aom_d153_predictor_32x32_c; + if (flags & HAS_SSSE3) aom_d153_predictor_32x32 = aom_d153_predictor_32x32_ssse3; + aom_d153_predictor_4x4 = aom_d153_predictor_4x4_c; + if (flags & HAS_SSSE3) aom_d153_predictor_4x4 = aom_d153_predictor_4x4_ssse3; + aom_d153_predictor_8x8 = aom_d153_predictor_8x8_c; + if (flags & HAS_SSSE3) aom_d153_predictor_8x8 = aom_d153_predictor_8x8_ssse3; + aom_d63e_predictor_4x4 = aom_d63e_predictor_4x4_c; + if (flags & HAS_SSSE3) aom_d63e_predictor_4x4 = aom_d63e_predictor_4x4_ssse3; + aom_dc_128_predictor_32x16 = aom_dc_128_predictor_32x16_sse2; + if (flags & HAS_AVX2) aom_dc_128_predictor_32x16 = aom_dc_128_predictor_32x16_avx2; + aom_dc_128_predictor_32x32 = aom_dc_128_predictor_32x32_sse2; + if (flags & HAS_AVX2) aom_dc_128_predictor_32x32 = aom_dc_128_predictor_32x32_avx2; + aom_dc_left_predictor_32x16 = aom_dc_left_predictor_32x16_sse2; + if (flags & HAS_AVX2) aom_dc_left_predictor_32x16 = aom_dc_left_predictor_32x16_avx2; + aom_dc_left_predictor_32x32 = aom_dc_left_predictor_32x32_sse2; + if (flags & HAS_AVX2) aom_dc_left_predictor_32x32 = aom_dc_left_predictor_32x32_avx2; + aom_dc_predictor_32x16 = aom_dc_predictor_32x16_sse2; + if (flags & HAS_AVX2) aom_dc_predictor_32x16 = aom_dc_predictor_32x16_avx2; + aom_dc_predictor_32x32 = aom_dc_predictor_32x32_sse2; + if (flags & HAS_AVX2) aom_dc_predictor_32x32 = aom_dc_predictor_32x32_avx2; + aom_dc_top_predictor_32x16 = aom_dc_top_predictor_32x16_sse2; + if (flags & HAS_AVX2) aom_dc_top_predictor_32x16 = aom_dc_top_predictor_32x16_avx2; + aom_dc_top_predictor_32x32 = aom_dc_top_predictor_32x32_sse2; + if (flags & HAS_AVX2) aom_dc_top_predictor_32x32 = aom_dc_top_predictor_32x32_avx2; + aom_fdct32x32 = aom_fdct32x32_sse2; + if (flags & HAS_AVX2) aom_fdct32x32 = aom_fdct32x32_avx2; + aom_fdct32x32_rd = aom_fdct32x32_rd_sse2; + if (flags & HAS_AVX2) aom_fdct32x32_rd = aom_fdct32x32_rd_avx2; + aom_fdct8x8 = aom_fdct8x8_sse2; + if (flags & HAS_SSSE3) aom_fdct8x8 = aom_fdct8x8_ssse3; + aom_get16x16var = aom_get16x16var_sse2; + if (flags & HAS_AVX2) aom_get16x16var = aom_get16x16var_avx2; + aom_h_predictor_32x32 = aom_h_predictor_32x32_sse2; + if (flags & HAS_AVX2) aom_h_predictor_32x32 = aom_h_predictor_32x32_avx2; + aom_hadamard_8x8 = aom_hadamard_8x8_sse2; + if (flags & HAS_SSSE3) aom_hadamard_8x8 = aom_hadamard_8x8_ssse3; + aom_highbd_10_masked_sub_pixel_variance16x16 = aom_highbd_10_masked_sub_pixel_variance16x16_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance16x16 = aom_highbd_10_masked_sub_pixel_variance16x16_ssse3; + aom_highbd_10_masked_sub_pixel_variance16x32 = aom_highbd_10_masked_sub_pixel_variance16x32_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance16x32 = aom_highbd_10_masked_sub_pixel_variance16x32_ssse3; + aom_highbd_10_masked_sub_pixel_variance16x8 = aom_highbd_10_masked_sub_pixel_variance16x8_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance16x8 = aom_highbd_10_masked_sub_pixel_variance16x8_ssse3; + aom_highbd_10_masked_sub_pixel_variance32x16 = aom_highbd_10_masked_sub_pixel_variance32x16_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance32x16 = aom_highbd_10_masked_sub_pixel_variance32x16_ssse3; + aom_highbd_10_masked_sub_pixel_variance32x32 = aom_highbd_10_masked_sub_pixel_variance32x32_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance32x32 = aom_highbd_10_masked_sub_pixel_variance32x32_ssse3; + aom_highbd_10_masked_sub_pixel_variance32x64 = aom_highbd_10_masked_sub_pixel_variance32x64_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance32x64 = aom_highbd_10_masked_sub_pixel_variance32x64_ssse3; + aom_highbd_10_masked_sub_pixel_variance4x4 = aom_highbd_10_masked_sub_pixel_variance4x4_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance4x4 = aom_highbd_10_masked_sub_pixel_variance4x4_ssse3; + aom_highbd_10_masked_sub_pixel_variance4x8 = aom_highbd_10_masked_sub_pixel_variance4x8_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance4x8 = aom_highbd_10_masked_sub_pixel_variance4x8_ssse3; + aom_highbd_10_masked_sub_pixel_variance64x32 = aom_highbd_10_masked_sub_pixel_variance64x32_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance64x32 = aom_highbd_10_masked_sub_pixel_variance64x32_ssse3; + aom_highbd_10_masked_sub_pixel_variance64x64 = aom_highbd_10_masked_sub_pixel_variance64x64_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance64x64 = aom_highbd_10_masked_sub_pixel_variance64x64_ssse3; + aom_highbd_10_masked_sub_pixel_variance8x16 = aom_highbd_10_masked_sub_pixel_variance8x16_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance8x16 = aom_highbd_10_masked_sub_pixel_variance8x16_ssse3; + aom_highbd_10_masked_sub_pixel_variance8x4 = aom_highbd_10_masked_sub_pixel_variance8x4_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance8x4 = aom_highbd_10_masked_sub_pixel_variance8x4_ssse3; + aom_highbd_10_masked_sub_pixel_variance8x8 = aom_highbd_10_masked_sub_pixel_variance8x8_c; + if (flags & HAS_SSSE3) aom_highbd_10_masked_sub_pixel_variance8x8 = aom_highbd_10_masked_sub_pixel_variance8x8_ssse3; + aom_highbd_10_obmc_variance16x16 = aom_highbd_10_obmc_variance16x16_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance16x16 = aom_highbd_10_obmc_variance16x16_sse4_1; + aom_highbd_10_obmc_variance16x32 = aom_highbd_10_obmc_variance16x32_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance16x32 = aom_highbd_10_obmc_variance16x32_sse4_1; + aom_highbd_10_obmc_variance16x8 = aom_highbd_10_obmc_variance16x8_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance16x8 = aom_highbd_10_obmc_variance16x8_sse4_1; + aom_highbd_10_obmc_variance32x16 = aom_highbd_10_obmc_variance32x16_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance32x16 = aom_highbd_10_obmc_variance32x16_sse4_1; + aom_highbd_10_obmc_variance32x32 = aom_highbd_10_obmc_variance32x32_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance32x32 = aom_highbd_10_obmc_variance32x32_sse4_1; + aom_highbd_10_obmc_variance32x64 = aom_highbd_10_obmc_variance32x64_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance32x64 = aom_highbd_10_obmc_variance32x64_sse4_1; + aom_highbd_10_obmc_variance4x4 = aom_highbd_10_obmc_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance4x4 = aom_highbd_10_obmc_variance4x4_sse4_1; + aom_highbd_10_obmc_variance4x8 = aom_highbd_10_obmc_variance4x8_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance4x8 = aom_highbd_10_obmc_variance4x8_sse4_1; + aom_highbd_10_obmc_variance64x32 = aom_highbd_10_obmc_variance64x32_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance64x32 = aom_highbd_10_obmc_variance64x32_sse4_1; + aom_highbd_10_obmc_variance64x64 = aom_highbd_10_obmc_variance64x64_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance64x64 = aom_highbd_10_obmc_variance64x64_sse4_1; + aom_highbd_10_obmc_variance8x16 = aom_highbd_10_obmc_variance8x16_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance8x16 = aom_highbd_10_obmc_variance8x16_sse4_1; + aom_highbd_10_obmc_variance8x4 = aom_highbd_10_obmc_variance8x4_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance8x4 = aom_highbd_10_obmc_variance8x4_sse4_1; + aom_highbd_10_obmc_variance8x8 = aom_highbd_10_obmc_variance8x8_c; + if (flags & HAS_SSE4_1) aom_highbd_10_obmc_variance8x8 = aom_highbd_10_obmc_variance8x8_sse4_1; + aom_highbd_10_sub_pixel_avg_variance4x4 = aom_highbd_10_sub_pixel_avg_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_10_sub_pixel_avg_variance4x4 = aom_highbd_10_sub_pixel_avg_variance4x4_sse4_1; + aom_highbd_10_sub_pixel_variance4x4 = aom_highbd_10_sub_pixel_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_10_sub_pixel_variance4x4 = aom_highbd_10_sub_pixel_variance4x4_sse4_1; + aom_highbd_10_variance4x4 = aom_highbd_10_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_10_variance4x4 = aom_highbd_10_variance4x4_sse4_1; + aom_highbd_12_masked_sub_pixel_variance16x16 = aom_highbd_12_masked_sub_pixel_variance16x16_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance16x16 = aom_highbd_12_masked_sub_pixel_variance16x16_ssse3; + aom_highbd_12_masked_sub_pixel_variance16x32 = aom_highbd_12_masked_sub_pixel_variance16x32_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance16x32 = aom_highbd_12_masked_sub_pixel_variance16x32_ssse3; + aom_highbd_12_masked_sub_pixel_variance16x8 = aom_highbd_12_masked_sub_pixel_variance16x8_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance16x8 = aom_highbd_12_masked_sub_pixel_variance16x8_ssse3; + aom_highbd_12_masked_sub_pixel_variance32x16 = aom_highbd_12_masked_sub_pixel_variance32x16_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance32x16 = aom_highbd_12_masked_sub_pixel_variance32x16_ssse3; + aom_highbd_12_masked_sub_pixel_variance32x32 = aom_highbd_12_masked_sub_pixel_variance32x32_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance32x32 = aom_highbd_12_masked_sub_pixel_variance32x32_ssse3; + aom_highbd_12_masked_sub_pixel_variance32x64 = aom_highbd_12_masked_sub_pixel_variance32x64_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance32x64 = aom_highbd_12_masked_sub_pixel_variance32x64_ssse3; + aom_highbd_12_masked_sub_pixel_variance4x4 = aom_highbd_12_masked_sub_pixel_variance4x4_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance4x4 = aom_highbd_12_masked_sub_pixel_variance4x4_ssse3; + aom_highbd_12_masked_sub_pixel_variance4x8 = aom_highbd_12_masked_sub_pixel_variance4x8_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance4x8 = aom_highbd_12_masked_sub_pixel_variance4x8_ssse3; + aom_highbd_12_masked_sub_pixel_variance64x32 = aom_highbd_12_masked_sub_pixel_variance64x32_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance64x32 = aom_highbd_12_masked_sub_pixel_variance64x32_ssse3; + aom_highbd_12_masked_sub_pixel_variance64x64 = aom_highbd_12_masked_sub_pixel_variance64x64_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance64x64 = aom_highbd_12_masked_sub_pixel_variance64x64_ssse3; + aom_highbd_12_masked_sub_pixel_variance8x16 = aom_highbd_12_masked_sub_pixel_variance8x16_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance8x16 = aom_highbd_12_masked_sub_pixel_variance8x16_ssse3; + aom_highbd_12_masked_sub_pixel_variance8x4 = aom_highbd_12_masked_sub_pixel_variance8x4_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance8x4 = aom_highbd_12_masked_sub_pixel_variance8x4_ssse3; + aom_highbd_12_masked_sub_pixel_variance8x8 = aom_highbd_12_masked_sub_pixel_variance8x8_c; + if (flags & HAS_SSSE3) aom_highbd_12_masked_sub_pixel_variance8x8 = aom_highbd_12_masked_sub_pixel_variance8x8_ssse3; + aom_highbd_12_obmc_variance16x16 = aom_highbd_12_obmc_variance16x16_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance16x16 = aom_highbd_12_obmc_variance16x16_sse4_1; + aom_highbd_12_obmc_variance16x32 = aom_highbd_12_obmc_variance16x32_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance16x32 = aom_highbd_12_obmc_variance16x32_sse4_1; + aom_highbd_12_obmc_variance16x8 = aom_highbd_12_obmc_variance16x8_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance16x8 = aom_highbd_12_obmc_variance16x8_sse4_1; + aom_highbd_12_obmc_variance32x16 = aom_highbd_12_obmc_variance32x16_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance32x16 = aom_highbd_12_obmc_variance32x16_sse4_1; + aom_highbd_12_obmc_variance32x32 = aom_highbd_12_obmc_variance32x32_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance32x32 = aom_highbd_12_obmc_variance32x32_sse4_1; + aom_highbd_12_obmc_variance32x64 = aom_highbd_12_obmc_variance32x64_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance32x64 = aom_highbd_12_obmc_variance32x64_sse4_1; + aom_highbd_12_obmc_variance4x4 = aom_highbd_12_obmc_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance4x4 = aom_highbd_12_obmc_variance4x4_sse4_1; + aom_highbd_12_obmc_variance4x8 = aom_highbd_12_obmc_variance4x8_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance4x8 = aom_highbd_12_obmc_variance4x8_sse4_1; + aom_highbd_12_obmc_variance64x32 = aom_highbd_12_obmc_variance64x32_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance64x32 = aom_highbd_12_obmc_variance64x32_sse4_1; + aom_highbd_12_obmc_variance64x64 = aom_highbd_12_obmc_variance64x64_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance64x64 = aom_highbd_12_obmc_variance64x64_sse4_1; + aom_highbd_12_obmc_variance8x16 = aom_highbd_12_obmc_variance8x16_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance8x16 = aom_highbd_12_obmc_variance8x16_sse4_1; + aom_highbd_12_obmc_variance8x4 = aom_highbd_12_obmc_variance8x4_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance8x4 = aom_highbd_12_obmc_variance8x4_sse4_1; + aom_highbd_12_obmc_variance8x8 = aom_highbd_12_obmc_variance8x8_c; + if (flags & HAS_SSE4_1) aom_highbd_12_obmc_variance8x8 = aom_highbd_12_obmc_variance8x8_sse4_1; + aom_highbd_12_sub_pixel_avg_variance4x4 = aom_highbd_12_sub_pixel_avg_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_12_sub_pixel_avg_variance4x4 = aom_highbd_12_sub_pixel_avg_variance4x4_sse4_1; + aom_highbd_12_sub_pixel_variance4x4 = aom_highbd_12_sub_pixel_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_12_sub_pixel_variance4x4 = aom_highbd_12_sub_pixel_variance4x4_sse4_1; + aom_highbd_12_variance4x4 = aom_highbd_12_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_12_variance4x4 = aom_highbd_12_variance4x4_sse4_1; + aom_highbd_8_masked_sub_pixel_variance16x16 = aom_highbd_8_masked_sub_pixel_variance16x16_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance16x16 = aom_highbd_8_masked_sub_pixel_variance16x16_ssse3; + aom_highbd_8_masked_sub_pixel_variance16x32 = aom_highbd_8_masked_sub_pixel_variance16x32_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance16x32 = aom_highbd_8_masked_sub_pixel_variance16x32_ssse3; + aom_highbd_8_masked_sub_pixel_variance16x8 = aom_highbd_8_masked_sub_pixel_variance16x8_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance16x8 = aom_highbd_8_masked_sub_pixel_variance16x8_ssse3; + aom_highbd_8_masked_sub_pixel_variance32x16 = aom_highbd_8_masked_sub_pixel_variance32x16_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance32x16 = aom_highbd_8_masked_sub_pixel_variance32x16_ssse3; + aom_highbd_8_masked_sub_pixel_variance32x32 = aom_highbd_8_masked_sub_pixel_variance32x32_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance32x32 = aom_highbd_8_masked_sub_pixel_variance32x32_ssse3; + aom_highbd_8_masked_sub_pixel_variance32x64 = aom_highbd_8_masked_sub_pixel_variance32x64_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance32x64 = aom_highbd_8_masked_sub_pixel_variance32x64_ssse3; + aom_highbd_8_masked_sub_pixel_variance4x4 = aom_highbd_8_masked_sub_pixel_variance4x4_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance4x4 = aom_highbd_8_masked_sub_pixel_variance4x4_ssse3; + aom_highbd_8_masked_sub_pixel_variance4x8 = aom_highbd_8_masked_sub_pixel_variance4x8_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance4x8 = aom_highbd_8_masked_sub_pixel_variance4x8_ssse3; + aom_highbd_8_masked_sub_pixel_variance64x32 = aom_highbd_8_masked_sub_pixel_variance64x32_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance64x32 = aom_highbd_8_masked_sub_pixel_variance64x32_ssse3; + aom_highbd_8_masked_sub_pixel_variance64x64 = aom_highbd_8_masked_sub_pixel_variance64x64_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance64x64 = aom_highbd_8_masked_sub_pixel_variance64x64_ssse3; + aom_highbd_8_masked_sub_pixel_variance8x16 = aom_highbd_8_masked_sub_pixel_variance8x16_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance8x16 = aom_highbd_8_masked_sub_pixel_variance8x16_ssse3; + aom_highbd_8_masked_sub_pixel_variance8x4 = aom_highbd_8_masked_sub_pixel_variance8x4_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance8x4 = aom_highbd_8_masked_sub_pixel_variance8x4_ssse3; + aom_highbd_8_masked_sub_pixel_variance8x8 = aom_highbd_8_masked_sub_pixel_variance8x8_c; + if (flags & HAS_SSSE3) aom_highbd_8_masked_sub_pixel_variance8x8 = aom_highbd_8_masked_sub_pixel_variance8x8_ssse3; + aom_highbd_8_sub_pixel_avg_variance4x4 = aom_highbd_8_sub_pixel_avg_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_8_sub_pixel_avg_variance4x4 = aom_highbd_8_sub_pixel_avg_variance4x4_sse4_1; + aom_highbd_8_sub_pixel_variance4x4 = aom_highbd_8_sub_pixel_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_8_sub_pixel_variance4x4 = aom_highbd_8_sub_pixel_variance4x4_sse4_1; + aom_highbd_8_variance4x4 = aom_highbd_8_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_8_variance4x4 = aom_highbd_8_variance4x4_sse4_1; + aom_highbd_blend_a64_hmask = aom_highbd_blend_a64_hmask_c; + if (flags & HAS_SSE4_1) aom_highbd_blend_a64_hmask = aom_highbd_blend_a64_hmask_sse4_1; + aom_highbd_blend_a64_mask = aom_highbd_blend_a64_mask_c; + if (flags & HAS_SSE4_1) aom_highbd_blend_a64_mask = aom_highbd_blend_a64_mask_sse4_1; + aom_highbd_blend_a64_vmask = aom_highbd_blend_a64_vmask_c; + if (flags & HAS_SSE4_1) aom_highbd_blend_a64_vmask = aom_highbd_blend_a64_vmask_sse4_1; + aom_highbd_convolve8 = aom_highbd_convolve8_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve8 = aom_highbd_convolve8_avx2; + aom_highbd_convolve8_add_src_hip = aom_highbd_convolve8_add_src_hip_c; + if (flags & HAS_SSSE3) aom_highbd_convolve8_add_src_hip = aom_highbd_convolve8_add_src_hip_ssse3; + aom_highbd_convolve8_avg = aom_highbd_convolve8_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve8_avg = aom_highbd_convolve8_avg_avx2; + aom_highbd_convolve8_avg_horiz = aom_highbd_convolve8_avg_horiz_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve8_avg_horiz = aom_highbd_convolve8_avg_horiz_avx2; + aom_highbd_convolve8_avg_vert = aom_highbd_convolve8_avg_vert_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve8_avg_vert = aom_highbd_convolve8_avg_vert_avx2; + aom_highbd_convolve8_horiz = aom_highbd_convolve8_horiz_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve8_horiz = aom_highbd_convolve8_horiz_avx2; + aom_highbd_convolve8_vert = aom_highbd_convolve8_vert_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve8_vert = aom_highbd_convolve8_vert_avx2; + aom_highbd_convolve_avg = aom_highbd_convolve_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve_avg = aom_highbd_convolve_avg_avx2; + aom_highbd_convolve_copy = aom_highbd_convolve_copy_sse2; + if (flags & HAS_AVX2) aom_highbd_convolve_copy = aom_highbd_convolve_copy_avx2; + aom_highbd_d117_predictor_16x16 = aom_highbd_d117_predictor_16x16_c; + if (flags & HAS_SSSE3) aom_highbd_d117_predictor_16x16 = aom_highbd_d117_predictor_16x16_ssse3; + aom_highbd_d117_predictor_32x32 = aom_highbd_d117_predictor_32x32_c; + if (flags & HAS_SSSE3) aom_highbd_d117_predictor_32x32 = aom_highbd_d117_predictor_32x32_ssse3; + aom_highbd_d117_predictor_8x8 = aom_highbd_d117_predictor_8x8_c; + if (flags & HAS_SSSE3) aom_highbd_d117_predictor_8x8 = aom_highbd_d117_predictor_8x8_ssse3; + aom_highbd_d135_predictor_16x16 = aom_highbd_d135_predictor_16x16_c; + if (flags & HAS_SSSE3) aom_highbd_d135_predictor_16x16 = aom_highbd_d135_predictor_16x16_ssse3; + aom_highbd_d135_predictor_32x32 = aom_highbd_d135_predictor_32x32_c; + if (flags & HAS_SSSE3) aom_highbd_d135_predictor_32x32 = aom_highbd_d135_predictor_32x32_ssse3; + aom_highbd_d135_predictor_8x8 = aom_highbd_d135_predictor_8x8_c; + if (flags & HAS_SSSE3) aom_highbd_d135_predictor_8x8 = aom_highbd_d135_predictor_8x8_ssse3; + aom_highbd_d153_predictor_16x16 = aom_highbd_d153_predictor_16x16_c; + if (flags & HAS_SSSE3) aom_highbd_d153_predictor_16x16 = aom_highbd_d153_predictor_16x16_ssse3; + aom_highbd_d153_predictor_32x32 = aom_highbd_d153_predictor_32x32_c; + if (flags & HAS_SSSE3) aom_highbd_d153_predictor_32x32 = aom_highbd_d153_predictor_32x32_ssse3; + aom_highbd_d153_predictor_8x8 = aom_highbd_d153_predictor_8x8_c; + if (flags & HAS_SSSE3) aom_highbd_d153_predictor_8x8 = aom_highbd_d153_predictor_8x8_ssse3; + aom_highbd_d45e_predictor_16x16 = aom_highbd_d45e_predictor_16x16_c; + if (flags & HAS_AVX2) aom_highbd_d45e_predictor_16x16 = aom_highbd_d45e_predictor_16x16_avx2; + aom_highbd_d45e_predictor_16x32 = aom_highbd_d45e_predictor_16x32_c; + if (flags & HAS_AVX2) aom_highbd_d45e_predictor_16x32 = aom_highbd_d45e_predictor_16x32_avx2; + aom_highbd_d45e_predictor_16x8 = aom_highbd_d45e_predictor_16x8_c; + if (flags & HAS_AVX2) aom_highbd_d45e_predictor_16x8 = aom_highbd_d45e_predictor_16x8_avx2; + aom_highbd_d45e_predictor_32x16 = aom_highbd_d45e_predictor_32x16_c; + if (flags & HAS_AVX2) aom_highbd_d45e_predictor_32x16 = aom_highbd_d45e_predictor_32x16_avx2; + aom_highbd_d45e_predictor_32x32 = aom_highbd_d45e_predictor_32x32_c; + if (flags & HAS_AVX2) aom_highbd_d45e_predictor_32x32 = aom_highbd_d45e_predictor_32x32_avx2; + aom_highbd_lpf_horizontal_4_dual = aom_highbd_lpf_horizontal_4_dual_sse2; + if (flags & HAS_AVX2) aom_highbd_lpf_horizontal_4_dual = aom_highbd_lpf_horizontal_4_dual_avx2; + aom_highbd_lpf_horizontal_8_dual = aom_highbd_lpf_horizontal_8_dual_sse2; + if (flags & HAS_AVX2) aom_highbd_lpf_horizontal_8_dual = aom_highbd_lpf_horizontal_8_dual_avx2; + aom_highbd_lpf_horizontal_edge_16 = aom_highbd_lpf_horizontal_edge_16_sse2; + if (flags & HAS_AVX2) aom_highbd_lpf_horizontal_edge_16 = aom_highbd_lpf_horizontal_edge_16_avx2; + aom_highbd_lpf_vertical_16_dual = aom_highbd_lpf_vertical_16_dual_sse2; + if (flags & HAS_AVX2) aom_highbd_lpf_vertical_16_dual = aom_highbd_lpf_vertical_16_dual_avx2; + aom_highbd_lpf_vertical_4_dual = aom_highbd_lpf_vertical_4_dual_sse2; + if (flags & HAS_AVX2) aom_highbd_lpf_vertical_4_dual = aom_highbd_lpf_vertical_4_dual_avx2; + aom_highbd_lpf_vertical_8_dual = aom_highbd_lpf_vertical_8_dual_sse2; + if (flags & HAS_AVX2) aom_highbd_lpf_vertical_8_dual = aom_highbd_lpf_vertical_8_dual_avx2; + aom_highbd_masked_sad16x16 = aom_highbd_masked_sad16x16_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad16x16 = aom_highbd_masked_sad16x16_ssse3; + aom_highbd_masked_sad16x32 = aom_highbd_masked_sad16x32_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad16x32 = aom_highbd_masked_sad16x32_ssse3; + aom_highbd_masked_sad16x8 = aom_highbd_masked_sad16x8_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad16x8 = aom_highbd_masked_sad16x8_ssse3; + aom_highbd_masked_sad32x16 = aom_highbd_masked_sad32x16_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad32x16 = aom_highbd_masked_sad32x16_ssse3; + aom_highbd_masked_sad32x32 = aom_highbd_masked_sad32x32_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad32x32 = aom_highbd_masked_sad32x32_ssse3; + aom_highbd_masked_sad32x64 = aom_highbd_masked_sad32x64_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad32x64 = aom_highbd_masked_sad32x64_ssse3; + aom_highbd_masked_sad4x4 = aom_highbd_masked_sad4x4_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad4x4 = aom_highbd_masked_sad4x4_ssse3; + aom_highbd_masked_sad4x8 = aom_highbd_masked_sad4x8_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad4x8 = aom_highbd_masked_sad4x8_ssse3; + aom_highbd_masked_sad64x32 = aom_highbd_masked_sad64x32_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad64x32 = aom_highbd_masked_sad64x32_ssse3; + aom_highbd_masked_sad64x64 = aom_highbd_masked_sad64x64_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad64x64 = aom_highbd_masked_sad64x64_ssse3; + aom_highbd_masked_sad8x16 = aom_highbd_masked_sad8x16_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad8x16 = aom_highbd_masked_sad8x16_ssse3; + aom_highbd_masked_sad8x4 = aom_highbd_masked_sad8x4_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad8x4 = aom_highbd_masked_sad8x4_ssse3; + aom_highbd_masked_sad8x8 = aom_highbd_masked_sad8x8_c; + if (flags & HAS_SSSE3) aom_highbd_masked_sad8x8 = aom_highbd_masked_sad8x8_ssse3; + aom_highbd_obmc_sad16x16 = aom_highbd_obmc_sad16x16_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad16x16 = aom_highbd_obmc_sad16x16_sse4_1; + aom_highbd_obmc_sad16x32 = aom_highbd_obmc_sad16x32_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad16x32 = aom_highbd_obmc_sad16x32_sse4_1; + aom_highbd_obmc_sad16x8 = aom_highbd_obmc_sad16x8_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad16x8 = aom_highbd_obmc_sad16x8_sse4_1; + aom_highbd_obmc_sad32x16 = aom_highbd_obmc_sad32x16_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad32x16 = aom_highbd_obmc_sad32x16_sse4_1; + aom_highbd_obmc_sad32x32 = aom_highbd_obmc_sad32x32_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad32x32 = aom_highbd_obmc_sad32x32_sse4_1; + aom_highbd_obmc_sad32x64 = aom_highbd_obmc_sad32x64_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad32x64 = aom_highbd_obmc_sad32x64_sse4_1; + aom_highbd_obmc_sad4x4 = aom_highbd_obmc_sad4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad4x4 = aom_highbd_obmc_sad4x4_sse4_1; + aom_highbd_obmc_sad4x8 = aom_highbd_obmc_sad4x8_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad4x8 = aom_highbd_obmc_sad4x8_sse4_1; + aom_highbd_obmc_sad64x32 = aom_highbd_obmc_sad64x32_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad64x32 = aom_highbd_obmc_sad64x32_sse4_1; + aom_highbd_obmc_sad64x64 = aom_highbd_obmc_sad64x64_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad64x64 = aom_highbd_obmc_sad64x64_sse4_1; + aom_highbd_obmc_sad8x16 = aom_highbd_obmc_sad8x16_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad8x16 = aom_highbd_obmc_sad8x16_sse4_1; + aom_highbd_obmc_sad8x4 = aom_highbd_obmc_sad8x4_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad8x4 = aom_highbd_obmc_sad8x4_sse4_1; + aom_highbd_obmc_sad8x8 = aom_highbd_obmc_sad8x8_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_sad8x8 = aom_highbd_obmc_sad8x8_sse4_1; + aom_highbd_obmc_variance16x16 = aom_highbd_obmc_variance16x16_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance16x16 = aom_highbd_obmc_variance16x16_sse4_1; + aom_highbd_obmc_variance16x32 = aom_highbd_obmc_variance16x32_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance16x32 = aom_highbd_obmc_variance16x32_sse4_1; + aom_highbd_obmc_variance16x8 = aom_highbd_obmc_variance16x8_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance16x8 = aom_highbd_obmc_variance16x8_sse4_1; + aom_highbd_obmc_variance32x16 = aom_highbd_obmc_variance32x16_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance32x16 = aom_highbd_obmc_variance32x16_sse4_1; + aom_highbd_obmc_variance32x32 = aom_highbd_obmc_variance32x32_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance32x32 = aom_highbd_obmc_variance32x32_sse4_1; + aom_highbd_obmc_variance32x64 = aom_highbd_obmc_variance32x64_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance32x64 = aom_highbd_obmc_variance32x64_sse4_1; + aom_highbd_obmc_variance4x4 = aom_highbd_obmc_variance4x4_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance4x4 = aom_highbd_obmc_variance4x4_sse4_1; + aom_highbd_obmc_variance4x8 = aom_highbd_obmc_variance4x8_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance4x8 = aom_highbd_obmc_variance4x8_sse4_1; + aom_highbd_obmc_variance64x32 = aom_highbd_obmc_variance64x32_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance64x32 = aom_highbd_obmc_variance64x32_sse4_1; + aom_highbd_obmc_variance64x64 = aom_highbd_obmc_variance64x64_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance64x64 = aom_highbd_obmc_variance64x64_sse4_1; + aom_highbd_obmc_variance8x16 = aom_highbd_obmc_variance8x16_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance8x16 = aom_highbd_obmc_variance8x16_sse4_1; + aom_highbd_obmc_variance8x4 = aom_highbd_obmc_variance8x4_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance8x4 = aom_highbd_obmc_variance8x4_sse4_1; + aom_highbd_obmc_variance8x8 = aom_highbd_obmc_variance8x8_c; + if (flags & HAS_SSE4_1) aom_highbd_obmc_variance8x8 = aom_highbd_obmc_variance8x8_sse4_1; + aom_highbd_quantize_b = aom_highbd_quantize_b_sse2; + if (flags & HAS_AVX2) aom_highbd_quantize_b = aom_highbd_quantize_b_avx2; + aom_highbd_sad16x16 = aom_highbd_sad16x16_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x16 = aom_highbd_sad16x16_avx2; + aom_highbd_sad16x16_avg = aom_highbd_sad16x16_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x16_avg = aom_highbd_sad16x16_avg_avx2; + aom_highbd_sad16x16x4d = aom_highbd_sad16x16x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x16x4d = aom_highbd_sad16x16x4d_avx2; + aom_highbd_sad16x32 = aom_highbd_sad16x32_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x32 = aom_highbd_sad16x32_avx2; + aom_highbd_sad16x32_avg = aom_highbd_sad16x32_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x32_avg = aom_highbd_sad16x32_avg_avx2; + aom_highbd_sad16x32x4d = aom_highbd_sad16x32x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x32x4d = aom_highbd_sad16x32x4d_avx2; + aom_highbd_sad16x8 = aom_highbd_sad16x8_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x8 = aom_highbd_sad16x8_avx2; + aom_highbd_sad16x8_avg = aom_highbd_sad16x8_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x8_avg = aom_highbd_sad16x8_avg_avx2; + aom_highbd_sad16x8x4d = aom_highbd_sad16x8x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad16x8x4d = aom_highbd_sad16x8x4d_avx2; + aom_highbd_sad32x16 = aom_highbd_sad32x16_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x16 = aom_highbd_sad32x16_avx2; + aom_highbd_sad32x16_avg = aom_highbd_sad32x16_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x16_avg = aom_highbd_sad32x16_avg_avx2; + aom_highbd_sad32x16x4d = aom_highbd_sad32x16x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x16x4d = aom_highbd_sad32x16x4d_avx2; + aom_highbd_sad32x32 = aom_highbd_sad32x32_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x32 = aom_highbd_sad32x32_avx2; + aom_highbd_sad32x32_avg = aom_highbd_sad32x32_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x32_avg = aom_highbd_sad32x32_avg_avx2; + aom_highbd_sad32x32x4d = aom_highbd_sad32x32x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x32x4d = aom_highbd_sad32x32x4d_avx2; + aom_highbd_sad32x64 = aom_highbd_sad32x64_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x64 = aom_highbd_sad32x64_avx2; + aom_highbd_sad32x64_avg = aom_highbd_sad32x64_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x64_avg = aom_highbd_sad32x64_avg_avx2; + aom_highbd_sad32x64x4d = aom_highbd_sad32x64x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad32x64x4d = aom_highbd_sad32x64x4d_avx2; + aom_highbd_sad64x32 = aom_highbd_sad64x32_sse2; + if (flags & HAS_AVX2) aom_highbd_sad64x32 = aom_highbd_sad64x32_avx2; + aom_highbd_sad64x32_avg = aom_highbd_sad64x32_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad64x32_avg = aom_highbd_sad64x32_avg_avx2; + aom_highbd_sad64x32x4d = aom_highbd_sad64x32x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad64x32x4d = aom_highbd_sad64x32x4d_avx2; + aom_highbd_sad64x64 = aom_highbd_sad64x64_sse2; + if (flags & HAS_AVX2) aom_highbd_sad64x64 = aom_highbd_sad64x64_avx2; + aom_highbd_sad64x64_avg = aom_highbd_sad64x64_avg_sse2; + if (flags & HAS_AVX2) aom_highbd_sad64x64_avg = aom_highbd_sad64x64_avg_avx2; + aom_highbd_sad64x64x4d = aom_highbd_sad64x64x4d_sse2; + if (flags & HAS_AVX2) aom_highbd_sad64x64x4d = aom_highbd_sad64x64x4d_avx2; + aom_idct16x16_10_add = aom_idct16x16_10_add_sse2; + if (flags & HAS_AVX2) aom_idct16x16_10_add = aom_idct16x16_10_add_avx2; + aom_idct16x16_1_add = aom_idct16x16_1_add_sse2; + if (flags & HAS_AVX2) aom_idct16x16_1_add = aom_idct16x16_1_add_avx2; + aom_idct16x16_256_add = aom_idct16x16_256_add_sse2; + if (flags & HAS_AVX2) aom_idct16x16_256_add = aom_idct16x16_256_add_avx2; + aom_idct16x16_38_add = aom_idct16x16_38_add_c; + if (flags & HAS_AVX2) aom_idct16x16_38_add = aom_idct16x16_38_add_avx2; + aom_idct32x32_1024_add = aom_idct32x32_1024_add_sse2; + if (flags & HAS_SSSE3) aom_idct32x32_1024_add = aom_idct32x32_1024_add_ssse3; + if (flags & HAS_AVX2) aom_idct32x32_1024_add = aom_idct32x32_1024_add_avx2; + aom_idct32x32_135_add = aom_idct32x32_1024_add_sse2; + if (flags & HAS_SSSE3) aom_idct32x32_135_add = aom_idct32x32_135_add_ssse3; + if (flags & HAS_AVX2) aom_idct32x32_135_add = aom_idct32x32_135_add_avx2; + aom_idct32x32_1_add = aom_idct32x32_1_add_sse2; + if (flags & HAS_AVX2) aom_idct32x32_1_add = aom_idct32x32_1_add_avx2; + aom_idct32x32_34_add = aom_idct32x32_34_add_sse2; + if (flags & HAS_SSSE3) aom_idct32x32_34_add = aom_idct32x32_34_add_ssse3; + if (flags & HAS_AVX2) aom_idct32x32_34_add = aom_idct32x32_34_add_avx2; + aom_idct8x8_12_add = aom_idct8x8_12_add_sse2; + if (flags & HAS_SSSE3) aom_idct8x8_12_add = aom_idct8x8_12_add_ssse3; + aom_idct8x8_64_add = aom_idct8x8_64_add_sse2; + if (flags & HAS_SSSE3) aom_idct8x8_64_add = aom_idct8x8_64_add_ssse3; + aom_masked_sad16x16 = aom_masked_sad16x16_c; + if (flags & HAS_SSSE3) aom_masked_sad16x16 = aom_masked_sad16x16_ssse3; + aom_masked_sad16x32 = aom_masked_sad16x32_c; + if (flags & HAS_SSSE3) aom_masked_sad16x32 = aom_masked_sad16x32_ssse3; + aom_masked_sad16x8 = aom_masked_sad16x8_c; + if (flags & HAS_SSSE3) aom_masked_sad16x8 = aom_masked_sad16x8_ssse3; + aom_masked_sad32x16 = aom_masked_sad32x16_c; + if (flags & HAS_SSSE3) aom_masked_sad32x16 = aom_masked_sad32x16_ssse3; + aom_masked_sad32x32 = aom_masked_sad32x32_c; + if (flags & HAS_SSSE3) aom_masked_sad32x32 = aom_masked_sad32x32_ssse3; + aom_masked_sad32x64 = aom_masked_sad32x64_c; + if (flags & HAS_SSSE3) aom_masked_sad32x64 = aom_masked_sad32x64_ssse3; + aom_masked_sad4x4 = aom_masked_sad4x4_c; + if (flags & HAS_SSSE3) aom_masked_sad4x4 = aom_masked_sad4x4_ssse3; + aom_masked_sad4x8 = aom_masked_sad4x8_c; + if (flags & HAS_SSSE3) aom_masked_sad4x8 = aom_masked_sad4x8_ssse3; + aom_masked_sad64x32 = aom_masked_sad64x32_c; + if (flags & HAS_SSSE3) aom_masked_sad64x32 = aom_masked_sad64x32_ssse3; + aom_masked_sad64x64 = aom_masked_sad64x64_c; + if (flags & HAS_SSSE3) aom_masked_sad64x64 = aom_masked_sad64x64_ssse3; + aom_masked_sad8x16 = aom_masked_sad8x16_c; + if (flags & HAS_SSSE3) aom_masked_sad8x16 = aom_masked_sad8x16_ssse3; + aom_masked_sad8x4 = aom_masked_sad8x4_c; + if (flags & HAS_SSSE3) aom_masked_sad8x4 = aom_masked_sad8x4_ssse3; + aom_masked_sad8x8 = aom_masked_sad8x8_c; + if (flags & HAS_SSSE3) aom_masked_sad8x8 = aom_masked_sad8x8_ssse3; + aom_masked_sub_pixel_variance16x16 = aom_masked_sub_pixel_variance16x16_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance16x16 = aom_masked_sub_pixel_variance16x16_ssse3; + aom_masked_sub_pixel_variance16x32 = aom_masked_sub_pixel_variance16x32_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance16x32 = aom_masked_sub_pixel_variance16x32_ssse3; + aom_masked_sub_pixel_variance16x8 = aom_masked_sub_pixel_variance16x8_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance16x8 = aom_masked_sub_pixel_variance16x8_ssse3; + aom_masked_sub_pixel_variance32x16 = aom_masked_sub_pixel_variance32x16_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance32x16 = aom_masked_sub_pixel_variance32x16_ssse3; + aom_masked_sub_pixel_variance32x32 = aom_masked_sub_pixel_variance32x32_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance32x32 = aom_masked_sub_pixel_variance32x32_ssse3; + aom_masked_sub_pixel_variance32x64 = aom_masked_sub_pixel_variance32x64_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance32x64 = aom_masked_sub_pixel_variance32x64_ssse3; + aom_masked_sub_pixel_variance4x4 = aom_masked_sub_pixel_variance4x4_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance4x4 = aom_masked_sub_pixel_variance4x4_ssse3; + aom_masked_sub_pixel_variance4x8 = aom_masked_sub_pixel_variance4x8_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance4x8 = aom_masked_sub_pixel_variance4x8_ssse3; + aom_masked_sub_pixel_variance64x32 = aom_masked_sub_pixel_variance64x32_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance64x32 = aom_masked_sub_pixel_variance64x32_ssse3; + aom_masked_sub_pixel_variance64x64 = aom_masked_sub_pixel_variance64x64_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance64x64 = aom_masked_sub_pixel_variance64x64_ssse3; + aom_masked_sub_pixel_variance8x16 = aom_masked_sub_pixel_variance8x16_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance8x16 = aom_masked_sub_pixel_variance8x16_ssse3; + aom_masked_sub_pixel_variance8x4 = aom_masked_sub_pixel_variance8x4_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance8x4 = aom_masked_sub_pixel_variance8x4_ssse3; + aom_masked_sub_pixel_variance8x8 = aom_masked_sub_pixel_variance8x8_c; + if (flags & HAS_SSSE3) aom_masked_sub_pixel_variance8x8 = aom_masked_sub_pixel_variance8x8_ssse3; + aom_mse16x16 = aom_mse16x16_sse2; + if (flags & HAS_AVX2) aom_mse16x16 = aom_mse16x16_avx2; + aom_obmc_sad16x16 = aom_obmc_sad16x16_c; + if (flags & HAS_SSE4_1) aom_obmc_sad16x16 = aom_obmc_sad16x16_sse4_1; + aom_obmc_sad16x32 = aom_obmc_sad16x32_c; + if (flags & HAS_SSE4_1) aom_obmc_sad16x32 = aom_obmc_sad16x32_sse4_1; + aom_obmc_sad16x8 = aom_obmc_sad16x8_c; + if (flags & HAS_SSE4_1) aom_obmc_sad16x8 = aom_obmc_sad16x8_sse4_1; + aom_obmc_sad32x16 = aom_obmc_sad32x16_c; + if (flags & HAS_SSE4_1) aom_obmc_sad32x16 = aom_obmc_sad32x16_sse4_1; + aom_obmc_sad32x32 = aom_obmc_sad32x32_c; + if (flags & HAS_SSE4_1) aom_obmc_sad32x32 = aom_obmc_sad32x32_sse4_1; + aom_obmc_sad32x64 = aom_obmc_sad32x64_c; + if (flags & HAS_SSE4_1) aom_obmc_sad32x64 = aom_obmc_sad32x64_sse4_1; + aom_obmc_sad4x4 = aom_obmc_sad4x4_c; + if (flags & HAS_SSE4_1) aom_obmc_sad4x4 = aom_obmc_sad4x4_sse4_1; + aom_obmc_sad4x8 = aom_obmc_sad4x8_c; + if (flags & HAS_SSE4_1) aom_obmc_sad4x8 = aom_obmc_sad4x8_sse4_1; + aom_obmc_sad64x32 = aom_obmc_sad64x32_c; + if (flags & HAS_SSE4_1) aom_obmc_sad64x32 = aom_obmc_sad64x32_sse4_1; + aom_obmc_sad64x64 = aom_obmc_sad64x64_c; + if (flags & HAS_SSE4_1) aom_obmc_sad64x64 = aom_obmc_sad64x64_sse4_1; + aom_obmc_sad8x16 = aom_obmc_sad8x16_c; + if (flags & HAS_SSE4_1) aom_obmc_sad8x16 = aom_obmc_sad8x16_sse4_1; + aom_obmc_sad8x4 = aom_obmc_sad8x4_c; + if (flags & HAS_SSE4_1) aom_obmc_sad8x4 = aom_obmc_sad8x4_sse4_1; + aom_obmc_sad8x8 = aom_obmc_sad8x8_c; + if (flags & HAS_SSE4_1) aom_obmc_sad8x8 = aom_obmc_sad8x8_sse4_1; + aom_obmc_variance16x16 = aom_obmc_variance16x16_c; + if (flags & HAS_SSE4_1) aom_obmc_variance16x16 = aom_obmc_variance16x16_sse4_1; + aom_obmc_variance16x32 = aom_obmc_variance16x32_c; + if (flags & HAS_SSE4_1) aom_obmc_variance16x32 = aom_obmc_variance16x32_sse4_1; + aom_obmc_variance16x8 = aom_obmc_variance16x8_c; + if (flags & HAS_SSE4_1) aom_obmc_variance16x8 = aom_obmc_variance16x8_sse4_1; + aom_obmc_variance32x16 = aom_obmc_variance32x16_c; + if (flags & HAS_SSE4_1) aom_obmc_variance32x16 = aom_obmc_variance32x16_sse4_1; + aom_obmc_variance32x32 = aom_obmc_variance32x32_c; + if (flags & HAS_SSE4_1) aom_obmc_variance32x32 = aom_obmc_variance32x32_sse4_1; + aom_obmc_variance32x64 = aom_obmc_variance32x64_c; + if (flags & HAS_SSE4_1) aom_obmc_variance32x64 = aom_obmc_variance32x64_sse4_1; + aom_obmc_variance4x4 = aom_obmc_variance4x4_c; + if (flags & HAS_SSE4_1) aom_obmc_variance4x4 = aom_obmc_variance4x4_sse4_1; + aom_obmc_variance4x8 = aom_obmc_variance4x8_c; + if (flags & HAS_SSE4_1) aom_obmc_variance4x8 = aom_obmc_variance4x8_sse4_1; + aom_obmc_variance64x32 = aom_obmc_variance64x32_c; + if (flags & HAS_SSE4_1) aom_obmc_variance64x32 = aom_obmc_variance64x32_sse4_1; + aom_obmc_variance64x64 = aom_obmc_variance64x64_c; + if (flags & HAS_SSE4_1) aom_obmc_variance64x64 = aom_obmc_variance64x64_sse4_1; + aom_obmc_variance8x16 = aom_obmc_variance8x16_c; + if (flags & HAS_SSE4_1) aom_obmc_variance8x16 = aom_obmc_variance8x16_sse4_1; + aom_obmc_variance8x4 = aom_obmc_variance8x4_c; + if (flags & HAS_SSE4_1) aom_obmc_variance8x4 = aom_obmc_variance8x4_sse4_1; + aom_obmc_variance8x8 = aom_obmc_variance8x8_c; + if (flags & HAS_SSE4_1) aom_obmc_variance8x8 = aom_obmc_variance8x8_sse4_1; + aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_ssse3; + if (flags & HAS_AVX2) aom_paeth_predictor_16x16 = aom_paeth_predictor_16x16_avx2; + aom_paeth_predictor_16x32 = aom_paeth_predictor_16x32_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_16x32 = aom_paeth_predictor_16x32_ssse3; + if (flags & HAS_AVX2) aom_paeth_predictor_16x32 = aom_paeth_predictor_16x32_avx2; + aom_paeth_predictor_16x8 = aom_paeth_predictor_16x8_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_16x8 = aom_paeth_predictor_16x8_ssse3; + if (flags & HAS_AVX2) aom_paeth_predictor_16x8 = aom_paeth_predictor_16x8_avx2; + aom_paeth_predictor_32x16 = aom_paeth_predictor_32x16_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_32x16 = aom_paeth_predictor_32x16_ssse3; + if (flags & HAS_AVX2) aom_paeth_predictor_32x16 = aom_paeth_predictor_32x16_avx2; + aom_paeth_predictor_32x32 = aom_paeth_predictor_32x32_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_32x32 = aom_paeth_predictor_32x32_ssse3; + if (flags & HAS_AVX2) aom_paeth_predictor_32x32 = aom_paeth_predictor_32x32_avx2; + aom_paeth_predictor_4x4 = aom_paeth_predictor_4x4_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_4x4 = aom_paeth_predictor_4x4_ssse3; + aom_paeth_predictor_4x8 = aom_paeth_predictor_4x8_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_4x8 = aom_paeth_predictor_4x8_ssse3; + aom_paeth_predictor_8x16 = aom_paeth_predictor_8x16_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_8x16 = aom_paeth_predictor_8x16_ssse3; + aom_paeth_predictor_8x4 = aom_paeth_predictor_8x4_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_8x4 = aom_paeth_predictor_8x4_ssse3; + aom_paeth_predictor_8x8 = aom_paeth_predictor_8x8_c; + if (flags & HAS_SSSE3) aom_paeth_predictor_8x8 = aom_paeth_predictor_8x8_ssse3; + aom_quantize_b = aom_quantize_b_sse2; + if (flags & HAS_SSSE3) aom_quantize_b = aom_quantize_b_ssse3; + if (flags & HAS_AVX) aom_quantize_b = aom_quantize_b_avx; + aom_quantize_b_32x32 = aom_quantize_b_32x32_c; + if (flags & HAS_SSSE3) aom_quantize_b_32x32 = aom_quantize_b_32x32_ssse3; + if (flags & HAS_AVX) aom_quantize_b_32x32 = aom_quantize_b_32x32_avx; + aom_sad16x16x3 = aom_sad16x16x3_c; + if (flags & HAS_SSE3) aom_sad16x16x3 = aom_sad16x16x3_sse3; + if (flags & HAS_SSSE3) aom_sad16x16x3 = aom_sad16x16x3_ssse3; + aom_sad16x16x8 = aom_sad16x16x8_c; + if (flags & HAS_SSE4_1) aom_sad16x16x8 = aom_sad16x16x8_sse4_1; + aom_sad16x8x3 = aom_sad16x8x3_c; + if (flags & HAS_SSE3) aom_sad16x8x3 = aom_sad16x8x3_sse3; + if (flags & HAS_SSSE3) aom_sad16x8x3 = aom_sad16x8x3_ssse3; + aom_sad16x8x8 = aom_sad16x8x8_c; + if (flags & HAS_SSE4_1) aom_sad16x8x8 = aom_sad16x8x8_sse4_1; + aom_sad32x16 = aom_sad32x16_sse2; + if (flags & HAS_AVX2) aom_sad32x16 = aom_sad32x16_avx2; + aom_sad32x16_avg = aom_sad32x16_avg_sse2; + if (flags & HAS_AVX2) aom_sad32x16_avg = aom_sad32x16_avg_avx2; + aom_sad32x32 = aom_sad32x32_sse2; + if (flags & HAS_AVX2) aom_sad32x32 = aom_sad32x32_avx2; + aom_sad32x32_avg = aom_sad32x32_avg_sse2; + if (flags & HAS_AVX2) aom_sad32x32_avg = aom_sad32x32_avg_avx2; + aom_sad32x32x4d = aom_sad32x32x4d_sse2; + if (flags & HAS_AVX2) aom_sad32x32x4d = aom_sad32x32x4d_avx2; + aom_sad32x64 = aom_sad32x64_sse2; + if (flags & HAS_AVX2) aom_sad32x64 = aom_sad32x64_avx2; + aom_sad32x64_avg = aom_sad32x64_avg_sse2; + if (flags & HAS_AVX2) aom_sad32x64_avg = aom_sad32x64_avg_avx2; + aom_sad32x64x4d = aom_sad32x64x4d_sse2; + if (flags & HAS_AVX2) aom_sad32x64x4d = aom_sad32x64x4d_avx2; + aom_sad4x4x3 = aom_sad4x4x3_c; + if (flags & HAS_SSE3) aom_sad4x4x3 = aom_sad4x4x3_sse3; + aom_sad4x4x8 = aom_sad4x4x8_c; + if (flags & HAS_SSE4_1) aom_sad4x4x8 = aom_sad4x4x8_sse4_1; + aom_sad64x32 = aom_sad64x32_sse2; + if (flags & HAS_AVX2) aom_sad64x32 = aom_sad64x32_avx2; + aom_sad64x32_avg = aom_sad64x32_avg_sse2; + if (flags & HAS_AVX2) aom_sad64x32_avg = aom_sad64x32_avg_avx2; + aom_sad64x32x4d = aom_sad64x32x4d_sse2; + if (flags & HAS_AVX2) aom_sad64x32x4d = aom_sad64x32x4d_avx2; + aom_sad64x64 = aom_sad64x64_sse2; + if (flags & HAS_AVX2) aom_sad64x64 = aom_sad64x64_avx2; + aom_sad64x64_avg = aom_sad64x64_avg_sse2; + if (flags & HAS_AVX2) aom_sad64x64_avg = aom_sad64x64_avg_avx2; + aom_sad64x64x4d = aom_sad64x64x4d_sse2; + if (flags & HAS_AVX2) aom_sad64x64x4d = aom_sad64x64x4d_avx2; + aom_sad8x16x3 = aom_sad8x16x3_c; + if (flags & HAS_SSE3) aom_sad8x16x3 = aom_sad8x16x3_sse3; + aom_sad8x16x8 = aom_sad8x16x8_c; + if (flags & HAS_SSE4_1) aom_sad8x16x8 = aom_sad8x16x8_sse4_1; + aom_sad8x8x3 = aom_sad8x8x3_c; + if (flags & HAS_SSE3) aom_sad8x8x3 = aom_sad8x8x3_sse3; + aom_sad8x8x8 = aom_sad8x8x8_c; + if (flags & HAS_SSE4_1) aom_sad8x8x8 = aom_sad8x8x8_sse4_1; + aom_scaled_2d = aom_scaled_2d_c; + if (flags & HAS_SSSE3) aom_scaled_2d = aom_scaled_2d_ssse3; + aom_smooth_predictor_16x16 = aom_smooth_predictor_16x16_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_16x16 = aom_smooth_predictor_16x16_ssse3; + aom_smooth_predictor_16x32 = aom_smooth_predictor_16x32_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_16x32 = aom_smooth_predictor_16x32_ssse3; + aom_smooth_predictor_16x8 = aom_smooth_predictor_16x8_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_16x8 = aom_smooth_predictor_16x8_ssse3; + aom_smooth_predictor_32x16 = aom_smooth_predictor_32x16_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_32x16 = aom_smooth_predictor_32x16_ssse3; + aom_smooth_predictor_32x32 = aom_smooth_predictor_32x32_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_32x32 = aom_smooth_predictor_32x32_ssse3; + aom_smooth_predictor_4x4 = aom_smooth_predictor_4x4_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_4x4 = aom_smooth_predictor_4x4_ssse3; + aom_smooth_predictor_4x8 = aom_smooth_predictor_4x8_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_4x8 = aom_smooth_predictor_4x8_ssse3; + aom_smooth_predictor_8x16 = aom_smooth_predictor_8x16_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_8x16 = aom_smooth_predictor_8x16_ssse3; + aom_smooth_predictor_8x4 = aom_smooth_predictor_8x4_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_8x4 = aom_smooth_predictor_8x4_ssse3; + aom_smooth_predictor_8x8 = aom_smooth_predictor_8x8_c; + if (flags & HAS_SSSE3) aom_smooth_predictor_8x8 = aom_smooth_predictor_8x8_ssse3; + aom_sub_pixel_avg_variance16x16 = aom_sub_pixel_avg_variance16x16_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance16x16 = aom_sub_pixel_avg_variance16x16_ssse3; + aom_sub_pixel_avg_variance16x32 = aom_sub_pixel_avg_variance16x32_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance16x32 = aom_sub_pixel_avg_variance16x32_ssse3; + aom_sub_pixel_avg_variance16x8 = aom_sub_pixel_avg_variance16x8_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance16x8 = aom_sub_pixel_avg_variance16x8_ssse3; + aom_sub_pixel_avg_variance32x16 = aom_sub_pixel_avg_variance32x16_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance32x16 = aom_sub_pixel_avg_variance32x16_ssse3; + aom_sub_pixel_avg_variance32x32 = aom_sub_pixel_avg_variance32x32_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance32x32 = aom_sub_pixel_avg_variance32x32_ssse3; + if (flags & HAS_AVX2) aom_sub_pixel_avg_variance32x32 = aom_sub_pixel_avg_variance32x32_avx2; + aom_sub_pixel_avg_variance32x64 = aom_sub_pixel_avg_variance32x64_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance32x64 = aom_sub_pixel_avg_variance32x64_ssse3; + aom_sub_pixel_avg_variance4x4 = aom_sub_pixel_avg_variance4x4_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance4x4 = aom_sub_pixel_avg_variance4x4_ssse3; + aom_sub_pixel_avg_variance4x8 = aom_sub_pixel_avg_variance4x8_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance4x8 = aom_sub_pixel_avg_variance4x8_ssse3; + aom_sub_pixel_avg_variance64x32 = aom_sub_pixel_avg_variance64x32_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance64x32 = aom_sub_pixel_avg_variance64x32_ssse3; + aom_sub_pixel_avg_variance64x64 = aom_sub_pixel_avg_variance64x64_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance64x64 = aom_sub_pixel_avg_variance64x64_ssse3; + if (flags & HAS_AVX2) aom_sub_pixel_avg_variance64x64 = aom_sub_pixel_avg_variance64x64_avx2; + aom_sub_pixel_avg_variance8x16 = aom_sub_pixel_avg_variance8x16_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance8x16 = aom_sub_pixel_avg_variance8x16_ssse3; + aom_sub_pixel_avg_variance8x4 = aom_sub_pixel_avg_variance8x4_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance8x4 = aom_sub_pixel_avg_variance8x4_ssse3; + aom_sub_pixel_avg_variance8x8 = aom_sub_pixel_avg_variance8x8_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_avg_variance8x8 = aom_sub_pixel_avg_variance8x8_ssse3; + aom_sub_pixel_variance16x16 = aom_sub_pixel_variance16x16_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance16x16 = aom_sub_pixel_variance16x16_ssse3; + aom_sub_pixel_variance16x32 = aom_sub_pixel_variance16x32_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance16x32 = aom_sub_pixel_variance16x32_ssse3; + aom_sub_pixel_variance16x8 = aom_sub_pixel_variance16x8_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance16x8 = aom_sub_pixel_variance16x8_ssse3; + aom_sub_pixel_variance32x16 = aom_sub_pixel_variance32x16_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance32x16 = aom_sub_pixel_variance32x16_ssse3; + aom_sub_pixel_variance32x32 = aom_sub_pixel_variance32x32_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance32x32 = aom_sub_pixel_variance32x32_ssse3; + if (flags & HAS_AVX2) aom_sub_pixel_variance32x32 = aom_sub_pixel_variance32x32_avx2; + aom_sub_pixel_variance32x64 = aom_sub_pixel_variance32x64_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance32x64 = aom_sub_pixel_variance32x64_ssse3; + aom_sub_pixel_variance4x4 = aom_sub_pixel_variance4x4_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance4x4 = aom_sub_pixel_variance4x4_ssse3; + aom_sub_pixel_variance4x8 = aom_sub_pixel_variance4x8_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance4x8 = aom_sub_pixel_variance4x8_ssse3; + aom_sub_pixel_variance64x32 = aom_sub_pixel_variance64x32_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance64x32 = aom_sub_pixel_variance64x32_ssse3; + aom_sub_pixel_variance64x64 = aom_sub_pixel_variance64x64_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance64x64 = aom_sub_pixel_variance64x64_ssse3; + if (flags & HAS_AVX2) aom_sub_pixel_variance64x64 = aom_sub_pixel_variance64x64_avx2; + aom_sub_pixel_variance8x16 = aom_sub_pixel_variance8x16_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance8x16 = aom_sub_pixel_variance8x16_ssse3; + aom_sub_pixel_variance8x4 = aom_sub_pixel_variance8x4_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance8x4 = aom_sub_pixel_variance8x4_ssse3; + aom_sub_pixel_variance8x8 = aom_sub_pixel_variance8x8_sse2; + if (flags & HAS_SSSE3) aom_sub_pixel_variance8x8 = aom_sub_pixel_variance8x8_ssse3; + aom_v_predictor_32x16 = aom_v_predictor_32x16_sse2; + if (flags & HAS_AVX2) aom_v_predictor_32x16 = aom_v_predictor_32x16_avx2; + aom_v_predictor_32x32 = aom_v_predictor_32x32_sse2; + if (flags & HAS_AVX2) aom_v_predictor_32x32 = aom_v_predictor_32x32_avx2; + aom_variance16x16 = aom_variance16x16_sse2; + if (flags & HAS_AVX2) aom_variance16x16 = aom_variance16x16_avx2; + aom_variance32x16 = aom_variance32x16_sse2; + if (flags & HAS_AVX2) aom_variance32x16 = aom_variance32x16_avx2; + aom_variance32x32 = aom_variance32x32_sse2; + if (flags & HAS_AVX2) aom_variance32x32 = aom_variance32x32_avx2; + aom_variance64x32 = aom_variance64x32_sse2; + if (flags & HAS_AVX2) aom_variance64x32 = aom_variance64x32_avx2; + aom_variance64x64 = aom_variance64x64_sse2; + if (flags & HAS_AVX2) aom_variance64x64 = aom_variance64x64_avx2; +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libaom/config/win/mingw64/aom_scale_rtcd.h b/media/libaom/config/win/mingw64/aom_scale_rtcd.h new file mode 100644 index 000000000000..62f079065dc9 --- /dev/null +++ b/media/libaom/config/win/mingw64/aom_scale_rtcd.h @@ -0,0 +1,78 @@ +#ifndef AOM_SCALE_RTCD_H_ +#define AOM_SCALE_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +struct yv12_buffer_config; + +#ifdef __cplusplus +extern "C" { +#endif + +void aom_extend_frame_borders_c(struct yv12_buffer_config *ybf); +#define aom_extend_frame_borders aom_extend_frame_borders_c + +void aom_extend_frame_borders_y_c(struct yv12_buffer_config *ybf); +#define aom_extend_frame_borders_y aom_extend_frame_borders_y_c + +void aom_extend_frame_inner_borders_c(struct yv12_buffer_config *ybf); +#define aom_extend_frame_inner_borders aom_extend_frame_inner_borders_c + +void aom_horizontal_line_2_1_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width); +#define aom_horizontal_line_2_1_scale aom_horizontal_line_2_1_scale_c + +void aom_horizontal_line_5_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width); +#define aom_horizontal_line_5_3_scale aom_horizontal_line_5_3_scale_c + +void aom_horizontal_line_5_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width); +#define aom_horizontal_line_5_4_scale aom_horizontal_line_5_4_scale_c + +void aom_vertical_band_2_1_scale_c(unsigned char *source, int src_pitch, unsigned char *dest, int dest_pitch, unsigned int dest_width); +#define aom_vertical_band_2_1_scale aom_vertical_band_2_1_scale_c + +void aom_vertical_band_2_1_scale_i_c(unsigned char *source, int src_pitch, unsigned char *dest, int dest_pitch, unsigned int dest_width); +#define aom_vertical_band_2_1_scale_i aom_vertical_band_2_1_scale_i_c + +void aom_vertical_band_5_3_scale_c(unsigned char *source, int src_pitch, unsigned char *dest, int dest_pitch, unsigned int dest_width); +#define aom_vertical_band_5_3_scale aom_vertical_band_5_3_scale_c + +void aom_vertical_band_5_4_scale_c(unsigned char *source, int src_pitch, unsigned char *dest, int dest_pitch, unsigned int dest_width); +#define aom_vertical_band_5_4_scale aom_vertical_band_5_4_scale_c + +void aom_yv12_copy_frame_c(const struct yv12_buffer_config *src_bc, struct yv12_buffer_config *dst_bc); +#define aom_yv12_copy_frame aom_yv12_copy_frame_c + +void aom_yv12_copy_u_c(const struct yv12_buffer_config *src_bc, struct yv12_buffer_config *dst_bc); +#define aom_yv12_copy_u aom_yv12_copy_u_c + +void aom_yv12_copy_v_c(const struct yv12_buffer_config *src_bc, struct yv12_buffer_config *dst_bc); +#define aom_yv12_copy_v aom_yv12_copy_v_c + +void aom_yv12_copy_y_c(const struct yv12_buffer_config *src_ybc, struct yv12_buffer_config *dst_ybc); +#define aom_yv12_copy_y aom_yv12_copy_y_c + +void aom_yv12_extend_frame_borders_c(struct yv12_buffer_config *ybf); +#define aom_yv12_extend_frame_borders aom_yv12_extend_frame_borders_c + +void aom_scale_rtcd(void); + +#ifdef RTCD_C +#include "aom_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libaom/config/win/mingw64/av1_rtcd.h b/media/libaom/config/win/mingw64/av1_rtcd.h new file mode 100644 index 000000000000..66c0349aa9b1 --- /dev/null +++ b/media/libaom/config/win/mingw64/av1_rtcd.h @@ -0,0 +1,590 @@ +#ifndef AOM_RTCD_H_ +#define AOM_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +/* + * AV1 + */ + +#include "aom/aom_integer.h" +#include "aom_dsp/txfm_common.h" +#include "av1/common/common.h" +#include "av1/common/enums.h" +#include "av1/common/quant_common.h" +#include "av1/common/filter.h" +#include "av1/common/convolve.h" +#include "av1/common/av1_txfm.h" +#include "av1/common/odintrin.h" + +struct macroblockd; + +/* Encoder forward decls */ +struct macroblock; +struct txfm_param; +struct aom_variance_vtable; +struct search_site_config; +struct mv; +union int_mv; +struct yv12_buffer_config; + +#ifdef __cplusplus +extern "C" { +#endif + +void apply_selfguided_restoration_c(uint8_t *dat, int width, int height, int stride, int eps, int *xqd, uint8_t *dst, int dst_stride, int32_t *tmpbuf); +void apply_selfguided_restoration_sse4_1(uint8_t *dat, int width, int height, int stride, int eps, int *xqd, uint8_t *dst, int dst_stride, int32_t *tmpbuf); +RTCD_EXTERN void (*apply_selfguided_restoration)(uint8_t *dat, int width, int height, int stride, int eps, int *xqd, uint8_t *dst, int dst_stride, int32_t *tmpbuf); + +void apply_selfguided_restoration_highbd_c(uint16_t *dat, int width, int height, int stride, int bit_depth, int eps, int *xqd, uint16_t *dst, int dst_stride, int32_t *tmpbuf); +void apply_selfguided_restoration_highbd_sse4_1(uint16_t *dat, int width, int height, int stride, int bit_depth, int eps, int *xqd, uint16_t *dst, int dst_stride, int32_t *tmpbuf); +RTCD_EXTERN void (*apply_selfguided_restoration_highbd)(uint16_t *dat, int width, int height, int stride, int bit_depth, int eps, int *xqd, uint16_t *dst, int dst_stride, int32_t *tmpbuf); + +int64_t av1_block_error_c(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); +int64_t av1_block_error_avx2(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); +RTCD_EXTERN int64_t (*av1_block_error)(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); + +void av1_convolve_2d_c(const uint8_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params); +void av1_convolve_2d_sse2(const uint8_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params); +#define av1_convolve_2d av1_convolve_2d_sse2 + +void av1_convolve_2d_scale_c(const uint8_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_qn, const int x_step_qn, const int subpel_y_q4, const int y_step_qn, ConvolveParams *conv_params); +void av1_convolve_2d_scale_sse4_1(const uint8_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_qn, const int x_step_qn, const int subpel_y_q4, const int y_step_qn, ConvolveParams *conv_params); +RTCD_EXTERN void (*av1_convolve_2d_scale)(const uint8_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_qn, const int x_step_qn, const int subpel_y_q4, const int y_step_qn, ConvolveParams *conv_params); + +void av1_convolve_horiz_c(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, ConvolveParams *conv_params); +void av1_convolve_horiz_ssse3(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, ConvolveParams *conv_params); +RTCD_EXTERN void (*av1_convolve_horiz)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, ConvolveParams *conv_params); + +void av1_convolve_rounding_c(const int32_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, int bits); +void av1_convolve_rounding_avx2(const int32_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, int bits); +RTCD_EXTERN void (*av1_convolve_rounding)(const int32_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, int bits); + +void av1_convolve_vert_c(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, ConvolveParams *conv_params); +void av1_convolve_vert_ssse3(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, ConvolveParams *conv_params); +RTCD_EXTERN void (*av1_convolve_vert)(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, ConvolveParams *conv_params); + +int av1_diamond_search_sad_c(struct macroblock *x, const struct search_site_config *cfg, struct mv *ref_mv, struct mv *best_mv, int search_param, int sad_per_bit, int *num00, const struct aom_variance_vtable *fn_ptr, const struct mv *center_mv); +#define av1_diamond_search_sad av1_diamond_search_sad_c + +void av1_fht16x16_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht16x16_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht16x16_avx2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +RTCD_EXTERN void (*av1_fht16x16)(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); + +void av1_fht16x32_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht16x32_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht16x32 av1_fht16x32_sse2 + +void av1_fht16x4_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht16x4 av1_fht16x4_c + +void av1_fht16x8_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht16x8_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht16x8 av1_fht16x8_sse2 + +void av1_fht32x16_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht32x16_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht32x16 av1_fht32x16_sse2 + +void av1_fht32x32_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht32x32_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht32x32_avx2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +RTCD_EXTERN void (*av1_fht32x32)(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); + +void av1_fht32x8_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht32x8 av1_fht32x8_c + +void av1_fht4x16_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht4x16 av1_fht4x16_c + +void av1_fht4x4_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht4x4_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht4x4 av1_fht4x4_sse2 + +void av1_fht4x8_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht4x8_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht4x8 av1_fht4x8_sse2 + +void av1_fht8x16_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht8x16_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht8x16 av1_fht8x16_sse2 + +void av1_fht8x32_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht8x32 av1_fht8x32_c + +void av1_fht8x4_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht8x4_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht8x4 av1_fht8x4_sse2 + +void av1_fht8x8_c(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +void av1_fht8x8_sse2(const int16_t *input, tran_low_t *output, int stride, struct txfm_param *param); +#define av1_fht8x8 av1_fht8x8_sse2 + +void av1_filter_intra_edge_c(uint8_t *p, int sz, int strength); +void av1_filter_intra_edge_sse4_1(uint8_t *p, int sz, int strength); +RTCD_EXTERN void (*av1_filter_intra_edge)(uint8_t *p, int sz, int strength); + +void av1_filter_intra_edge_high_c(uint16_t *p, int sz, int strength); +void av1_filter_intra_edge_high_sse4_1(uint16_t *p, int sz, int strength); +RTCD_EXTERN void (*av1_filter_intra_edge_high)(uint16_t *p, int sz, int strength); + +int av1_full_range_search_c(const struct macroblock *x, const struct search_site_config *cfg, struct mv *ref_mv, struct mv *best_mv, int search_param, int sad_per_bit, int *num00, const struct aom_variance_vtable *fn_ptr, const struct mv *center_mv); +#define av1_full_range_search av1_full_range_search_c + +int av1_full_search_sad_c(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct aom_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); +int av1_full_search_sadx3(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct aom_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); +int av1_full_search_sadx8(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct aom_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); +RTCD_EXTERN int (*av1_full_search_sad)(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct aom_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); + +void av1_fwd_idtx_c(const int16_t *src_diff, tran_low_t *coeff, int stride, int bsx, int bsy, TX_TYPE tx_type); +#define av1_fwd_idtx av1_fwd_idtx_c + +void av1_fwd_txfm2d_16x16_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_fwd_txfm2d_16x16_sse4_1(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_fwd_txfm2d_16x16)(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_fwd_txfm2d_16x32_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_fwd_txfm2d_16x32 av1_fwd_txfm2d_16x32_c + +void av1_fwd_txfm2d_16x8_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_fwd_txfm2d_16x8 av1_fwd_txfm2d_16x8_c + +void av1_fwd_txfm2d_32x16_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_fwd_txfm2d_32x16 av1_fwd_txfm2d_32x16_c + +void av1_fwd_txfm2d_32x32_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_fwd_txfm2d_32x32_sse4_1(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_fwd_txfm2d_32x32)(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_fwd_txfm2d_4x4_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_fwd_txfm2d_4x4_sse4_1(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_fwd_txfm2d_4x4)(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_fwd_txfm2d_4x8_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_fwd_txfm2d_4x8 av1_fwd_txfm2d_4x8_c + +void av1_fwd_txfm2d_8x16_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_fwd_txfm2d_8x16 av1_fwd_txfm2d_8x16_c + +void av1_fwd_txfm2d_8x4_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_fwd_txfm2d_8x4 av1_fwd_txfm2d_8x4_c + +void av1_fwd_txfm2d_8x8_c(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_fwd_txfm2d_8x8_sse4_1(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_fwd_txfm2d_8x8)(const int16_t *input, int32_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_fwht4x4_c(const int16_t *input, tran_low_t *output, int stride); +#define av1_fwht4x4 av1_fwht4x4_c + +int64_t av1_highbd_block_error_c(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz, int bd); +int64_t av1_highbd_block_error_sse2(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz, int bd); +#define av1_highbd_block_error av1_highbd_block_error_sse2 + +void av1_highbd_convolve8_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void av1_highbd_convolve8_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve8 av1_highbd_convolve8_sse2 + +void av1_highbd_convolve8_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void av1_highbd_convolve8_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve8_avg av1_highbd_convolve8_avg_sse2 + +void av1_highbd_convolve8_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void av1_highbd_convolve8_avg_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve8_avg_horiz av1_highbd_convolve8_avg_horiz_sse2 + +void av1_highbd_convolve8_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void av1_highbd_convolve8_avg_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve8_avg_vert av1_highbd_convolve8_avg_vert_sse2 + +void av1_highbd_convolve8_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void av1_highbd_convolve8_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve8_horiz av1_highbd_convolve8_horiz_sse2 + +void av1_highbd_convolve8_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +void av1_highbd_convolve8_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve8_vert av1_highbd_convolve8_vert_sse2 + +void av1_highbd_convolve_2d_c(const uint16_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params, int bd); +void av1_highbd_convolve_2d_ssse3(const uint16_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params, int bd); +RTCD_EXTERN void (*av1_highbd_convolve_2d)(const uint16_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int subpel_y_q4, ConvolveParams *conv_params, int bd); + +void av1_highbd_convolve_2d_scale_c(const uint16_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int x_step_qn, const int subpel_y_q4, const int y_step_qn, ConvolveParams *conv_params, int bd); +void av1_highbd_convolve_2d_scale_sse4_1(const uint16_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int x_step_qn, const int subpel_y_q4, const int y_step_qn, ConvolveParams *conv_params, int bd); +RTCD_EXTERN void (*av1_highbd_convolve_2d_scale)(const uint16_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride, int w, int h, InterpFilterParams *filter_params_x, InterpFilterParams *filter_params_y, const int subpel_x_q4, const int x_step_qn, const int subpel_y_q4, const int y_step_qn, ConvolveParams *conv_params, int bd); + +void av1_highbd_convolve_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve_avg av1_highbd_convolve_avg_c + +void av1_highbd_convolve_copy_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h, int bps); +#define av1_highbd_convolve_copy av1_highbd_convolve_copy_c + +void av1_highbd_convolve_horiz_c(const uint16_t *src, int src_stride, uint16_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, int avg, int bd); +void av1_highbd_convolve_horiz_sse4_1(const uint16_t *src, int src_stride, uint16_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, int avg, int bd); +RTCD_EXTERN void (*av1_highbd_convolve_horiz)(const uint16_t *src, int src_stride, uint16_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, int avg, int bd); + +void av1_highbd_convolve_init_c(void); +void av1_highbd_convolve_init_sse4_1(void); +RTCD_EXTERN void (*av1_highbd_convolve_init)(void); + +void av1_highbd_convolve_rounding_c(const int32_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, int bits, int bd); +void av1_highbd_convolve_rounding_avx2(const int32_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, int bits, int bd); +RTCD_EXTERN void (*av1_highbd_convolve_rounding)(const int32_t *src, int src_stride, uint8_t *dst, int dst_stride, int w, int h, int bits, int bd); + +void av1_highbd_convolve_vert_c(const uint16_t *src, int src_stride, uint16_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, int avg, int bd); +void av1_highbd_convolve_vert_sse4_1(const uint16_t *src, int src_stride, uint16_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, int avg, int bd); +RTCD_EXTERN void (*av1_highbd_convolve_vert)(const uint16_t *src, int src_stride, uint16_t *dst, int dst_stride, int w, int h, const InterpFilterParams fp, const int subpel_x_q4, int x_step_q4, int avg, int bd); + +void av1_highbd_fwht4x4_c(const int16_t *input, tran_low_t *output, int stride); +#define av1_highbd_fwht4x4 av1_highbd_fwht4x4_c + +void av1_highbd_iht16x16_256_add_c(const tran_low_t *input, uint8_t *output, int pitch, const struct txfm_param *param); +#define av1_highbd_iht16x16_256_add av1_highbd_iht16x16_256_add_c + +void av1_highbd_iht16x32_512_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht16x32_512_add av1_highbd_iht16x32_512_add_c + +void av1_highbd_iht16x4_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht16x4_64_add av1_highbd_iht16x4_64_add_c + +void av1_highbd_iht16x8_128_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht16x8_128_add av1_highbd_iht16x8_128_add_c + +void av1_highbd_iht32x16_512_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht32x16_512_add av1_highbd_iht32x16_512_add_c + +void av1_highbd_iht32x8_256_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht32x8_256_add av1_highbd_iht32x8_256_add_c + +void av1_highbd_iht4x16_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht4x16_64_add av1_highbd_iht4x16_64_add_c + +void av1_highbd_iht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht4x4_16_add av1_highbd_iht4x4_16_add_c + +void av1_highbd_iht4x8_32_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht4x8_32_add av1_highbd_iht4x8_32_add_c + +void av1_highbd_iht8x16_128_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht8x16_128_add av1_highbd_iht8x16_128_add_c + +void av1_highbd_iht8x32_256_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht8x32_256_add av1_highbd_iht8x32_256_add_c + +void av1_highbd_iht8x4_32_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht8x4_32_add av1_highbd_iht8x4_32_add_c + +void av1_highbd_iht8x8_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_highbd_iht8x8_64_add av1_highbd_iht8x8_64_add_c + +void av1_highbd_quantize_fp_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan, int log_scale); +void av1_highbd_quantize_fp_sse4_1(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan, int log_scale); +void av1_highbd_quantize_fp_avx2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan, int log_scale); +RTCD_EXTERN void (*av1_highbd_quantize_fp)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan, int log_scale); + +void av1_highbd_temporal_filter_apply_c(uint8_t *frame1, unsigned int stride, uint8_t *frame2, unsigned int block_width, unsigned int block_height, int strength, int filter_weight, unsigned int *accumulator, uint16_t *count); +#define av1_highbd_temporal_filter_apply av1_highbd_temporal_filter_apply_c + +void av1_highbd_warp_affine_c(const int32_t *mat, const uint16_t *ref, int width, int height, int stride, uint16_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, int bd, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); +void av1_highbd_warp_affine_ssse3(const int32_t *mat, const uint16_t *ref, int width, int height, int stride, uint16_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, int bd, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); +RTCD_EXTERN void (*av1_highbd_warp_affine)(const int32_t *mat, const uint16_t *ref, int width, int height, int stride, uint16_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, int bd, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); + +void av1_highpass_filter_c(uint8_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); +void av1_highpass_filter_sse4_1(uint8_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); +RTCD_EXTERN void (*av1_highpass_filter)(uint8_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); + +void av1_highpass_filter_highbd_c(uint16_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); +void av1_highpass_filter_highbd_sse4_1(uint16_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); +RTCD_EXTERN void (*av1_highpass_filter_highbd)(uint16_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); + +void av1_iht16x16_256_add_c(const tran_low_t *input, uint8_t *output, int pitch, const struct txfm_param *param); +void av1_iht16x16_256_add_sse2(const tran_low_t *input, uint8_t *output, int pitch, const struct txfm_param *param); +void av1_iht16x16_256_add_avx2(const tran_low_t *input, uint8_t *output, int pitch, const struct txfm_param *param); +RTCD_EXTERN void (*av1_iht16x16_256_add)(const tran_low_t *input, uint8_t *output, int pitch, const struct txfm_param *param); + +void av1_iht16x32_512_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht16x32_512_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht16x32_512_add av1_iht16x32_512_add_sse2 + +void av1_iht16x4_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht16x4_64_add av1_iht16x4_64_add_c + +void av1_iht16x8_128_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht16x8_128_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht16x8_128_add av1_iht16x8_128_add_sse2 + +void av1_iht32x16_512_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht32x16_512_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht32x16_512_add av1_iht32x16_512_add_sse2 + +void av1_iht32x32_1024_add_c(const tran_low_t *input, uint8_t *output, int pitch, const struct txfm_param *param); +#define av1_iht32x32_1024_add av1_iht32x32_1024_add_c + +void av1_iht32x8_256_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht32x8_256_add av1_iht32x8_256_add_c + +void av1_iht4x16_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht4x16_64_add av1_iht4x16_64_add_c + +void av1_iht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht4x4_16_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht4x4_16_add av1_iht4x4_16_add_sse2 + +void av1_iht4x8_32_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht4x8_32_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht4x8_32_add av1_iht4x8_32_add_sse2 + +void av1_iht8x16_128_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht8x16_128_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht8x16_128_add av1_iht8x16_128_add_sse2 + +void av1_iht8x32_256_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht8x32_256_add av1_iht8x32_256_add_c + +void av1_iht8x4_32_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht8x4_32_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht8x4_32_add av1_iht8x4_32_add_sse2 + +void av1_iht8x8_64_add_c(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +void av1_iht8x8_64_add_sse2(const tran_low_t *input, uint8_t *dest, int dest_stride, const struct txfm_param *param); +#define av1_iht8x8_64_add av1_iht8x8_64_add_sse2 + +void av1_inv_txfm2d_add_16x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_inv_txfm2d_add_16x16_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_inv_txfm2d_add_16x16)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_inv_txfm2d_add_16x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_inv_txfm2d_add_16x32 av1_inv_txfm2d_add_16x32_c + +void av1_inv_txfm2d_add_16x8_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_inv_txfm2d_add_16x8 av1_inv_txfm2d_add_16x8_c + +void av1_inv_txfm2d_add_32x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_inv_txfm2d_add_32x16 av1_inv_txfm2d_add_32x16_c + +void av1_inv_txfm2d_add_32x32_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_inv_txfm2d_add_32x32_avx2(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_inv_txfm2d_add_32x32)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_inv_txfm2d_add_4x4_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_inv_txfm2d_add_4x4_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_inv_txfm2d_add_4x4)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_inv_txfm2d_add_4x8_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_inv_txfm2d_add_4x8 av1_inv_txfm2d_add_4x8_c + +void av1_inv_txfm2d_add_8x16_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_inv_txfm2d_add_8x16 av1_inv_txfm2d_add_8x16_c + +void av1_inv_txfm2d_add_8x4_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +#define av1_inv_txfm2d_add_8x4 av1_inv_txfm2d_add_8x4_c + +void av1_inv_txfm2d_add_8x8_c(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +void av1_inv_txfm2d_add_8x8_sse4_1(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); +RTCD_EXTERN void (*av1_inv_txfm2d_add_8x8)(const int32_t *input, uint16_t *output, int stride, TX_TYPE tx_type, int bd); + +void av1_lowbd_convolve_init_c(void); +void av1_lowbd_convolve_init_ssse3(void); +RTCD_EXTERN void (*av1_lowbd_convolve_init)(void); + +void av1_quantize_b_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan, const qm_val_t * qm_ptr, const qm_val_t * iqm_ptr, int log_scale); +#define av1_quantize_b av1_quantize_b_c + +void av1_quantize_fp_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void av1_quantize_fp_sse2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void av1_quantize_fp_avx2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*av1_quantize_fp)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void av1_quantize_fp_32x32_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void av1_quantize_fp_32x32_avx2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*av1_quantize_fp_32x32)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void av1_selfguided_restoration_c(uint8_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); +void av1_selfguided_restoration_sse4_1(uint8_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); +RTCD_EXTERN void (*av1_selfguided_restoration)(uint8_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int r, int eps); + +void av1_selfguided_restoration_highbd_c(uint16_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int bit_depth, int r, int eps); +void av1_selfguided_restoration_highbd_sse4_1(uint16_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int bit_depth, int r, int eps); +RTCD_EXTERN void (*av1_selfguided_restoration_highbd)(uint16_t *dgd, int width, int height, int stride, int32_t *dst, int dst_stride, int bit_depth, int r, int eps); + +void av1_temporal_filter_apply_c(uint8_t *frame1, unsigned int stride, uint8_t *frame2, unsigned int block_width, unsigned int block_height, int strength, int filter_weight, unsigned int *accumulator, uint16_t *count); +void av1_temporal_filter_apply_sse2(uint8_t *frame1, unsigned int stride, uint8_t *frame2, unsigned int block_width, unsigned int block_height, int strength, int filter_weight, unsigned int *accumulator, uint16_t *count); +#define av1_temporal_filter_apply av1_temporal_filter_apply_sse2 + +void av1_upsample_intra_edge_c(uint8_t *p, int sz); +void av1_upsample_intra_edge_sse4_1(uint8_t *p, int sz); +RTCD_EXTERN void (*av1_upsample_intra_edge)(uint8_t *p, int sz); + +void av1_upsample_intra_edge_high_c(uint16_t *p, int sz, int bd); +void av1_upsample_intra_edge_high_sse4_1(uint16_t *p, int sz, int bd); +RTCD_EXTERN void (*av1_upsample_intra_edge_high)(uint16_t *p, int sz, int bd); + +void av1_warp_affine_c(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); +void av1_warp_affine_sse2(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); +void av1_warp_affine_ssse3(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); +RTCD_EXTERN void (*av1_warp_affine)(const int32_t *mat, const uint8_t *ref, int width, int height, int stride, uint8_t *pred, int p_col, int p_row, int p_width, int p_height, int p_stride, int subsampling_x, int subsampling_y, ConvolveParams *conv_params, int16_t alpha, int16_t beta, int16_t gamma, int16_t delta); + +void av1_wedge_compute_delta_squares_c(int16_t *d, const int16_t *a, const int16_t *b, int N); +void av1_wedge_compute_delta_squares_sse2(int16_t *d, const int16_t *a, const int16_t *b, int N); +#define av1_wedge_compute_delta_squares av1_wedge_compute_delta_squares_sse2 + +int av1_wedge_sign_from_residuals_c(const int16_t *ds, const uint8_t *m, int N, int64_t limit); +int av1_wedge_sign_from_residuals_sse2(const int16_t *ds, const uint8_t *m, int N, int64_t limit); +#define av1_wedge_sign_from_residuals av1_wedge_sign_from_residuals_sse2 + +uint64_t av1_wedge_sse_from_residuals_c(const int16_t *r1, const int16_t *d, const uint8_t *m, int N); +uint64_t av1_wedge_sse_from_residuals_sse2(const int16_t *r1, const int16_t *d, const uint8_t *m, int N); +#define av1_wedge_sse_from_residuals av1_wedge_sse_from_residuals_sse2 + +void cdef_filter_block_c(uint8_t *dst8, uint16_t *dst16, int dstride, const uint16_t *in, int pri_strength, int sec_strength, int dir, int pri_damping, int sec_damping, int bsize, int max); +void cdef_filter_block_sse2(uint8_t *dst8, uint16_t *dst16, int dstride, const uint16_t *in, int pri_strength, int sec_strength, int dir, int pri_damping, int sec_damping, int bsize, int max); +void cdef_filter_block_ssse3(uint8_t *dst8, uint16_t *dst16, int dstride, const uint16_t *in, int pri_strength, int sec_strength, int dir, int pri_damping, int sec_damping, int bsize, int max); +void cdef_filter_block_sse4_1(uint8_t *dst8, uint16_t *dst16, int dstride, const uint16_t *in, int pri_strength, int sec_strength, int dir, int pri_damping, int sec_damping, int bsize, int max); +void cdef_filter_block_avx2(uint8_t *dst8, uint16_t *dst16, int dstride, const uint16_t *in, int pri_strength, int sec_strength, int dir, int pri_damping, int sec_damping, int bsize, int max); +RTCD_EXTERN void (*cdef_filter_block)(uint8_t *dst8, uint16_t *dst16, int dstride, const uint16_t *in, int pri_strength, int sec_strength, int dir, int pri_damping, int sec_damping, int bsize, int max); + +int cdef_find_dir_c(const uint16_t *img, int stride, int32_t *var, int coeff_shift); +int cdef_find_dir_sse2(const uint16_t *img, int stride, int32_t *var, int coeff_shift); +int cdef_find_dir_ssse3(const uint16_t *img, int stride, int32_t *var, int coeff_shift); +int cdef_find_dir_sse4_1(const uint16_t *img, int stride, int32_t *var, int coeff_shift); +int cdef_find_dir_avx2(const uint16_t *img, int stride, int32_t *var, int coeff_shift); +RTCD_EXTERN int (*cdef_find_dir)(const uint16_t *img, int stride, int32_t *var, int coeff_shift); + +double compute_cross_correlation_c(unsigned char *im1, int stride1, int x1, int y1, unsigned char *im2, int stride2, int x2, int y2); +double compute_cross_correlation_sse4_1(unsigned char *im1, int stride1, int x1, int y1, unsigned char *im2, int stride2, int x2, int y2); +RTCD_EXTERN double (*compute_cross_correlation)(unsigned char *im1, int stride1, int x1, int y1, unsigned char *im2, int stride2, int x2, int y2); + +void copy_rect8_16bit_to_16bit_c(uint16_t *dst, int dstride, const uint16_t *src, int sstride, int v, int h); +void copy_rect8_16bit_to_16bit_sse2(uint16_t *dst, int dstride, const uint16_t *src, int sstride, int v, int h); +void copy_rect8_16bit_to_16bit_ssse3(uint16_t *dst, int dstride, const uint16_t *src, int sstride, int v, int h); +void copy_rect8_16bit_to_16bit_sse4_1(uint16_t *dst, int dstride, const uint16_t *src, int sstride, int v, int h); +void copy_rect8_16bit_to_16bit_avx2(uint16_t *dst, int dstride, const uint16_t *src, int sstride, int v, int h); +RTCD_EXTERN void (*copy_rect8_16bit_to_16bit)(uint16_t *dst, int dstride, const uint16_t *src, int sstride, int v, int h); + +void copy_rect8_8bit_to_16bit_c(uint16_t *dst, int dstride, const uint8_t *src, int sstride, int v, int h); +void copy_rect8_8bit_to_16bit_sse2(uint16_t *dst, int dstride, const uint8_t *src, int sstride, int v, int h); +void copy_rect8_8bit_to_16bit_ssse3(uint16_t *dst, int dstride, const uint8_t *src, int sstride, int v, int h); +void copy_rect8_8bit_to_16bit_sse4_1(uint16_t *dst, int dstride, const uint8_t *src, int sstride, int v, int h); +void copy_rect8_8bit_to_16bit_avx2(uint16_t *dst, int dstride, const uint8_t *src, int sstride, int v, int h); +RTCD_EXTERN void (*copy_rect8_8bit_to_16bit)(uint16_t *dst, int dstride, const uint8_t *src, int sstride, int v, int h); + +void aom_rtcd(void); + +#ifdef RTCD_C +#include "aom_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + + apply_selfguided_restoration = apply_selfguided_restoration_c; + if (flags & HAS_SSE4_1) apply_selfguided_restoration = apply_selfguided_restoration_sse4_1; + apply_selfguided_restoration_highbd = apply_selfguided_restoration_highbd_c; + if (flags & HAS_SSE4_1) apply_selfguided_restoration_highbd = apply_selfguided_restoration_highbd_sse4_1; + av1_block_error = av1_block_error_c; + if (flags & HAS_AVX2) av1_block_error = av1_block_error_avx2; + av1_convolve_2d_scale = av1_convolve_2d_scale_c; + if (flags & HAS_SSE4_1) av1_convolve_2d_scale = av1_convolve_2d_scale_sse4_1; + av1_convolve_horiz = av1_convolve_horiz_c; + if (flags & HAS_SSSE3) av1_convolve_horiz = av1_convolve_horiz_ssse3; + av1_convolve_rounding = av1_convolve_rounding_c; + if (flags & HAS_AVX2) av1_convolve_rounding = av1_convolve_rounding_avx2; + av1_convolve_vert = av1_convolve_vert_c; + if (flags & HAS_SSSE3) av1_convolve_vert = av1_convolve_vert_ssse3; + av1_fht16x16 = av1_fht16x16_sse2; + if (flags & HAS_AVX2) av1_fht16x16 = av1_fht16x16_avx2; + av1_fht32x32 = av1_fht32x32_sse2; + if (flags & HAS_AVX2) av1_fht32x32 = av1_fht32x32_avx2; + av1_filter_intra_edge = av1_filter_intra_edge_c; + if (flags & HAS_SSE4_1) av1_filter_intra_edge = av1_filter_intra_edge_sse4_1; + av1_filter_intra_edge_high = av1_filter_intra_edge_high_c; + if (flags & HAS_SSE4_1) av1_filter_intra_edge_high = av1_filter_intra_edge_high_sse4_1; + av1_full_search_sad = av1_full_search_sad_c; + if (flags & HAS_SSE3) av1_full_search_sad = av1_full_search_sadx3; + if (flags & HAS_SSE4_1) av1_full_search_sad = av1_full_search_sadx8; + av1_fwd_txfm2d_16x16 = av1_fwd_txfm2d_16x16_c; + if (flags & HAS_SSE4_1) av1_fwd_txfm2d_16x16 = av1_fwd_txfm2d_16x16_sse4_1; + av1_fwd_txfm2d_32x32 = av1_fwd_txfm2d_32x32_c; + if (flags & HAS_SSE4_1) av1_fwd_txfm2d_32x32 = av1_fwd_txfm2d_32x32_sse4_1; + av1_fwd_txfm2d_4x4 = av1_fwd_txfm2d_4x4_c; + if (flags & HAS_SSE4_1) av1_fwd_txfm2d_4x4 = av1_fwd_txfm2d_4x4_sse4_1; + av1_fwd_txfm2d_8x8 = av1_fwd_txfm2d_8x8_c; + if (flags & HAS_SSE4_1) av1_fwd_txfm2d_8x8 = av1_fwd_txfm2d_8x8_sse4_1; + av1_highbd_convolve_2d = av1_highbd_convolve_2d_c; + if (flags & HAS_SSSE3) av1_highbd_convolve_2d = av1_highbd_convolve_2d_ssse3; + av1_highbd_convolve_2d_scale = av1_highbd_convolve_2d_scale_c; + if (flags & HAS_SSE4_1) av1_highbd_convolve_2d_scale = av1_highbd_convolve_2d_scale_sse4_1; + av1_highbd_convolve_horiz = av1_highbd_convolve_horiz_c; + if (flags & HAS_SSE4_1) av1_highbd_convolve_horiz = av1_highbd_convolve_horiz_sse4_1; + av1_highbd_convolve_init = av1_highbd_convolve_init_c; + if (flags & HAS_SSE4_1) av1_highbd_convolve_init = av1_highbd_convolve_init_sse4_1; + av1_highbd_convolve_rounding = av1_highbd_convolve_rounding_c; + if (flags & HAS_AVX2) av1_highbd_convolve_rounding = av1_highbd_convolve_rounding_avx2; + av1_highbd_convolve_vert = av1_highbd_convolve_vert_c; + if (flags & HAS_SSE4_1) av1_highbd_convolve_vert = av1_highbd_convolve_vert_sse4_1; + av1_highbd_quantize_fp = av1_highbd_quantize_fp_c; + if (flags & HAS_SSE4_1) av1_highbd_quantize_fp = av1_highbd_quantize_fp_sse4_1; + if (flags & HAS_AVX2) av1_highbd_quantize_fp = av1_highbd_quantize_fp_avx2; + av1_highbd_warp_affine = av1_highbd_warp_affine_c; + if (flags & HAS_SSSE3) av1_highbd_warp_affine = av1_highbd_warp_affine_ssse3; + av1_highpass_filter = av1_highpass_filter_c; + if (flags & HAS_SSE4_1) av1_highpass_filter = av1_highpass_filter_sse4_1; + av1_highpass_filter_highbd = av1_highpass_filter_highbd_c; + if (flags & HAS_SSE4_1) av1_highpass_filter_highbd = av1_highpass_filter_highbd_sse4_1; + av1_iht16x16_256_add = av1_iht16x16_256_add_sse2; + if (flags & HAS_AVX2) av1_iht16x16_256_add = av1_iht16x16_256_add_avx2; + av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_c; + if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_16x16 = av1_inv_txfm2d_add_16x16_sse4_1; + av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_c; + if (flags & HAS_AVX2) av1_inv_txfm2d_add_32x32 = av1_inv_txfm2d_add_32x32_avx2; + av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_c; + if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_4x4 = av1_inv_txfm2d_add_4x4_sse4_1; + av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_c; + if (flags & HAS_SSE4_1) av1_inv_txfm2d_add_8x8 = av1_inv_txfm2d_add_8x8_sse4_1; + av1_lowbd_convolve_init = av1_lowbd_convolve_init_c; + if (flags & HAS_SSSE3) av1_lowbd_convolve_init = av1_lowbd_convolve_init_ssse3; + av1_quantize_fp = av1_quantize_fp_sse2; + if (flags & HAS_AVX2) av1_quantize_fp = av1_quantize_fp_avx2; + av1_quantize_fp_32x32 = av1_quantize_fp_32x32_c; + if (flags & HAS_AVX2) av1_quantize_fp_32x32 = av1_quantize_fp_32x32_avx2; + av1_selfguided_restoration = av1_selfguided_restoration_c; + if (flags & HAS_SSE4_1) av1_selfguided_restoration = av1_selfguided_restoration_sse4_1; + av1_selfguided_restoration_highbd = av1_selfguided_restoration_highbd_c; + if (flags & HAS_SSE4_1) av1_selfguided_restoration_highbd = av1_selfguided_restoration_highbd_sse4_1; + av1_upsample_intra_edge = av1_upsample_intra_edge_c; + if (flags & HAS_SSE4_1) av1_upsample_intra_edge = av1_upsample_intra_edge_sse4_1; + av1_upsample_intra_edge_high = av1_upsample_intra_edge_high_c; + if (flags & HAS_SSE4_1) av1_upsample_intra_edge_high = av1_upsample_intra_edge_high_sse4_1; + av1_warp_affine = av1_warp_affine_sse2; + if (flags & HAS_SSSE3) av1_warp_affine = av1_warp_affine_ssse3; + cdef_filter_block = cdef_filter_block_sse2; + if (flags & HAS_SSSE3) cdef_filter_block = cdef_filter_block_ssse3; + if (flags & HAS_SSE4_1) cdef_filter_block = cdef_filter_block_sse4_1; + if (flags & HAS_AVX2) cdef_filter_block = cdef_filter_block_avx2; + cdef_find_dir = cdef_find_dir_sse2; + if (flags & HAS_SSSE3) cdef_find_dir = cdef_find_dir_ssse3; + if (flags & HAS_SSE4_1) cdef_find_dir = cdef_find_dir_sse4_1; + if (flags & HAS_AVX2) cdef_find_dir = cdef_find_dir_avx2; + compute_cross_correlation = compute_cross_correlation_c; + if (flags & HAS_SSE4_1) compute_cross_correlation = compute_cross_correlation_sse4_1; + copy_rect8_16bit_to_16bit = copy_rect8_16bit_to_16bit_sse2; + if (flags & HAS_SSSE3) copy_rect8_16bit_to_16bit = copy_rect8_16bit_to_16bit_ssse3; + if (flags & HAS_SSE4_1) copy_rect8_16bit_to_16bit = copy_rect8_16bit_to_16bit_sse4_1; + if (flags & HAS_AVX2) copy_rect8_16bit_to_16bit = copy_rect8_16bit_to_16bit_avx2; + copy_rect8_8bit_to_16bit = copy_rect8_8bit_to_16bit_sse2; + if (flags & HAS_SSSE3) copy_rect8_8bit_to_16bit = copy_rect8_8bit_to_16bit_ssse3; + if (flags & HAS_SSE4_1) copy_rect8_8bit_to_16bit = copy_rect8_8bit_to_16bit_sse4_1; + if (flags & HAS_AVX2) copy_rect8_8bit_to_16bit = copy_rect8_8bit_to_16bit_avx2; +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libaom/generate_sources_mozbuild.sh b/media/libaom/generate_sources_mozbuild.sh old mode 100755 new mode 100644 index adf0cace6022..ef50a9503ba8 --- a/media/libaom/generate_sources_mozbuild.sh +++ b/media/libaom/generate_sources_mozbuild.sh @@ -199,6 +199,7 @@ gen_config_files mac/x64 "--target=x86_64-darwin9-gcc ${all_platforms} ${x86_pla gen_config_files win/x64 "--target=x86_64-win64-vs14 ${all_platforms} ${x86_platforms}" gen_config_files win/ia32 "--target=x86-win32-vs14 ${all_platforms} ${x86_platforms}" gen_config_files win/mingw32 "--target=x86-win32-gcc ${all_platforms} ${x86_platforms}" +gen_config_files win/mingw64 "--target=x86_64-win32-gcc ${all_platforms} ${x86_platforms}" gen_config_files linux/arm "--target=armv7-linux-gcc ${all_platforms} ${arm_platforms}" @@ -206,7 +207,9 @@ gen_config_files generic "--target=generic-gnu ${all_platforms}" # AOM doesn't know if mingw32 has winpthreads or not, and doesn't try to detect it. sed -i 's/HAVE_PTHREAD_H equ 0/HAVE_PTHREAD_H equ 1/' $BASE_DIR/$LIBAOM_CONFIG_DIR/win/mingw32/aom_config.asm +sed -i 's/HAVE_PTHREAD_H equ 0/HAVE_PTHREAD_H equ 1/' $BASE_DIR/$LIBAOM_CONFIG_DIR/win/mingw64/aom_config.asm sed -i 's/HAVE_PTHREAD_H 0/HAVE_PTHREAD_H 1/' $BASE_DIR/$LIBAOM_CONFIG_DIR/win/mingw32/aom_config.h +sed -i 's/HAVE_PTHREAD_H 0/HAVE_PTHREAD_H 1/' $BASE_DIR/$LIBAOM_CONFIG_DIR/win/mingw64/aom_config.h echo "Remove temporary directory." @@ -225,6 +228,7 @@ gen_rtcd_header mac/x64 x86_64 gen_rtcd_header win/x64 x86_64 gen_rtcd_header win/ia32 x86 gen_rtcd_header win/mingw32 x86 +gen_rtcd_header win/mingw64 x86_64 gen_rtcd_header linux/arm armv7 diff --git a/media/libaom/moz.build b/media/libaom/moz.build index ccade2204231..6f64762d4121 100644 --- a/media/libaom/moz.build +++ b/media/libaom/moz.build @@ -15,9 +15,14 @@ if CONFIG['CPU_ARCH'] == 'x86_64': SOURCES += files['X64_SOURCES'] USE_YASM = True if CONFIG['OS_TARGET'] == 'WINNT': - ASFLAGS += [ '-I%s/media/libaom/config/win/x64/' % TOPSRCDIR ] - LOCAL_INCLUDES += [ '/media/libaom/config/win/x64/' ] - EXPORTS.aom += [ 'config/win/x64/aom_config.h' ] + if CONFIG['CC_TYPE'] == 'gcc': + ASFLAGS += [ '-I%s/media/libaom/config/win/mingw64/' % TOPSRCDIR ] + LOCAL_INCLUDES += [ '/media/libaom/config/win/mingw64/' ] + EXPORTS.aom += [ 'config/win/mingw64/aom_config.h' ] + else: + ASFLAGS += [ '-I%s/media/libaom/config/win/x64/' % TOPSRCDIR ] + LOCAL_INCLUDES += [ '/media/libaom/config/win/x64/' ] + EXPORTS.aom += [ 'config/win/x64/aom_config.h' ] elif CONFIG['OS_TARGET'] == 'Darwin': ASFLAGS += [ '-I%s/media/libaom/config/mac/x64/' % TOPSRCDIR ] LOCAL_INCLUDES += [ '/media/libaom/config/mac/x64/' ]

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1448453 - Update libvpx to have a 64 bit mingw config. r=kinetik, a=jcristau
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 5a8dfc18b8b87bb952eeb59eb146f6091548616d Author: Tom Ritter <tom(a)mozilla.com> Date: Fri Mar 23 14:56:54 2018 -0500 Bug 1448453 - Update libvpx to have a 64 bit mingw config. r=kinetik, a=jcristau MozReview-Commit-ID: 1Dt3OcMgWii --HG-- extra : rebase_source : 98b1b48718e637bf3dc29aa44a218e8f06a6af62 extra : source : 5c5f3602567270308f6e2d51a226faaa159db692 --- media/libvpx/config/win/mingw64/vp8_rtcd.h | 264 +++++ media/libvpx/config/win/mingw64/vp9_rtcd.h | 140 +++ media/libvpx/config/win/mingw64/vpx_config.asm | 78 ++ media/libvpx/config/win/mingw64/vpx_config.c | 10 + media/libvpx/config/win/mingw64/vpx_config.h | 93 ++ media/libvpx/config/win/mingw64/vpx_dsp_rtcd.h | 1207 ++++++++++++++++++++++ media/libvpx/config/win/mingw64/vpx_scale_rtcd.h | 69 ++ media/libvpx/moz.build | 8 +- 8 files changed, 1867 insertions(+), 2 deletions(-) diff --git a/media/libvpx/config/win/mingw64/vp8_rtcd.h b/media/libvpx/config/win/mingw64/vp8_rtcd.h new file mode 100644 index 000000000000..472863970439 --- /dev/null +++ b/media/libvpx/config/win/mingw64/vp8_rtcd.h @@ -0,0 +1,264 @@ +#ifndef VP8_RTCD_H_ +#define VP8_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +/* + * VP8 + */ + +struct blockd; +struct macroblockd; +struct loop_filter_info; + +/* Encoder forward decls */ +struct block; +struct macroblock; +struct variance_vtable; +union int_mv; +struct yv12_buffer_config; + +#ifdef __cplusplus +extern "C" { +#endif + +void vp8_bilinear_predict16x16_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_bilinear_predict16x16_sse2(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_bilinear_predict16x16_ssse3(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +RTCD_EXTERN void (*vp8_bilinear_predict16x16)(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); + +void vp8_bilinear_predict4x4_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_bilinear_predict4x4_mmx(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +#define vp8_bilinear_predict4x4 vp8_bilinear_predict4x4_mmx + +void vp8_bilinear_predict8x4_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_bilinear_predict8x4_mmx(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +#define vp8_bilinear_predict8x4 vp8_bilinear_predict8x4_mmx + +void vp8_bilinear_predict8x8_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_bilinear_predict8x8_sse2(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_bilinear_predict8x8_ssse3(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +RTCD_EXTERN void (*vp8_bilinear_predict8x8)(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); + +void vp8_blend_b_c(unsigned char *y, unsigned char *u, unsigned char *v, int y1, int u1, int v1, int alpha, int stride); +#define vp8_blend_b vp8_blend_b_c + +void vp8_blend_mb_inner_c(unsigned char *y, unsigned char *u, unsigned char *v, int y1, int u1, int v1, int alpha, int stride); +#define vp8_blend_mb_inner vp8_blend_mb_inner_c + +void vp8_blend_mb_outer_c(unsigned char *y, unsigned char *u, unsigned char *v, int y1, int u1, int v1, int alpha, int stride); +#define vp8_blend_mb_outer vp8_blend_mb_outer_c + +int vp8_block_error_c(short *coeff, short *dqcoeff); +int vp8_block_error_sse2(short *coeff, short *dqcoeff); +#define vp8_block_error vp8_block_error_sse2 + +void vp8_copy32xn_c(const unsigned char *src_ptr, int source_stride, unsigned char *dst_ptr, int dst_stride, int n); +void vp8_copy32xn_sse2(const unsigned char *src_ptr, int source_stride, unsigned char *dst_ptr, int dst_stride, int n); +void vp8_copy32xn_sse3(const unsigned char *src_ptr, int source_stride, unsigned char *dst_ptr, int dst_stride, int n); +RTCD_EXTERN void (*vp8_copy32xn)(const unsigned char *src_ptr, int source_stride, unsigned char *dst_ptr, int dst_stride, int n); + +void vp8_copy_mem16x16_c(unsigned char *src, int src_pitch, unsigned char *dst, int dst_pitch); +void vp8_copy_mem16x16_sse2(unsigned char *src, int src_pitch, unsigned char *dst, int dst_pitch); +#define vp8_copy_mem16x16 vp8_copy_mem16x16_sse2 + +void vp8_copy_mem8x4_c(unsigned char *src, int src_pitch, unsigned char *dst, int dst_pitch); +void vp8_copy_mem8x4_mmx(unsigned char *src, int src_pitch, unsigned char *dst, int dst_pitch); +#define vp8_copy_mem8x4 vp8_copy_mem8x4_mmx + +void vp8_copy_mem8x8_c(unsigned char *src, int src_pitch, unsigned char *dst, int dst_pitch); +void vp8_copy_mem8x8_mmx(unsigned char *src, int src_pitch, unsigned char *dst, int dst_pitch); +#define vp8_copy_mem8x8 vp8_copy_mem8x8_mmx + +void vp8_dc_only_idct_add_c(short input, unsigned char *pred, int pred_stride, unsigned char *dst, int dst_stride); +void vp8_dc_only_idct_add_mmx(short input, unsigned char *pred, int pred_stride, unsigned char *dst, int dst_stride); +#define vp8_dc_only_idct_add vp8_dc_only_idct_add_mmx + +int vp8_denoiser_filter_c(unsigned char *mc_running_avg_y, int mc_avg_y_stride, unsigned char *running_avg_y, int avg_y_stride, unsigned char *sig, int sig_stride, unsigned int motion_magnitude, int increase_denoising); +int vp8_denoiser_filter_sse2(unsigned char *mc_running_avg_y, int mc_avg_y_stride, unsigned char *running_avg_y, int avg_y_stride, unsigned char *sig, int sig_stride, unsigned int motion_magnitude, int increase_denoising); +#define vp8_denoiser_filter vp8_denoiser_filter_sse2 + +int vp8_denoiser_filter_uv_c(unsigned char *mc_running_avg, int mc_avg_stride, unsigned char *running_avg, int avg_stride, unsigned char *sig, int sig_stride, unsigned int motion_magnitude, int increase_denoising); +int vp8_denoiser_filter_uv_sse2(unsigned char *mc_running_avg, int mc_avg_stride, unsigned char *running_avg, int avg_stride, unsigned char *sig, int sig_stride, unsigned int motion_magnitude, int increase_denoising); +#define vp8_denoiser_filter_uv vp8_denoiser_filter_uv_sse2 + +void vp8_dequant_idct_add_c(short *input, short *dq, unsigned char *output, int stride); +void vp8_dequant_idct_add_mmx(short *input, short *dq, unsigned char *output, int stride); +#define vp8_dequant_idct_add vp8_dequant_idct_add_mmx + +void vp8_dequant_idct_add_uv_block_c(short *q, short *dq, unsigned char *dst_u, unsigned char *dst_v, int stride, char *eobs); +void vp8_dequant_idct_add_uv_block_sse2(short *q, short *dq, unsigned char *dst_u, unsigned char *dst_v, int stride, char *eobs); +#define vp8_dequant_idct_add_uv_block vp8_dequant_idct_add_uv_block_sse2 + +void vp8_dequant_idct_add_y_block_c(short *q, short *dq, unsigned char *dst, int stride, char *eobs); +void vp8_dequant_idct_add_y_block_sse2(short *q, short *dq, unsigned char *dst, int stride, char *eobs); +#define vp8_dequant_idct_add_y_block vp8_dequant_idct_add_y_block_sse2 + +void vp8_dequantize_b_c(struct blockd*, short *dqc); +void vp8_dequantize_b_mmx(struct blockd*, short *dqc); +#define vp8_dequantize_b vp8_dequantize_b_mmx + +int vp8_diamond_search_sad_c(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, union int_mv *best_mv, int search_param, int sad_per_bit, int *num00, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +int vp8_diamond_search_sadx4(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, union int_mv *best_mv, int search_param, int sad_per_bit, int *num00, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +#define vp8_diamond_search_sad vp8_diamond_search_sadx4 + +void vp8_fast_quantize_b_c(struct block *, struct blockd *); +void vp8_fast_quantize_b_sse2(struct block *, struct blockd *); +void vp8_fast_quantize_b_ssse3(struct block *, struct blockd *); +RTCD_EXTERN void (*vp8_fast_quantize_b)(struct block *, struct blockd *); + +void vp8_filter_by_weight16x16_c(unsigned char *src, int src_stride, unsigned char *dst, int dst_stride, int src_weight); +void vp8_filter_by_weight16x16_sse2(unsigned char *src, int src_stride, unsigned char *dst, int dst_stride, int src_weight); +#define vp8_filter_by_weight16x16 vp8_filter_by_weight16x16_sse2 + +void vp8_filter_by_weight4x4_c(unsigned char *src, int src_stride, unsigned char *dst, int dst_stride, int src_weight); +#define vp8_filter_by_weight4x4 vp8_filter_by_weight4x4_c + +void vp8_filter_by_weight8x8_c(unsigned char *src, int src_stride, unsigned char *dst, int dst_stride, int src_weight); +void vp8_filter_by_weight8x8_sse2(unsigned char *src, int src_stride, unsigned char *dst, int dst_stride, int src_weight); +#define vp8_filter_by_weight8x8 vp8_filter_by_weight8x8_sse2 + +int vp8_full_search_sad_c(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, int sad_per_bit, int distance, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +int vp8_full_search_sadx3(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, int sad_per_bit, int distance, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +int vp8_full_search_sadx8(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, int sad_per_bit, int distance, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +RTCD_EXTERN int (*vp8_full_search_sad)(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, int sad_per_bit, int distance, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); + +void vp8_loop_filter_bh_c(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +void vp8_loop_filter_bh_sse2(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +#define vp8_loop_filter_bh vp8_loop_filter_bh_sse2 + +void vp8_loop_filter_bv_c(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +void vp8_loop_filter_bv_sse2(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +#define vp8_loop_filter_bv vp8_loop_filter_bv_sse2 + +void vp8_loop_filter_mbh_c(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +void vp8_loop_filter_mbh_sse2(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +#define vp8_loop_filter_mbh vp8_loop_filter_mbh_sse2 + +void vp8_loop_filter_mbv_c(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +void vp8_loop_filter_mbv_sse2(unsigned char *y, unsigned char *u, unsigned char *v, int ystride, int uv_stride, struct loop_filter_info *lfi); +#define vp8_loop_filter_mbv vp8_loop_filter_mbv_sse2 + +void vp8_loop_filter_bhs_c(unsigned char *y, int ystride, const unsigned char *blimit); +void vp8_loop_filter_bhs_sse2(unsigned char *y, int ystride, const unsigned char *blimit); +#define vp8_loop_filter_simple_bh vp8_loop_filter_bhs_sse2 + +void vp8_loop_filter_bvs_c(unsigned char *y, int ystride, const unsigned char *blimit); +void vp8_loop_filter_bvs_sse2(unsigned char *y, int ystride, const unsigned char *blimit); +#define vp8_loop_filter_simple_bv vp8_loop_filter_bvs_sse2 + +void vp8_loop_filter_simple_horizontal_edge_c(unsigned char *y, int ystride, const unsigned char *blimit); +void vp8_loop_filter_simple_horizontal_edge_sse2(unsigned char *y, int ystride, const unsigned char *blimit); +#define vp8_loop_filter_simple_mbh vp8_loop_filter_simple_horizontal_edge_sse2 + +void vp8_loop_filter_simple_vertical_edge_c(unsigned char *y, int ystride, const unsigned char *blimit); +void vp8_loop_filter_simple_vertical_edge_sse2(unsigned char *y, int ystride, const unsigned char *blimit); +#define vp8_loop_filter_simple_mbv vp8_loop_filter_simple_vertical_edge_sse2 + +int vp8_mbblock_error_c(struct macroblock *mb, int dc); +int vp8_mbblock_error_sse2(struct macroblock *mb, int dc); +#define vp8_mbblock_error vp8_mbblock_error_sse2 + +int vp8_mbuverror_c(struct macroblock *mb); +int vp8_mbuverror_sse2(struct macroblock *mb); +#define vp8_mbuverror vp8_mbuverror_sse2 + +int vp8_refining_search_sad_c(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, int sad_per_bit, int distance, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +int vp8_refining_search_sadx4(struct macroblock *x, struct block *b, struct blockd *d, union int_mv *ref_mv, int sad_per_bit, int distance, struct variance_vtable *fn_ptr, int *mvcost[2], union int_mv *center_mv); +#define vp8_refining_search_sad vp8_refining_search_sadx4 + +void vp8_regular_quantize_b_c(struct block *, struct blockd *); +void vp8_regular_quantize_b_sse2(struct block *, struct blockd *); +void vp8_regular_quantize_b_sse4_1(struct block *, struct blockd *); +RTCD_EXTERN void (*vp8_regular_quantize_b)(struct block *, struct blockd *); + +void vp8_short_fdct4x4_c(short *input, short *output, int pitch); +void vp8_short_fdct4x4_sse2(short *input, short *output, int pitch); +#define vp8_short_fdct4x4 vp8_short_fdct4x4_sse2 + +void vp8_short_fdct8x4_c(short *input, short *output, int pitch); +void vp8_short_fdct8x4_sse2(short *input, short *output, int pitch); +#define vp8_short_fdct8x4 vp8_short_fdct8x4_sse2 + +void vp8_short_idct4x4llm_c(short *input, unsigned char *pred, int pitch, unsigned char *dst, int dst_stride); +void vp8_short_idct4x4llm_mmx(short *input, unsigned char *pred, int pitch, unsigned char *dst, int dst_stride); +#define vp8_short_idct4x4llm vp8_short_idct4x4llm_mmx + +void vp8_short_inv_walsh4x4_c(short *input, short *output); +void vp8_short_inv_walsh4x4_sse2(short *input, short *output); +#define vp8_short_inv_walsh4x4 vp8_short_inv_walsh4x4_sse2 + +void vp8_short_inv_walsh4x4_1_c(short *input, short *output); +#define vp8_short_inv_walsh4x4_1 vp8_short_inv_walsh4x4_1_c + +void vp8_short_walsh4x4_c(short *input, short *output, int pitch); +void vp8_short_walsh4x4_sse2(short *input, short *output, int pitch); +#define vp8_short_walsh4x4 vp8_short_walsh4x4_sse2 + +void vp8_sixtap_predict16x16_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict16x16_sse2(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict16x16_ssse3(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +RTCD_EXTERN void (*vp8_sixtap_predict16x16)(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); + +void vp8_sixtap_predict4x4_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict4x4_mmx(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict4x4_ssse3(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +RTCD_EXTERN void (*vp8_sixtap_predict4x4)(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); + +void vp8_sixtap_predict8x4_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict8x4_sse2(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict8x4_ssse3(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +RTCD_EXTERN void (*vp8_sixtap_predict8x4)(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); + +void vp8_sixtap_predict8x8_c(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict8x8_sse2(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +void vp8_sixtap_predict8x8_ssse3(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); +RTCD_EXTERN void (*vp8_sixtap_predict8x8)(unsigned char *src, int src_pitch, int xofst, int yofst, unsigned char *dst, int dst_pitch); + +void vp8_temporal_filter_apply_c(unsigned char *frame1, unsigned int stride, unsigned char *frame2, unsigned int block_size, int strength, int filter_weight, unsigned int *accumulator, unsigned short *count); +void vp8_temporal_filter_apply_sse2(unsigned char *frame1, unsigned int stride, unsigned char *frame2, unsigned int block_size, int strength, int filter_weight, unsigned int *accumulator, unsigned short *count); +#define vp8_temporal_filter_apply vp8_temporal_filter_apply_sse2 + +void vp8_rtcd(void); + +#ifdef RTCD_C +#include "vpx_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + + vp8_bilinear_predict16x16 = vp8_bilinear_predict16x16_sse2; + if (flags & HAS_SSSE3) vp8_bilinear_predict16x16 = vp8_bilinear_predict16x16_ssse3; + vp8_bilinear_predict8x8 = vp8_bilinear_predict8x8_sse2; + if (flags & HAS_SSSE3) vp8_bilinear_predict8x8 = vp8_bilinear_predict8x8_ssse3; + vp8_copy32xn = vp8_copy32xn_sse2; + if (flags & HAS_SSE3) vp8_copy32xn = vp8_copy32xn_sse3; + vp8_fast_quantize_b = vp8_fast_quantize_b_sse2; + if (flags & HAS_SSSE3) vp8_fast_quantize_b = vp8_fast_quantize_b_ssse3; + vp8_full_search_sad = vp8_full_search_sad_c; + if (flags & HAS_SSE3) vp8_full_search_sad = vp8_full_search_sadx3; + if (flags & HAS_SSE4_1) vp8_full_search_sad = vp8_full_search_sadx8; + vp8_regular_quantize_b = vp8_regular_quantize_b_sse2; + if (flags & HAS_SSE4_1) vp8_regular_quantize_b = vp8_regular_quantize_b_sse4_1; + vp8_sixtap_predict16x16 = vp8_sixtap_predict16x16_sse2; + if (flags & HAS_SSSE3) vp8_sixtap_predict16x16 = vp8_sixtap_predict16x16_ssse3; + vp8_sixtap_predict4x4 = vp8_sixtap_predict4x4_mmx; + if (flags & HAS_SSSE3) vp8_sixtap_predict4x4 = vp8_sixtap_predict4x4_ssse3; + vp8_sixtap_predict8x4 = vp8_sixtap_predict8x4_sse2; + if (flags & HAS_SSSE3) vp8_sixtap_predict8x4 = vp8_sixtap_predict8x4_ssse3; + vp8_sixtap_predict8x8 = vp8_sixtap_predict8x8_sse2; + if (flags & HAS_SSSE3) vp8_sixtap_predict8x8 = vp8_sixtap_predict8x8_ssse3; +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libvpx/config/win/mingw64/vp9_rtcd.h b/media/libvpx/config/win/mingw64/vp9_rtcd.h new file mode 100644 index 000000000000..47a708444d86 --- /dev/null +++ b/media/libvpx/config/win/mingw64/vp9_rtcd.h @@ -0,0 +1,140 @@ +#ifndef VP9_RTCD_H_ +#define VP9_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +/* + * VP9 + */ + +#include "vpx/vpx_integer.h" +#include "vp9/common/vp9_common.h" +#include "vp9/common/vp9_enums.h" + +struct macroblockd; + +/* Encoder forward decls */ +struct macroblock; +struct vp9_variance_vtable; +struct search_site_config; +struct mv; +union int_mv; +struct yv12_buffer_config; + +#ifdef __cplusplus +extern "C" { +#endif + +int64_t vp9_block_error_c(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); +int64_t vp9_block_error_sse2(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); +int64_t vp9_block_error_avx2(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); +RTCD_EXTERN int64_t (*vp9_block_error)(const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz); + +int64_t vp9_block_error_fp_c(const int16_t *coeff, const int16_t *dqcoeff, int block_size); +int64_t vp9_block_error_fp_sse2(const int16_t *coeff, const int16_t *dqcoeff, int block_size); +#define vp9_block_error_fp vp9_block_error_fp_sse2 + +int vp9_diamond_search_sad_c(const struct macroblock *x, const struct search_site_config *cfg, struct mv *ref_mv, struct mv *best_mv, int search_param, int sad_per_bit, int *num00, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv); +int vp9_diamond_search_sad_avx(const struct macroblock *x, const struct search_site_config *cfg, struct mv *ref_mv, struct mv *best_mv, int search_param, int sad_per_bit, int *num00, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv); +RTCD_EXTERN int (*vp9_diamond_search_sad)(const struct macroblock *x, const struct search_site_config *cfg, struct mv *ref_mv, struct mv *best_mv, int search_param, int sad_per_bit, int *num00, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv); + +void vp9_fdct8x8_quant_c(const int16_t *input, int stride, tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vp9_fdct8x8_quant_sse2(const int16_t *input, int stride, tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vp9_fdct8x8_quant_ssse3(const int16_t *input, int stride, tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*vp9_fdct8x8_quant)(const int16_t *input, int stride, tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void vp9_fht16x16_c(const int16_t *input, tran_low_t *output, int stride, int tx_type); +void vp9_fht16x16_sse2(const int16_t *input, tran_low_t *output, int stride, int tx_type); +#define vp9_fht16x16 vp9_fht16x16_sse2 + +void vp9_fht4x4_c(const int16_t *input, tran_low_t *output, int stride, int tx_type); +void vp9_fht4x4_sse2(const int16_t *input, tran_low_t *output, int stride, int tx_type); +#define vp9_fht4x4 vp9_fht4x4_sse2 + +void vp9_fht8x8_c(const int16_t *input, tran_low_t *output, int stride, int tx_type); +void vp9_fht8x8_sse2(const int16_t *input, tran_low_t *output, int stride, int tx_type); +#define vp9_fht8x8 vp9_fht8x8_sse2 + +void vp9_filter_by_weight16x16_c(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int src_weight); +void vp9_filter_by_weight16x16_sse2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int src_weight); +#define vp9_filter_by_weight16x16 vp9_filter_by_weight16x16_sse2 + +void vp9_filter_by_weight8x8_c(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int src_weight); +void vp9_filter_by_weight8x8_sse2(const uint8_t *src, int src_stride, uint8_t *dst, int dst_stride, int src_weight); +#define vp9_filter_by_weight8x8 vp9_filter_by_weight8x8_sse2 + +int vp9_full_search_sad_c(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); +int vp9_full_search_sadx3(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); +int vp9_full_search_sadx8(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); +RTCD_EXTERN int (*vp9_full_search_sad)(const struct macroblock *x, const struct mv *ref_mv, int sad_per_bit, int distance, const struct vp9_variance_vtable *fn_ptr, const struct mv *center_mv, struct mv *best_mv); + +void vp9_fwht4x4_c(const int16_t *input, tran_low_t *output, int stride); +void vp9_fwht4x4_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vp9_fwht4x4 vp9_fwht4x4_sse2 + +void vp9_iht16x16_256_add_c(const tran_low_t *input, uint8_t *output, int pitch, int tx_type); +void vp9_iht16x16_256_add_sse2(const tran_low_t *input, uint8_t *output, int pitch, int tx_type); +#define vp9_iht16x16_256_add vp9_iht16x16_256_add_sse2 + +void vp9_iht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int stride, int tx_type); +void vp9_iht4x4_16_add_sse2(const tran_low_t *input, uint8_t *dest, int stride, int tx_type); +#define vp9_iht4x4_16_add vp9_iht4x4_16_add_sse2 + +void vp9_iht8x8_64_add_c(const tran_low_t *input, uint8_t *dest, int stride, int tx_type); +void vp9_iht8x8_64_add_sse2(const tran_low_t *input, uint8_t *dest, int stride, int tx_type); +#define vp9_iht8x8_64_add vp9_iht8x8_64_add_sse2 + +void vp9_quantize_fp_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vp9_quantize_fp_sse2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vp9_quantize_fp_ssse3(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*vp9_quantize_fp)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void vp9_quantize_fp_32x32_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vp9_quantize_fp_32x32_ssse3(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*vp9_quantize_fp_32x32)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void vp9_scale_and_extend_frame_c(const struct yv12_buffer_config *src, struct yv12_buffer_config *dst); +void vp9_scale_and_extend_frame_ssse3(const struct yv12_buffer_config *src, struct yv12_buffer_config *dst); +RTCD_EXTERN void (*vp9_scale_and_extend_frame)(const struct yv12_buffer_config *src, struct yv12_buffer_config *dst); + +void vp9_temporal_filter_apply_c(uint8_t *frame1, unsigned int stride, uint8_t *frame2, unsigned int block_width, unsigned int block_height, int strength, int filter_weight, unsigned int *accumulator, uint16_t *count); +void vp9_temporal_filter_apply_sse2(uint8_t *frame1, unsigned int stride, uint8_t *frame2, unsigned int block_width, unsigned int block_height, int strength, int filter_weight, unsigned int *accumulator, uint16_t *count); +#define vp9_temporal_filter_apply vp9_temporal_filter_apply_sse2 + +void vp9_rtcd(void); + +#ifdef RTCD_C +#include "vpx_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + + vp9_block_error = vp9_block_error_sse2; + if (flags & HAS_AVX2) vp9_block_error = vp9_block_error_avx2; + vp9_diamond_search_sad = vp9_diamond_search_sad_c; + if (flags & HAS_AVX) vp9_diamond_search_sad = vp9_diamond_search_sad_avx; + vp9_fdct8x8_quant = vp9_fdct8x8_quant_sse2; + if (flags & HAS_SSSE3) vp9_fdct8x8_quant = vp9_fdct8x8_quant_ssse3; + vp9_full_search_sad = vp9_full_search_sad_c; + if (flags & HAS_SSE3) vp9_full_search_sad = vp9_full_search_sadx3; + if (flags & HAS_SSE4_1) vp9_full_search_sad = vp9_full_search_sadx8; + vp9_quantize_fp = vp9_quantize_fp_sse2; + if (flags & HAS_SSSE3) vp9_quantize_fp = vp9_quantize_fp_ssse3; + vp9_quantize_fp_32x32 = vp9_quantize_fp_32x32_c; + if (flags & HAS_SSSE3) vp9_quantize_fp_32x32 = vp9_quantize_fp_32x32_ssse3; + vp9_scale_and_extend_frame = vp9_scale_and_extend_frame_c; + if (flags & HAS_SSSE3) vp9_scale_and_extend_frame = vp9_scale_and_extend_frame_ssse3; +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libvpx/config/win/mingw64/vpx_config.asm b/media/libvpx/config/win/mingw64/vpx_config.asm new file mode 100755 index 000000000000..e4744099588a --- /dev/null +++ b/media/libvpx/config/win/mingw64/vpx_config.asm @@ -0,0 +1,78 @@ +%define ARCH_ARM 0 +%define ARCH_MIPS 0 +%define ARCH_X86 0 +%define ARCH_X86_64 1 +%define HAVE_NEON 0 +%define HAVE_NEON_ASM 0 +%define HAVE_MIPS32 0 +%define HAVE_DSPR2 0 +%define HAVE_MSA 0 +%define HAVE_MIPS64 0 +%define HAVE_MMX 1 +%define HAVE_SSE 1 +%define HAVE_SSE2 1 +%define HAVE_SSE3 1 +%define HAVE_SSSE3 1 +%define HAVE_SSE4_1 1 +%define HAVE_AVX 1 +%define HAVE_AVX2 1 +%define HAVE_VPX_PORTS 1 +%define HAVE_PTHREAD_H 1 +%define CONFIG_DEPENDENCY_TRACKING 1 +%define CONFIG_EXTERNAL_BUILD 1 +%define CONFIG_INSTALL_DOCS 0 +%define CONFIG_INSTALL_BINS 1 +%define CONFIG_INSTALL_LIBS 1 +%define CONFIG_INSTALL_SRCS 0 +%define CONFIG_DEBUG 0 +%define CONFIG_GPROF 0 +%define CONFIG_GCOV 0 +%define CONFIG_RVCT 0 +%define CONFIG_GCC 1 +%define CONFIG_MSVS 0 +%define CONFIG_PIC 1 +%define CONFIG_BIG_ENDIAN 0 +%define CONFIG_CODEC_SRCS 0 +%define CONFIG_DEBUG_LIBS 0 +%define CONFIG_DEQUANT_TOKENS 0 +%define CONFIG_DC_RECON 0 +%define CONFIG_RUNTIME_CPU_DETECT 1 +%define CONFIG_POSTPROC 1 +%define CONFIG_VP9_POSTPROC 1 +%define CONFIG_MULTITHREAD 1 +%define CONFIG_INTERNAL_STATS 0 +%define CONFIG_VP8_ENCODER 1 +%define CONFIG_VP8_DECODER 1 +%define CONFIG_VP9_ENCODER 1 +%define CONFIG_VP9_DECODER 1 +%define CONFIG_VP8 1 +%define CONFIG_VP9 1 +%define CONFIG_ENCODERS 1 +%define CONFIG_DECODERS 1 +%define CONFIG_STATIC_MSVCRT 0 +%define CONFIG_SPATIAL_RESAMPLING 1 +%define CONFIG_REALTIME_ONLY 0 +%define CONFIG_ONTHEFLY_BITPACKING 0 +%define CONFIG_ERROR_CONCEALMENT 0 +%define CONFIG_SHARED 0 +%define CONFIG_STATIC 1 +%define CONFIG_SMALL 0 +%define CONFIG_POSTPROC_VISUALIZER 0 +%define CONFIG_OS_SUPPORT 1 +%define CONFIG_UNIT_TESTS 0 +%define CONFIG_WEBM_IO 1 +%define CONFIG_LIBYUV 1 +%define CONFIG_DECODE_PERF_TESTS 0 +%define CONFIG_ENCODE_PERF_TESTS 0 +%define CONFIG_MULTI_RES_ENCODING 1 +%define CONFIG_TEMPORAL_DENOISING 1 +%define CONFIG_VP9_TEMPORAL_DENOISING 0 +%define CONFIG_COEFFICIENT_RANGE_CHECKING 0 +%define CONFIG_VP9_HIGHBITDEPTH 0 +%define CONFIG_BETTER_HW_COMPATIBILITY 0 +%define CONFIG_EXPERIMENTAL 0 +%define CONFIG_SIZE_LIMIT 1 +%define CONFIG_SPATIAL_SVC 0 +%define CONFIG_FP_MB_STATS 0 +%define CONFIG_EMULATE_HARDWARE 0 +%define CONFIG_MISC_FIXES 0 diff --git a/media/libvpx/config/win/mingw64/vpx_config.c b/media/libvpx/config/win/mingw64/vpx_config.c new file mode 100755 index 000000000000..81497a212296 --- /dev/null +++ b/media/libvpx/config/win/mingw64/vpx_config.c @@ -0,0 +1,10 @@ +/* Copyright (c) 2011 The WebM project authors. All Rights Reserved. */ +/* */ +/* Use of this source code is governed by a BSD-style license */ +/* that can be found in the LICENSE file in the root of the source */ +/* tree. An additional intellectual property rights grant can be found */ +/* in the file PATENTS. All contributing project authors may */ +/* be found in the AUTHORS file in the root of the source tree. */ +#include "vpx/vpx_codec.h" +static const char* const cfg = "--target=x86_64-win64-gcc --enable-external-build --disable-examples --disable-install-docs --disable-unit-tests --enable-multi-res-encoding --size-limit=8192x4608 --enable-pic --enable-postproc --enable-vp9-postproc --as=yasm"; +const char *vpx_codec_build_config(void) {return cfg;} diff --git a/media/libvpx/config/win/mingw64/vpx_config.h b/media/libvpx/config/win/mingw64/vpx_config.h new file mode 100755 index 000000000000..23f32d14871f --- /dev/null +++ b/media/libvpx/config/win/mingw64/vpx_config.h @@ -0,0 +1,93 @@ +/* Copyright (c) 2011 The WebM project authors. All Rights Reserved. */ +/* */ +/* Use of this source code is governed by a BSD-style license */ +/* that can be found in the LICENSE file in the root of the source */ +/* tree. An additional intellectual property rights grant can be found */ +/* in the file PATENTS. All contributing project authors may */ +/* be found in the AUTHORS file in the root of the source tree. */ +/* This file automatically generated by configure. Do not edit! */ +#ifndef VPX_CONFIG_H +#define VPX_CONFIG_H +#define RESTRICT +#define INLINE inline +#define ARCH_ARM 0 +#define ARCH_MIPS 0 +#define ARCH_X86 0 +#define ARCH_X86_64 1 +#define HAVE_NEON 0 +#define HAVE_NEON_ASM 0 +#define HAVE_MIPS32 0 +#define HAVE_DSPR2 0 +#define HAVE_MSA 0 +#define HAVE_MIPS64 0 +#define HAVE_MMX 1 +#define HAVE_SSE 1 +#define HAVE_SSE2 1 +#define HAVE_SSE3 1 +#define HAVE_SSSE3 1 +#define HAVE_SSE4_1 1 +#define HAVE_AVX 1 +#define HAVE_AVX2 1 +#define HAVE_VPX_PORTS 1 +#define HAVE_PTHREAD_H 1 +#define CONFIG_DEPENDENCY_TRACKING 1 +#define CONFIG_EXTERNAL_BUILD 1 +#define CONFIG_INSTALL_DOCS 0 +#define CONFIG_INSTALL_BINS 1 +#define CONFIG_INSTALL_LIBS 1 +#define CONFIG_INSTALL_SRCS 0 +#define CONFIG_DEBUG 0 +#define CONFIG_GPROF 0 +#define CONFIG_GCOV 0 +#define CONFIG_RVCT 0 +#define CONFIG_GCC 1 +#define CONFIG_MSVS 0 +#define CONFIG_PIC 1 +#define CONFIG_BIG_ENDIAN 0 +#define CONFIG_CODEC_SRCS 0 +#define CONFIG_DEBUG_LIBS 0 +#define CONFIG_DEQUANT_TOKENS 0 +#define CONFIG_DC_RECON 0 +#define CONFIG_RUNTIME_CPU_DETECT 1 +#define CONFIG_POSTPROC 1 +#define CONFIG_VP9_POSTPROC 1 +#define CONFIG_MULTITHREAD 1 +#define CONFIG_INTERNAL_STATS 0 +#define CONFIG_VP8_ENCODER 1 +#define CONFIG_VP8_DECODER 1 +#define CONFIG_VP9_ENCODER 1 +#define CONFIG_VP9_DECODER 1 +#define CONFIG_VP8 1 +#define CONFIG_VP9 1 +#define CONFIG_ENCODERS 1 +#define CONFIG_DECODERS 1 +#define CONFIG_STATIC_MSVCRT 0 +#define CONFIG_SPATIAL_RESAMPLING 1 +#define CONFIG_REALTIME_ONLY 0 +#define CONFIG_ONTHEFLY_BITPACKING 0 +#define CONFIG_ERROR_CONCEALMENT 0 +#define CONFIG_SHARED 0 +#define CONFIG_STATIC 1 +#define CONFIG_SMALL 0 +#define CONFIG_POSTPROC_VISUALIZER 0 +#define CONFIG_OS_SUPPORT 1 +#define CONFIG_UNIT_TESTS 0 +#define CONFIG_WEBM_IO 1 +#define CONFIG_LIBYUV 1 +#define CONFIG_DECODE_PERF_TESTS 0 +#define CONFIG_ENCODE_PERF_TESTS 0 +#define CONFIG_MULTI_RES_ENCODING 1 +#define CONFIG_TEMPORAL_DENOISING 1 +#define CONFIG_VP9_TEMPORAL_DENOISING 0 +#define CONFIG_COEFFICIENT_RANGE_CHECKING 0 +#define CONFIG_VP9_HIGHBITDEPTH 0 +#define CONFIG_BETTER_HW_COMPATIBILITY 0 +#define CONFIG_EXPERIMENTAL 0 +#define CONFIG_SIZE_LIMIT 1 +#define CONFIG_SPATIAL_SVC 0 +#define CONFIG_FP_MB_STATS 0 +#define CONFIG_EMULATE_HARDWARE 0 +#define CONFIG_MISC_FIXES 0 +#define DECODE_WIDTH_LIMIT 8192 +#define DECODE_HEIGHT_LIMIT 4608 +#endif /* VPX_CONFIG_H */ diff --git a/media/libvpx/config/win/mingw64/vpx_dsp_rtcd.h b/media/libvpx/config/win/mingw64/vpx_dsp_rtcd.h new file mode 100644 index 000000000000..6f181c0a0e09 --- /dev/null +++ b/media/libvpx/config/win/mingw64/vpx_dsp_rtcd.h @@ -0,0 +1,1207 @@ +#ifndef VPX_DSP_RTCD_H_ +#define VPX_DSP_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +/* + * DSP + */ + +#include "vpx/vpx_integer.h" +#include "vpx_dsp/vpx_dsp_common.h" + + +#ifdef __cplusplus +extern "C" { +#endif + +unsigned int vpx_avg_4x4_c(const uint8_t *, int p); +unsigned int vpx_avg_4x4_sse2(const uint8_t *, int p); +#define vpx_avg_4x4 vpx_avg_4x4_sse2 + +unsigned int vpx_avg_8x8_c(const uint8_t *, int p); +unsigned int vpx_avg_8x8_sse2(const uint8_t *, int p); +#define vpx_avg_8x8 vpx_avg_8x8_sse2 + +void vpx_comp_avg_pred_c(uint8_t *comp_pred, const uint8_t *pred, int width, int height, const uint8_t *ref, int ref_stride); +#define vpx_comp_avg_pred vpx_comp_avg_pred_c + +void vpx_convolve8_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_convolve8)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_convolve8_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avg_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_convolve8_avg)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_convolve8_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avg_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avg_horiz_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_convolve8_avg_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_convolve8_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avg_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_avg_vert_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_convolve8_avg_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_convolve8_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_horiz_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_horiz_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_horiz_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_convolve8_horiz)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_convolve8_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_vert_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_vert_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve8_vert_avx2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_convolve8_vert)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_convolve_avg_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve_avg_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_convolve_avg vpx_convolve_avg_sse2 + +void vpx_convolve_copy_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_convolve_copy_sse2(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_convolve_copy vpx_convolve_copy_sse2 + +void vpx_d117_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d117_predictor_16x16 vpx_d117_predictor_16x16_c + +void vpx_d117_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d117_predictor_32x32 vpx_d117_predictor_32x32_c + +void vpx_d117_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d117_predictor_4x4 vpx_d117_predictor_4x4_c + +void vpx_d117_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d117_predictor_8x8 vpx_d117_predictor_8x8_c + +void vpx_d135_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d135_predictor_16x16 vpx_d135_predictor_16x16_c + +void vpx_d135_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d135_predictor_32x32 vpx_d135_predictor_32x32_c + +void vpx_d135_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d135_predictor_4x4 vpx_d135_predictor_4x4_c + +void vpx_d135_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d135_predictor_8x8 vpx_d135_predictor_8x8_c + +void vpx_d153_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d153_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d153_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d153_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d153_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d153_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d153_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d153_predictor_4x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d153_predictor_4x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d153_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d153_predictor_8x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d153_predictor_8x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d207_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d207_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d207_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d207_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d207_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d207_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d207_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d207_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d207_predictor_4x4 vpx_d207_predictor_4x4_sse2 + +void vpx_d207_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d207_predictor_8x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d207_predictor_8x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d207e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d207e_predictor_16x16 vpx_d207e_predictor_16x16_c + +void vpx_d207e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d207e_predictor_32x32 vpx_d207e_predictor_32x32_c + +void vpx_d207e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d207e_predictor_4x4 vpx_d207e_predictor_4x4_c + +void vpx_d207e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d207e_predictor_8x8 vpx_d207e_predictor_8x8_c + +void vpx_d45_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d45_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d45_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d45_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d45_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d45_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d45_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d45_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d45_predictor_4x4 vpx_d45_predictor_4x4_sse2 + +void vpx_d45_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d45_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d45_predictor_8x8 vpx_d45_predictor_8x8_sse2 + +void vpx_d45e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d45e_predictor_16x16 vpx_d45e_predictor_16x16_c + +void vpx_d45e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d45e_predictor_32x32 vpx_d45e_predictor_32x32_c + +void vpx_d45e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d45e_predictor_4x4 vpx_d45e_predictor_4x4_c + +void vpx_d45e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d45e_predictor_8x8 vpx_d45e_predictor_8x8_c + +void vpx_d63_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d63_predictor_16x16_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d63_predictor_16x16)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d63_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d63_predictor_32x32_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d63_predictor_32x32)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d63_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d63_predictor_4x4_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d63_predictor_4x4)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d63_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_d63_predictor_8x8_ssse3(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +RTCD_EXTERN void (*vpx_d63_predictor_8x8)(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); + +void vpx_d63e_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d63e_predictor_16x16 vpx_d63e_predictor_16x16_c + +void vpx_d63e_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d63e_predictor_32x32 vpx_d63e_predictor_32x32_c + +void vpx_d63e_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d63e_predictor_4x4 vpx_d63e_predictor_4x4_c + +void vpx_d63e_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d63e_predictor_8x8 vpx_d63e_predictor_8x8_c + +void vpx_d63f_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_d63f_predictor_4x4 vpx_d63f_predictor_4x4_c + +void vpx_dc_128_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_128_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_128_predictor_16x16 vpx_dc_128_predictor_16x16_sse2 + +void vpx_dc_128_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_128_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_128_predictor_32x32 vpx_dc_128_predictor_32x32_sse2 + +void vpx_dc_128_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_128_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_128_predictor_4x4 vpx_dc_128_predictor_4x4_sse2 + +void vpx_dc_128_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_128_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_128_predictor_8x8 vpx_dc_128_predictor_8x8_sse2 + +void vpx_dc_left_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_left_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_left_predictor_16x16 vpx_dc_left_predictor_16x16_sse2 + +void vpx_dc_left_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_left_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_left_predictor_32x32 vpx_dc_left_predictor_32x32_sse2 + +void vpx_dc_left_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_left_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_left_predictor_4x4 vpx_dc_left_predictor_4x4_sse2 + +void vpx_dc_left_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_left_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_left_predictor_8x8 vpx_dc_left_predictor_8x8_sse2 + +void vpx_dc_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_predictor_16x16 vpx_dc_predictor_16x16_sse2 + +void vpx_dc_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_predictor_32x32 vpx_dc_predictor_32x32_sse2 + +void vpx_dc_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_predictor_4x4 vpx_dc_predictor_4x4_sse2 + +void vpx_dc_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_predictor_8x8 vpx_dc_predictor_8x8_sse2 + +void vpx_dc_top_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_top_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_top_predictor_16x16 vpx_dc_top_predictor_16x16_sse2 + +void vpx_dc_top_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_top_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_top_predictor_32x32 vpx_dc_top_predictor_32x32_sse2 + +void vpx_dc_top_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_top_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_top_predictor_4x4 vpx_dc_top_predictor_4x4_sse2 + +void vpx_dc_top_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_dc_top_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_dc_top_predictor_8x8 vpx_dc_top_predictor_8x8_sse2 + +void vpx_fdct16x16_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct16x16_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vpx_fdct16x16 vpx_fdct16x16_sse2 + +void vpx_fdct16x16_1_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct16x16_1_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vpx_fdct16x16_1 vpx_fdct16x16_1_sse2 + +void vpx_fdct32x32_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct32x32_sse2(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct32x32_avx2(const int16_t *input, tran_low_t *output, int stride); +RTCD_EXTERN void (*vpx_fdct32x32)(const int16_t *input, tran_low_t *output, int stride); + +void vpx_fdct32x32_1_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct32x32_1_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vpx_fdct32x32_1 vpx_fdct32x32_1_sse2 + +void vpx_fdct32x32_rd_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct32x32_rd_sse2(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct32x32_rd_avx2(const int16_t *input, tran_low_t *output, int stride); +RTCD_EXTERN void (*vpx_fdct32x32_rd)(const int16_t *input, tran_low_t *output, int stride); + +void vpx_fdct4x4_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct4x4_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vpx_fdct4x4 vpx_fdct4x4_sse2 + +void vpx_fdct4x4_1_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct4x4_1_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vpx_fdct4x4_1 vpx_fdct4x4_1_sse2 + +void vpx_fdct8x8_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct8x8_sse2(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct8x8_ssse3(const int16_t *input, tran_low_t *output, int stride); +RTCD_EXTERN void (*vpx_fdct8x8)(const int16_t *input, tran_low_t *output, int stride); + +void vpx_fdct8x8_1_c(const int16_t *input, tran_low_t *output, int stride); +void vpx_fdct8x8_1_sse2(const int16_t *input, tran_low_t *output, int stride); +#define vpx_fdct8x8_1 vpx_fdct8x8_1_sse2 + +void vpx_get16x16var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +void vpx_get16x16var_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +void vpx_get16x16var_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +RTCD_EXTERN void (*vpx_get16x16var)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); + +unsigned int vpx_get4x4sse_cs_c(const unsigned char *src_ptr, int source_stride, const unsigned char *ref_ptr, int ref_stride); +#define vpx_get4x4sse_cs vpx_get4x4sse_cs_c + +void vpx_get8x8var_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +void vpx_get8x8var_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse, int *sum); +#define vpx_get8x8var vpx_get8x8var_sse2 + +unsigned int vpx_get_mb_ss_c(const int16_t *); +unsigned int vpx_get_mb_ss_sse2(const int16_t *); +#define vpx_get_mb_ss vpx_get_mb_ss_sse2 + +void vpx_h_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_h_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_h_predictor_16x16 vpx_h_predictor_16x16_sse2 + +void vpx_h_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_h_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_h_predictor_32x32 vpx_h_predictor_32x32_sse2 + +void vpx_h_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_h_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_h_predictor_4x4 vpx_h_predictor_4x4_sse2 + +void vpx_h_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_h_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_h_predictor_8x8 vpx_h_predictor_8x8_sse2 + +void vpx_hadamard_16x16_c(const int16_t *src_diff, int src_stride, int16_t *coeff); +void vpx_hadamard_16x16_sse2(const int16_t *src_diff, int src_stride, int16_t *coeff); +#define vpx_hadamard_16x16 vpx_hadamard_16x16_sse2 + +void vpx_hadamard_8x8_c(const int16_t *src_diff, int src_stride, int16_t *coeff); +void vpx_hadamard_8x8_sse2(const int16_t *src_diff, int src_stride, int16_t *coeff); +void vpx_hadamard_8x8_ssse3(const int16_t *src_diff, int src_stride, int16_t *coeff); +RTCD_EXTERN void (*vpx_hadamard_8x8)(const int16_t *src_diff, int src_stride, int16_t *coeff); + +void vpx_he_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_he_predictor_4x4 vpx_he_predictor_4x4_c + +void vpx_idct16x16_10_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct16x16_10_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct16x16_10_add vpx_idct16x16_10_add_sse2 + +void vpx_idct16x16_1_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct16x16_1_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct16x16_1_add vpx_idct16x16_1_add_sse2 + +void vpx_idct16x16_256_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct16x16_256_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct16x16_256_add vpx_idct16x16_256_add_sse2 + +void vpx_idct32x32_1024_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_1024_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_1024_add_ssse3(const tran_low_t *input, uint8_t *dest, int stride); +RTCD_EXTERN void (*vpx_idct32x32_1024_add)(const tran_low_t *input, uint8_t *dest, int stride); + +void vpx_idct32x32_135_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_1024_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_135_add_ssse3(const tran_low_t *input, uint8_t *dest, int stride); +RTCD_EXTERN void (*vpx_idct32x32_135_add)(const tran_low_t *input, uint8_t *dest, int stride); + +void vpx_idct32x32_1_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_1_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct32x32_1_add vpx_idct32x32_1_add_sse2 + +void vpx_idct32x32_34_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_34_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct32x32_34_add_ssse3(const tran_low_t *input, uint8_t *dest, int stride); +RTCD_EXTERN void (*vpx_idct32x32_34_add)(const tran_low_t *input, uint8_t *dest, int stride); + +void vpx_idct4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct4x4_16_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct4x4_16_add vpx_idct4x4_16_add_sse2 + +void vpx_idct4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct4x4_1_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct4x4_1_add vpx_idct4x4_1_add_sse2 + +void vpx_idct8x8_12_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct8x8_12_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct8x8_12_add_ssse3(const tran_low_t *input, uint8_t *dest, int stride); +RTCD_EXTERN void (*vpx_idct8x8_12_add)(const tran_low_t *input, uint8_t *dest, int stride); + +void vpx_idct8x8_1_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct8x8_1_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_idct8x8_1_add vpx_idct8x8_1_add_sse2 + +void vpx_idct8x8_64_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct8x8_64_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_idct8x8_64_add_ssse3(const tran_low_t *input, uint8_t *dest, int stride); +RTCD_EXTERN void (*vpx_idct8x8_64_add)(const tran_low_t *input, uint8_t *dest, int stride); + +int16_t vpx_int_pro_col_c(const uint8_t *ref, const int width); +int16_t vpx_int_pro_col_sse2(const uint8_t *ref, const int width); +#define vpx_int_pro_col vpx_int_pro_col_sse2 + +void vpx_int_pro_row_c(int16_t *hbuf, const uint8_t *ref, const int ref_stride, const int height); +void vpx_int_pro_row_sse2(int16_t *hbuf, const uint8_t *ref, const int ref_stride, const int height); +#define vpx_int_pro_row vpx_int_pro_row_sse2 + +void vpx_iwht4x4_16_add_c(const tran_low_t *input, uint8_t *dest, int stride); +void vpx_iwht4x4_16_add_sse2(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_iwht4x4_16_add vpx_iwht4x4_16_add_sse2 + +void vpx_iwht4x4_1_add_c(const tran_low_t *input, uint8_t *dest, int stride); +#define vpx_iwht4x4_1_add vpx_iwht4x4_1_add_c + +void vpx_lpf_horizontal_16_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_horizontal_16_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_horizontal_16_avx2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +RTCD_EXTERN void (*vpx_lpf_horizontal_16)(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); + +void vpx_lpf_horizontal_16_dual_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_horizontal_16_dual_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_horizontal_16_dual_avx2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +RTCD_EXTERN void (*vpx_lpf_horizontal_16_dual)(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); + +void vpx_lpf_horizontal_4_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_horizontal_4_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define vpx_lpf_horizontal_4 vpx_lpf_horizontal_4_sse2 + +void vpx_lpf_horizontal_4_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +void vpx_lpf_horizontal_4_dual_sse2(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define vpx_lpf_horizontal_4_dual vpx_lpf_horizontal_4_dual_sse2 + +void vpx_lpf_horizontal_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_horizontal_8_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define vpx_lpf_horizontal_8 vpx_lpf_horizontal_8_sse2 + +void vpx_lpf_horizontal_8_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +void vpx_lpf_horizontal_8_dual_sse2(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define vpx_lpf_horizontal_8_dual vpx_lpf_horizontal_8_dual_sse2 + +void vpx_lpf_vertical_16_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_vertical_16_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define vpx_lpf_vertical_16 vpx_lpf_vertical_16_sse2 + +void vpx_lpf_vertical_16_dual_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_vertical_16_dual_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define vpx_lpf_vertical_16_dual vpx_lpf_vertical_16_dual_sse2 + +void vpx_lpf_vertical_4_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_vertical_4_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define vpx_lpf_vertical_4 vpx_lpf_vertical_4_sse2 + +void vpx_lpf_vertical_4_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +void vpx_lpf_vertical_4_dual_sse2(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define vpx_lpf_vertical_4_dual vpx_lpf_vertical_4_dual_sse2 + +void vpx_lpf_vertical_8_c(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +void vpx_lpf_vertical_8_sse2(uint8_t *s, int pitch, const uint8_t *blimit, const uint8_t *limit, const uint8_t *thresh); +#define vpx_lpf_vertical_8 vpx_lpf_vertical_8_sse2 + +void vpx_lpf_vertical_8_dual_c(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +void vpx_lpf_vertical_8_dual_sse2(uint8_t *s, int pitch, const uint8_t *blimit0, const uint8_t *limit0, const uint8_t *thresh0, const uint8_t *blimit1, const uint8_t *limit1, const uint8_t *thresh1); +#define vpx_lpf_vertical_8_dual vpx_lpf_vertical_8_dual_sse2 + +void vpx_mbpost_proc_across_ip_c(unsigned char *dst, int pitch, int rows, int cols,int flimit); +void vpx_mbpost_proc_across_ip_sse2(unsigned char *dst, int pitch, int rows, int cols,int flimit); +#define vpx_mbpost_proc_across_ip vpx_mbpost_proc_across_ip_sse2 + +void vpx_mbpost_proc_down_c(unsigned char *dst, int pitch, int rows, int cols,int flimit); +void vpx_mbpost_proc_down_sse2(unsigned char *dst, int pitch, int rows, int cols,int flimit); +#define vpx_mbpost_proc_down vpx_mbpost_proc_down_sse2 + +void vpx_minmax_8x8_c(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max); +void vpx_minmax_8x8_sse2(const uint8_t *s, int p, const uint8_t *d, int dp, int *min, int *max); +#define vpx_minmax_8x8 vpx_minmax_8x8_sse2 + +unsigned int vpx_mse16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int vpx_mse16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int vpx_mse16x16_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*vpx_mse16x16)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); + +unsigned int vpx_mse16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int vpx_mse16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define vpx_mse16x8 vpx_mse16x8_sse2 + +unsigned int vpx_mse8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int vpx_mse8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define vpx_mse8x16 vpx_mse8x16_sse2 + +unsigned int vpx_mse8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +unsigned int vpx_mse8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int recon_stride, unsigned int *sse); +#define vpx_mse8x8 vpx_mse8x8_sse2 + +void vpx_plane_add_noise_c(uint8_t *start, const int8_t *noise, int blackclamp, int whiteclamp, int width, int height, int pitch); +void vpx_plane_add_noise_sse2(uint8_t *start, const int8_t *noise, int blackclamp, int whiteclamp, int width, int height, int pitch); +#define vpx_plane_add_noise vpx_plane_add_noise_sse2 + +void vpx_post_proc_down_and_across_mb_row_c(unsigned char *src, unsigned char *dst, int src_pitch, int dst_pitch, int cols, unsigned char *flimits, int size); +void vpx_post_proc_down_and_across_mb_row_sse2(unsigned char *src, unsigned char *dst, int src_pitch, int dst_pitch, int cols, unsigned char *flimits, int size); +#define vpx_post_proc_down_and_across_mb_row vpx_post_proc_down_and_across_mb_row_sse2 + +void vpx_quantize_b_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vpx_quantize_b_sse2(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vpx_quantize_b_ssse3(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vpx_quantize_b_avx(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*vpx_quantize_b)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +void vpx_quantize_b_32x32_c(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vpx_quantize_b_32x32_ssse3(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +void vpx_quantize_b_32x32_avx(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); +RTCD_EXTERN void (*vpx_quantize_b_32x32)(const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan); + +unsigned int vpx_sad16x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad16x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad16x16 vpx_sad16x16_sse2 + +unsigned int vpx_sad16x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad16x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad16x16_avg vpx_sad16x16_avg_sse2 + +void vpx_sad16x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad16x16x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad16x16x3_ssse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad16x16x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void vpx_sad16x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad16x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad16x16x4d vpx_sad16x16x4d_sse2 + +void vpx_sad16x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad16x16x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad16x16x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int vpx_sad16x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad16x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad16x32 vpx_sad16x32_sse2 + +unsigned int vpx_sad16x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad16x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad16x32_avg vpx_sad16x32_avg_sse2 + +void vpx_sad16x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad16x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad16x32x4d vpx_sad16x32x4d_sse2 + +unsigned int vpx_sad16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad16x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad16x8 vpx_sad16x8_sse2 + +unsigned int vpx_sad16x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad16x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad16x8_avg vpx_sad16x8_avg_sse2 + +void vpx_sad16x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad16x8x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad16x8x3_ssse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad16x8x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void vpx_sad16x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad16x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad16x8x4d vpx_sad16x8x4d_sse2 + +void vpx_sad16x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad16x8x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad16x8x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int vpx_sad32x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad32x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad32x16_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*vpx_sad32x16)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int vpx_sad32x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad32x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad32x16_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*vpx_sad32x16_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void vpx_sad32x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad32x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad32x16x4d vpx_sad32x16x4d_sse2 + +unsigned int vpx_sad32x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad32x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad32x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*vpx_sad32x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int vpx_sad32x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad32x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad32x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*vpx_sad32x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void vpx_sad32x32x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define vpx_sad32x32x3 vpx_sad32x32x3_c + +void vpx_sad32x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad32x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad32x32x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad32x32x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void vpx_sad32x32x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define vpx_sad32x32x8 vpx_sad32x32x8_c + +unsigned int vpx_sad32x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad32x64_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad32x64_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*vpx_sad32x64)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int vpx_sad32x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad32x64_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad32x64_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*vpx_sad32x64_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void vpx_sad32x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad32x64x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad32x64x4d vpx_sad32x64x4d_sse2 + +unsigned int vpx_sad4x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad4x4_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad4x4 vpx_sad4x4_sse2 + +unsigned int vpx_sad4x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad4x4_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad4x4_avg vpx_sad4x4_avg_sse2 + +void vpx_sad4x4x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad4x4x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad4x4x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void vpx_sad4x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad4x4x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad4x4x4d vpx_sad4x4x4d_sse2 + +void vpx_sad4x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad4x4x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad4x4x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int vpx_sad4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad4x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad4x8 vpx_sad4x8_sse2 + +unsigned int vpx_sad4x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad4x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad4x8_avg vpx_sad4x8_avg_sse2 + +void vpx_sad4x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad4x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad4x8x4d vpx_sad4x8x4d_sse2 + +void vpx_sad4x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define vpx_sad4x8x8 vpx_sad4x8x8_c + +unsigned int vpx_sad64x32_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad64x32_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad64x32_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*vpx_sad64x32)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int vpx_sad64x32_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad64x32_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad64x32_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*vpx_sad64x32_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void vpx_sad64x32x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad64x32x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad64x32x4d vpx_sad64x32x4d_sse2 + +unsigned int vpx_sad64x64_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad64x64_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad64x64_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +RTCD_EXTERN unsigned int (*vpx_sad64x64)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); + +unsigned int vpx_sad64x64_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad64x64_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad64x64_avg_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +RTCD_EXTERN unsigned int (*vpx_sad64x64_avg)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); + +void vpx_sad64x64x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define vpx_sad64x64x3 vpx_sad64x64x3_c + +void vpx_sad64x64x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad64x64x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad64x64x4d_avx2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad64x64x4d)(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); + +void vpx_sad64x64x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define vpx_sad64x64x8 vpx_sad64x64x8_c + +unsigned int vpx_sad8x16_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad8x16_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad8x16 vpx_sad8x16_sse2 + +unsigned int vpx_sad8x16_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad8x16_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad8x16_avg vpx_sad8x16_avg_sse2 + +void vpx_sad8x16x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad8x16x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad8x16x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void vpx_sad8x16x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad8x16x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad8x16x4d vpx_sad8x16x4d_sse2 + +void vpx_sad8x16x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad8x16x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad8x16x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +unsigned int vpx_sad8x4_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad8x4_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad8x4 vpx_sad8x4_sse2 + +unsigned int vpx_sad8x4_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad8x4_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad8x4_avg vpx_sad8x4_avg_sse2 + +void vpx_sad8x4x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad8x4x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad8x4x4d vpx_sad8x4x4d_sse2 + +void vpx_sad8x4x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +#define vpx_sad8x4x8 vpx_sad8x4x8_c + +unsigned int vpx_sad8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +unsigned int vpx_sad8x8_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride); +#define vpx_sad8x8 vpx_sad8x8_sse2 + +unsigned int vpx_sad8x8_avg_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +unsigned int vpx_sad8x8_avg_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, const uint8_t *second_pred); +#define vpx_sad8x8_avg vpx_sad8x8_avg_sse2 + +void vpx_sad8x8x3_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad8x8x3_sse3(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad8x8x3)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +void vpx_sad8x8x4d_c(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +void vpx_sad8x8x4d_sse2(const uint8_t *src_ptr, int src_stride, const uint8_t * const ref_ptr[], int ref_stride, uint32_t *sad_array); +#define vpx_sad8x8x4d vpx_sad8x8x4d_sse2 + +void vpx_sad8x8x8_c(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +void vpx_sad8x8x8_sse4_1(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); +RTCD_EXTERN void (*vpx_sad8x8x8)(const uint8_t *src_ptr, int src_stride, const uint8_t *ref_ptr, int ref_stride, uint32_t *sad_array); + +int vpx_satd_c(const int16_t *coeff, int length); +int vpx_satd_sse2(const int16_t *coeff, int length); +#define vpx_satd vpx_satd_sse2 + +void vpx_scaled_2d_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +void vpx_scaled_2d_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +RTCD_EXTERN void (*vpx_scaled_2d)(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); + +void vpx_scaled_avg_2d_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_scaled_avg_2d vpx_scaled_avg_2d_c + +void vpx_scaled_avg_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_scaled_avg_horiz vpx_scaled_avg_horiz_c + +void vpx_scaled_avg_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_scaled_avg_vert vpx_scaled_avg_vert_c + +void vpx_scaled_horiz_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_scaled_horiz vpx_scaled_horiz_c + +void vpx_scaled_vert_c(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst, ptrdiff_t dst_stride, const int16_t *filter_x, int x_step_q4, const int16_t *filter_y, int y_step_q4, int w, int h); +#define vpx_scaled_vert vpx_scaled_vert_c + +uint32_t vpx_sub_pixel_avg_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance16x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance16x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance16x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance16x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance16x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance16x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance32x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x32_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance32x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance32x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance32x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance4x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance4x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance4x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance4x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance4x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance64x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance64x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance64x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance64x64_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance64x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance8x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance8x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance8x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance8x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_avg_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +uint32_t vpx_sub_pixel_avg_variance8x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_avg_variance8x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse, const uint8_t *second_pred); + +uint32_t vpx_sub_pixel_variance16x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance16x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance16x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance16x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance16x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance16x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance16x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance16x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance16x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance32x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance32x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance32x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x32_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance32x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance32x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance32x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance32x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance4x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance4x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance4x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance4x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance4x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance4x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance4x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance4x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance64x32_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance64x32_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance64x32)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance64x64_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance64x64_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance64x64_avx2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance64x64)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance8x16_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance8x16_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance8x16)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance8x4_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance8x4_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance8x4)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +uint32_t vpx_sub_pixel_variance8x8_c(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +uint32_t vpx_sub_pixel_variance8x8_ssse3(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); +RTCD_EXTERN uint32_t (*vpx_sub_pixel_variance8x8)(const uint8_t *src_ptr, int source_stride, int xoffset, int yoffset, const uint8_t *ref_ptr, int ref_stride, uint32_t *sse); + +void vpx_subtract_block_c(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride); +void vpx_subtract_block_sse2(int rows, int cols, int16_t *diff_ptr, ptrdiff_t diff_stride, const uint8_t *src_ptr, ptrdiff_t src_stride, const uint8_t *pred_ptr, ptrdiff_t pred_stride); +#define vpx_subtract_block vpx_subtract_block_sse2 + +uint64_t vpx_sum_squares_2d_i16_c(const int16_t *src, int stride, int size); +uint64_t vpx_sum_squares_2d_i16_sse2(const int16_t *src, int stride, int size); +#define vpx_sum_squares_2d_i16 vpx_sum_squares_2d_i16_sse2 + +void vpx_tm_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_tm_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_tm_predictor_16x16 vpx_tm_predictor_16x16_sse2 + +void vpx_tm_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_tm_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_tm_predictor_32x32 vpx_tm_predictor_32x32_sse2 + +void vpx_tm_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_tm_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_tm_predictor_4x4 vpx_tm_predictor_4x4_sse2 + +void vpx_tm_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_tm_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_tm_predictor_8x8 vpx_tm_predictor_8x8_sse2 + +void vpx_v_predictor_16x16_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_v_predictor_16x16_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_v_predictor_16x16 vpx_v_predictor_16x16_sse2 + +void vpx_v_predictor_32x32_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_v_predictor_32x32_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_v_predictor_32x32 vpx_v_predictor_32x32_sse2 + +void vpx_v_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_v_predictor_4x4_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_v_predictor_4x4 vpx_v_predictor_4x4_sse2 + +void vpx_v_predictor_8x8_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +void vpx_v_predictor_8x8_sse2(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_v_predictor_8x8 vpx_v_predictor_8x8_sse2 + +unsigned int vpx_variance16x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance16x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance16x16_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*vpx_variance16x16)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int vpx_variance16x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance16x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance16x32 vpx_variance16x32_sse2 + +unsigned int vpx_variance16x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance16x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance16x8 vpx_variance16x8_sse2 + +unsigned int vpx_variance32x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance32x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance32x16_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*vpx_variance32x16)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int vpx_variance32x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance32x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance32x32_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*vpx_variance32x32)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int vpx_variance32x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance32x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance32x64 vpx_variance32x64_sse2 + +unsigned int vpx_variance4x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance4x4_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance4x4 vpx_variance4x4_sse2 + +unsigned int vpx_variance4x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance4x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance4x8 vpx_variance4x8_sse2 + +unsigned int vpx_variance64x32_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance64x32_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance64x32_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*vpx_variance64x32)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int vpx_variance64x64_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance64x64_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance64x64_avx2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +RTCD_EXTERN unsigned int (*vpx_variance64x64)(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); + +unsigned int vpx_variance8x16_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance8x16_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance8x16 vpx_variance8x16_sse2 + +unsigned int vpx_variance8x4_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance8x4_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance8x4 vpx_variance8x4_sse2 + +unsigned int vpx_variance8x8_c(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +unsigned int vpx_variance8x8_sse2(const uint8_t *src_ptr, int source_stride, const uint8_t *ref_ptr, int ref_stride, unsigned int *sse); +#define vpx_variance8x8 vpx_variance8x8_sse2 + +void vpx_ve_predictor_4x4_c(uint8_t *dst, ptrdiff_t y_stride, const uint8_t *above, const uint8_t *left); +#define vpx_ve_predictor_4x4 vpx_ve_predictor_4x4_c + +int vpx_vector_var_c(const int16_t *ref, const int16_t *src, const int bwl); +int vpx_vector_var_sse2(const int16_t *ref, const int16_t *src, const int bwl); +#define vpx_vector_var vpx_vector_var_sse2 + +void vpx_dsp_rtcd(void); + +#ifdef RTCD_C +#include "vpx_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + + vpx_convolve8 = vpx_convolve8_sse2; + if (flags & HAS_SSSE3) vpx_convolve8 = vpx_convolve8_ssse3; + if (flags & HAS_AVX2) vpx_convolve8 = vpx_convolve8_avx2; + vpx_convolve8_avg = vpx_convolve8_avg_sse2; + if (flags & HAS_SSSE3) vpx_convolve8_avg = vpx_convolve8_avg_ssse3; + vpx_convolve8_avg_horiz = vpx_convolve8_avg_horiz_sse2; + if (flags & HAS_SSSE3) vpx_convolve8_avg_horiz = vpx_convolve8_avg_horiz_ssse3; + vpx_convolve8_avg_vert = vpx_convolve8_avg_vert_sse2; + if (flags & HAS_SSSE3) vpx_convolve8_avg_vert = vpx_convolve8_avg_vert_ssse3; + vpx_convolve8_horiz = vpx_convolve8_horiz_sse2; + if (flags & HAS_SSSE3) vpx_convolve8_horiz = vpx_convolve8_horiz_ssse3; + if (flags & HAS_AVX2) vpx_convolve8_horiz = vpx_convolve8_horiz_avx2; + vpx_convolve8_vert = vpx_convolve8_vert_sse2; + if (flags & HAS_SSSE3) vpx_convolve8_vert = vpx_convolve8_vert_ssse3; + if (flags & HAS_AVX2) vpx_convolve8_vert = vpx_convolve8_vert_avx2; + vpx_d153_predictor_16x16 = vpx_d153_predictor_16x16_c; + if (flags & HAS_SSSE3) vpx_d153_predictor_16x16 = vpx_d153_predictor_16x16_ssse3; + vpx_d153_predictor_32x32 = vpx_d153_predictor_32x32_c; + if (flags & HAS_SSSE3) vpx_d153_predictor_32x32 = vpx_d153_predictor_32x32_ssse3; + vpx_d153_predictor_4x4 = vpx_d153_predictor_4x4_c; + if (flags & HAS_SSSE3) vpx_d153_predictor_4x4 = vpx_d153_predictor_4x4_ssse3; + vpx_d153_predictor_8x8 = vpx_d153_predictor_8x8_c; + if (flags & HAS_SSSE3) vpx_d153_predictor_8x8 = vpx_d153_predictor_8x8_ssse3; + vpx_d207_predictor_16x16 = vpx_d207_predictor_16x16_c; + if (flags & HAS_SSSE3) vpx_d207_predictor_16x16 = vpx_d207_predictor_16x16_ssse3; + vpx_d207_predictor_32x32 = vpx_d207_predictor_32x32_c; + if (flags & HAS_SSSE3) vpx_d207_predictor_32x32 = vpx_d207_predictor_32x32_ssse3; + vpx_d207_predictor_8x8 = vpx_d207_predictor_8x8_c; + if (flags & HAS_SSSE3) vpx_d207_predictor_8x8 = vpx_d207_predictor_8x8_ssse3; + vpx_d45_predictor_16x16 = vpx_d45_predictor_16x16_c; + if (flags & HAS_SSSE3) vpx_d45_predictor_16x16 = vpx_d45_predictor_16x16_ssse3; + vpx_d45_predictor_32x32 = vpx_d45_predictor_32x32_c; + if (flags & HAS_SSSE3) vpx_d45_predictor_32x32 = vpx_d45_predictor_32x32_ssse3; + vpx_d63_predictor_16x16 = vpx_d63_predictor_16x16_c; + if (flags & HAS_SSSE3) vpx_d63_predictor_16x16 = vpx_d63_predictor_16x16_ssse3; + vpx_d63_predictor_32x32 = vpx_d63_predictor_32x32_c; + if (flags & HAS_SSSE3) vpx_d63_predictor_32x32 = vpx_d63_predictor_32x32_ssse3; + vpx_d63_predictor_4x4 = vpx_d63_predictor_4x4_c; + if (flags & HAS_SSSE3) vpx_d63_predictor_4x4 = vpx_d63_predictor_4x4_ssse3; + vpx_d63_predictor_8x8 = vpx_d63_predictor_8x8_c; + if (flags & HAS_SSSE3) vpx_d63_predictor_8x8 = vpx_d63_predictor_8x8_ssse3; + vpx_fdct32x32 = vpx_fdct32x32_sse2; + if (flags & HAS_AVX2) vpx_fdct32x32 = vpx_fdct32x32_avx2; + vpx_fdct32x32_rd = vpx_fdct32x32_rd_sse2; + if (flags & HAS_AVX2) vpx_fdct32x32_rd = vpx_fdct32x32_rd_avx2; + vpx_fdct8x8 = vpx_fdct8x8_sse2; + if (flags & HAS_SSSE3) vpx_fdct8x8 = vpx_fdct8x8_ssse3; + vpx_get16x16var = vpx_get16x16var_sse2; + if (flags & HAS_AVX2) vpx_get16x16var = vpx_get16x16var_avx2; + vpx_hadamard_8x8 = vpx_hadamard_8x8_sse2; + if (flags & HAS_SSSE3) vpx_hadamard_8x8 = vpx_hadamard_8x8_ssse3; + vpx_idct32x32_1024_add = vpx_idct32x32_1024_add_sse2; + if (flags & HAS_SSSE3) vpx_idct32x32_1024_add = vpx_idct32x32_1024_add_ssse3; + vpx_idct32x32_135_add = vpx_idct32x32_1024_add_sse2; + if (flags & HAS_SSSE3) vpx_idct32x32_135_add = vpx_idct32x32_135_add_ssse3; + vpx_idct32x32_34_add = vpx_idct32x32_34_add_sse2; + if (flags & HAS_SSSE3) vpx_idct32x32_34_add = vpx_idct32x32_34_add_ssse3; + vpx_idct8x8_12_add = vpx_idct8x8_12_add_sse2; + if (flags & HAS_SSSE3) vpx_idct8x8_12_add = vpx_idct8x8_12_add_ssse3; + vpx_idct8x8_64_add = vpx_idct8x8_64_add_sse2; + if (flags & HAS_SSSE3) vpx_idct8x8_64_add = vpx_idct8x8_64_add_ssse3; + vpx_lpf_horizontal_16 = vpx_lpf_horizontal_16_sse2; + if (flags & HAS_AVX2) vpx_lpf_horizontal_16 = vpx_lpf_horizontal_16_avx2; + vpx_lpf_horizontal_16_dual = vpx_lpf_horizontal_16_dual_sse2; + if (flags & HAS_AVX2) vpx_lpf_horizontal_16_dual = vpx_lpf_horizontal_16_dual_avx2; + vpx_mse16x16 = vpx_mse16x16_sse2; + if (flags & HAS_AVX2) vpx_mse16x16 = vpx_mse16x16_avx2; + vpx_quantize_b = vpx_quantize_b_sse2; + if (flags & HAS_SSSE3) vpx_quantize_b = vpx_quantize_b_ssse3; + if (flags & HAS_AVX) vpx_quantize_b = vpx_quantize_b_avx; + vpx_quantize_b_32x32 = vpx_quantize_b_32x32_c; + if (flags & HAS_SSSE3) vpx_quantize_b_32x32 = vpx_quantize_b_32x32_ssse3; + if (flags & HAS_AVX) vpx_quantize_b_32x32 = vpx_quantize_b_32x32_avx; + vpx_sad16x16x3 = vpx_sad16x16x3_c; + if (flags & HAS_SSE3) vpx_sad16x16x3 = vpx_sad16x16x3_sse3; + if (flags & HAS_SSSE3) vpx_sad16x16x3 = vpx_sad16x16x3_ssse3; + vpx_sad16x16x8 = vpx_sad16x16x8_c; + if (flags & HAS_SSE4_1) vpx_sad16x16x8 = vpx_sad16x16x8_sse4_1; + vpx_sad16x8x3 = vpx_sad16x8x3_c; + if (flags & HAS_SSE3) vpx_sad16x8x3 = vpx_sad16x8x3_sse3; + if (flags & HAS_SSSE3) vpx_sad16x8x3 = vpx_sad16x8x3_ssse3; + vpx_sad16x8x8 = vpx_sad16x8x8_c; + if (flags & HAS_SSE4_1) vpx_sad16x8x8 = vpx_sad16x8x8_sse4_1; + vpx_sad32x16 = vpx_sad32x16_sse2; + if (flags & HAS_AVX2) vpx_sad32x16 = vpx_sad32x16_avx2; + vpx_sad32x16_avg = vpx_sad32x16_avg_sse2; + if (flags & HAS_AVX2) vpx_sad32x16_avg = vpx_sad32x16_avg_avx2; + vpx_sad32x32 = vpx_sad32x32_sse2; + if (flags & HAS_AVX2) vpx_sad32x32 = vpx_sad32x32_avx2; + vpx_sad32x32_avg = vpx_sad32x32_avg_sse2; + if (flags & HAS_AVX2) vpx_sad32x32_avg = vpx_sad32x32_avg_avx2; + vpx_sad32x32x4d = vpx_sad32x32x4d_sse2; + if (flags & HAS_AVX2) vpx_sad32x32x4d = vpx_sad32x32x4d_avx2; + vpx_sad32x64 = vpx_sad32x64_sse2; + if (flags & HAS_AVX2) vpx_sad32x64 = vpx_sad32x64_avx2; + vpx_sad32x64_avg = vpx_sad32x64_avg_sse2; + if (flags & HAS_AVX2) vpx_sad32x64_avg = vpx_sad32x64_avg_avx2; + vpx_sad4x4x3 = vpx_sad4x4x3_c; + if (flags & HAS_SSE3) vpx_sad4x4x3 = vpx_sad4x4x3_sse3; + vpx_sad4x4x8 = vpx_sad4x4x8_c; + if (flags & HAS_SSE4_1) vpx_sad4x4x8 = vpx_sad4x4x8_sse4_1; + vpx_sad64x32 = vpx_sad64x32_sse2; + if (flags & HAS_AVX2) vpx_sad64x32 = vpx_sad64x32_avx2; + vpx_sad64x32_avg = vpx_sad64x32_avg_sse2; + if (flags & HAS_AVX2) vpx_sad64x32_avg = vpx_sad64x32_avg_avx2; + vpx_sad64x64 = vpx_sad64x64_sse2; + if (flags & HAS_AVX2) vpx_sad64x64 = vpx_sad64x64_avx2; + vpx_sad64x64_avg = vpx_sad64x64_avg_sse2; + if (flags & HAS_AVX2) vpx_sad64x64_avg = vpx_sad64x64_avg_avx2; + vpx_sad64x64x4d = vpx_sad64x64x4d_sse2; + if (flags & HAS_AVX2) vpx_sad64x64x4d = vpx_sad64x64x4d_avx2; + vpx_sad8x16x3 = vpx_sad8x16x3_c; + if (flags & HAS_SSE3) vpx_sad8x16x3 = vpx_sad8x16x3_sse3; + vpx_sad8x16x8 = vpx_sad8x16x8_c; + if (flags & HAS_SSE4_1) vpx_sad8x16x8 = vpx_sad8x16x8_sse4_1; + vpx_sad8x8x3 = vpx_sad8x8x3_c; + if (flags & HAS_SSE3) vpx_sad8x8x3 = vpx_sad8x8x3_sse3; + vpx_sad8x8x8 = vpx_sad8x8x8_c; + if (flags & HAS_SSE4_1) vpx_sad8x8x8 = vpx_sad8x8x8_sse4_1; + vpx_scaled_2d = vpx_scaled_2d_c; + if (flags & HAS_SSSE3) vpx_scaled_2d = vpx_scaled_2d_ssse3; + vpx_sub_pixel_avg_variance16x16 = vpx_sub_pixel_avg_variance16x16_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance16x16 = vpx_sub_pixel_avg_variance16x16_ssse3; + vpx_sub_pixel_avg_variance16x32 = vpx_sub_pixel_avg_variance16x32_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance16x32 = vpx_sub_pixel_avg_variance16x32_ssse3; + vpx_sub_pixel_avg_variance16x8 = vpx_sub_pixel_avg_variance16x8_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance16x8 = vpx_sub_pixel_avg_variance16x8_ssse3; + vpx_sub_pixel_avg_variance32x16 = vpx_sub_pixel_avg_variance32x16_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance32x16 = vpx_sub_pixel_avg_variance32x16_ssse3; + vpx_sub_pixel_avg_variance32x32 = vpx_sub_pixel_avg_variance32x32_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance32x32 = vpx_sub_pixel_avg_variance32x32_ssse3; + if (flags & HAS_AVX2) vpx_sub_pixel_avg_variance32x32 = vpx_sub_pixel_avg_variance32x32_avx2; + vpx_sub_pixel_avg_variance32x64 = vpx_sub_pixel_avg_variance32x64_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance32x64 = vpx_sub_pixel_avg_variance32x64_ssse3; + vpx_sub_pixel_avg_variance4x4 = vpx_sub_pixel_avg_variance4x4_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance4x4 = vpx_sub_pixel_avg_variance4x4_ssse3; + vpx_sub_pixel_avg_variance4x8 = vpx_sub_pixel_avg_variance4x8_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance4x8 = vpx_sub_pixel_avg_variance4x8_ssse3; + vpx_sub_pixel_avg_variance64x32 = vpx_sub_pixel_avg_variance64x32_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance64x32 = vpx_sub_pixel_avg_variance64x32_ssse3; + vpx_sub_pixel_avg_variance64x64 = vpx_sub_pixel_avg_variance64x64_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance64x64 = vpx_sub_pixel_avg_variance64x64_ssse3; + if (flags & HAS_AVX2) vpx_sub_pixel_avg_variance64x64 = vpx_sub_pixel_avg_variance64x64_avx2; + vpx_sub_pixel_avg_variance8x16 = vpx_sub_pixel_avg_variance8x16_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance8x16 = vpx_sub_pixel_avg_variance8x16_ssse3; + vpx_sub_pixel_avg_variance8x4 = vpx_sub_pixel_avg_variance8x4_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance8x4 = vpx_sub_pixel_avg_variance8x4_ssse3; + vpx_sub_pixel_avg_variance8x8 = vpx_sub_pixel_avg_variance8x8_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_avg_variance8x8 = vpx_sub_pixel_avg_variance8x8_ssse3; + vpx_sub_pixel_variance16x16 = vpx_sub_pixel_variance16x16_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance16x16 = vpx_sub_pixel_variance16x16_ssse3; + vpx_sub_pixel_variance16x32 = vpx_sub_pixel_variance16x32_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance16x32 = vpx_sub_pixel_variance16x32_ssse3; + vpx_sub_pixel_variance16x8 = vpx_sub_pixel_variance16x8_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance16x8 = vpx_sub_pixel_variance16x8_ssse3; + vpx_sub_pixel_variance32x16 = vpx_sub_pixel_variance32x16_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance32x16 = vpx_sub_pixel_variance32x16_ssse3; + vpx_sub_pixel_variance32x32 = vpx_sub_pixel_variance32x32_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance32x32 = vpx_sub_pixel_variance32x32_ssse3; + if (flags & HAS_AVX2) vpx_sub_pixel_variance32x32 = vpx_sub_pixel_variance32x32_avx2; + vpx_sub_pixel_variance32x64 = vpx_sub_pixel_variance32x64_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance32x64 = vpx_sub_pixel_variance32x64_ssse3; + vpx_sub_pixel_variance4x4 = vpx_sub_pixel_variance4x4_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance4x4 = vpx_sub_pixel_variance4x4_ssse3; + vpx_sub_pixel_variance4x8 = vpx_sub_pixel_variance4x8_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance4x8 = vpx_sub_pixel_variance4x8_ssse3; + vpx_sub_pixel_variance64x32 = vpx_sub_pixel_variance64x32_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance64x32 = vpx_sub_pixel_variance64x32_ssse3; + vpx_sub_pixel_variance64x64 = vpx_sub_pixel_variance64x64_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance64x64 = vpx_sub_pixel_variance64x64_ssse3; + if (flags & HAS_AVX2) vpx_sub_pixel_variance64x64 = vpx_sub_pixel_variance64x64_avx2; + vpx_sub_pixel_variance8x16 = vpx_sub_pixel_variance8x16_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance8x16 = vpx_sub_pixel_variance8x16_ssse3; + vpx_sub_pixel_variance8x4 = vpx_sub_pixel_variance8x4_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance8x4 = vpx_sub_pixel_variance8x4_ssse3; + vpx_sub_pixel_variance8x8 = vpx_sub_pixel_variance8x8_sse2; + if (flags & HAS_SSSE3) vpx_sub_pixel_variance8x8 = vpx_sub_pixel_variance8x8_ssse3; + vpx_variance16x16 = vpx_variance16x16_sse2; + if (flags & HAS_AVX2) vpx_variance16x16 = vpx_variance16x16_avx2; + vpx_variance32x16 = vpx_variance32x16_sse2; + if (flags & HAS_AVX2) vpx_variance32x16 = vpx_variance32x16_avx2; + vpx_variance32x32 = vpx_variance32x32_sse2; + if (flags & HAS_AVX2) vpx_variance32x32 = vpx_variance32x32_avx2; + vpx_variance64x32 = vpx_variance64x32_sse2; + if (flags & HAS_AVX2) vpx_variance64x32 = vpx_variance64x32_avx2; + vpx_variance64x64 = vpx_variance64x64_sse2; + if (flags & HAS_AVX2) vpx_variance64x64 = vpx_variance64x64_avx2; +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libvpx/config/win/mingw64/vpx_scale_rtcd.h b/media/libvpx/config/win/mingw64/vpx_scale_rtcd.h new file mode 100644 index 000000000000..ddf7d01ccaa5 --- /dev/null +++ b/media/libvpx/config/win/mingw64/vpx_scale_rtcd.h @@ -0,0 +1,69 @@ +#ifndef VPX_SCALE_RTCD_H_ +#define VPX_SCALE_RTCD_H_ + +#ifdef RTCD_C +#define RTCD_EXTERN +#else +#define RTCD_EXTERN extern +#endif + +struct yv12_buffer_config; + +#ifdef __cplusplus +extern "C" { +#endif + +void vp8_horizontal_line_2_1_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width); +#define vp8_horizontal_line_2_1_scale vp8_horizontal_line_2_1_scale_c + +void vp8_horizontal_line_5_3_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width); +#define vp8_horizontal_line_5_3_scale vp8_horizontal_line_5_3_scale_c + +void vp8_horizontal_line_5_4_scale_c(const unsigned char *source, unsigned int source_width, unsigned char *dest, unsigned int dest_width); +#define vp8_horizontal_line_5_4_scale vp8_horizontal_line_5_4_scale_c + +void vp8_vertical_band_2_1_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width); +#define vp8_vertical_band_2_1_scale vp8_vertical_band_2_1_scale_c + +void vp8_vertical_band_2_1_scale_i_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width); +#define vp8_vertical_band_2_1_scale_i vp8_vertical_band_2_1_scale_i_c + +void vp8_vertical_band_5_3_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width); +#define vp8_vertical_band_5_3_scale vp8_vertical_band_5_3_scale_c + +void vp8_vertical_band_5_4_scale_c(unsigned char *source, unsigned int src_pitch, unsigned char *dest, unsigned int dest_pitch, unsigned int dest_width); +#define vp8_vertical_band_5_4_scale vp8_vertical_band_5_4_scale_c + +void vp8_yv12_copy_frame_c(const struct yv12_buffer_config *src_ybc, struct yv12_buffer_config *dst_ybc); +#define vp8_yv12_copy_frame vp8_yv12_copy_frame_c + +void vp8_yv12_extend_frame_borders_c(struct yv12_buffer_config *ybf); +#define vp8_yv12_extend_frame_borders vp8_yv12_extend_frame_borders_c + +void vpx_extend_frame_borders_c(struct yv12_buffer_config *ybf); +#define vpx_extend_frame_borders vpx_extend_frame_borders_c + +void vpx_extend_frame_inner_borders_c(struct yv12_buffer_config *ybf); +#define vpx_extend_frame_inner_borders vpx_extend_frame_inner_borders_c + +void vpx_yv12_copy_y_c(const struct yv12_buffer_config *src_ybc, struct yv12_buffer_config *dst_ybc); +#define vpx_yv12_copy_y vpx_yv12_copy_y_c + +void vpx_scale_rtcd(void); + +#ifdef RTCD_C +#include "vpx_ports/x86.h" +static void setup_rtcd_internal(void) +{ + int flags = x86_simd_caps(); + + (void)flags; + +} +#endif + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif diff --git a/media/libvpx/moz.build b/media/libvpx/moz.build old mode 100755 new mode 100644 index 48385dd9386f..f2e05075450a --- a/media/libvpx/moz.build +++ b/media/libvpx/moz.build @@ -17,8 +17,12 @@ if CONFIG['CPU_ARCH'] == 'x86_64': EXPORTS.vpx += files['X64_EXPORTS'] SOURCES += files['X64_SOURCES'] if CONFIG['OS_TARGET'] == 'WINNT': - ASFLAGS += [ '-I%s/media/libvpx/config/win/x64/' % TOPSRCDIR ] - LOCAL_INCLUDES += [ '/media/libvpx/config/win/x64/' ] + if CONFIG['CC_TYPE'] == 'gcc': + ASFLAGS += [ '-I%s/media/libvpx/config/win/mingw64/' % TOPSRCDIR ] + LOCAL_INCLUDES += [ '/media/libvpx/config/win/mingw64/' ] + else: + ASFLAGS += [ '-I%s/media/libvpx/config/win/x64/' % TOPSRCDIR ] + LOCAL_INCLUDES += [ '/media/libvpx/config/win/x64/' ] elif CONFIG['OS_TARGET'] == 'Darwin': ASFLAGS += [ '-I%s/media/libvpx/config/mac/x64/' % TOPSRCDIR ] LOCAL_INCLUDES += [ '/media/libvpx/config/mac/x64/' ]

1 0

[tor-browser-build/master] Bug 26206: Ship pthread related dll with tor
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 907be0ba29c55bac51f47afe1cf8777c5037ffe6 Author: Nicolas Vigier <boklm(a)torproject.org> Date: Thu Jun 14 11:25:15 2018 +0200 Bug 26206: Ship pthread related dll with tor --- projects/tor/build | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/projects/tor/build b/projects/tor/build index 3f845ea..8f129d6 100644 --- a/projects/tor/build +++ b/projects/tor/build @@ -31,8 +31,9 @@ openssldir=/var/tmp/dist/openssl [% IF c("var/windows") %] tar -C /var/tmp/build -xf [% c('input_files_by_name/zlib') %] zlibdir=/var/tmp/build/zlib + mingwlibs=/var/tmp/dist/mingw-w64/[% c("arch") %]-w64-mingw32/bin/ cp $zlibdir/lib/*.dll $openssldir/bin/*.dll $libeventdir/bin/*.dll \ - $gcclibs/*.dll $distdir/Tor/ + $gcclibs/*.dll $mingwlibs/libwinpthread-1.dll $distdir/Tor/ [% END %] [% IF c("var/linux") %]

1 0

[tor-browser-build/master] Bug 26370: Don't copy msvcr100.dll and libssp-0.dll twice
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 37d406206a0d7ec43ae4bcd35889a97fc85eff32 Author: Nicolas Vigier <boklm(a)torproject.org> Date: Thu Jun 14 11:04:43 2018 +0200 Bug 26370: Don't copy msvcr100.dll and libssp-0.dll twice --- projects/firefox/build | 5 ----- 1 file changed, 5 deletions(-) diff --git a/projects/firefox/build b/projects/firefox/build index 3ca8b32..0fd3da2 100644 --- a/projects/firefox/build +++ b/projects/firefox/build @@ -213,11 +213,6 @@ cd $distdir [% c("var/rezip", { rezip_file => '"Tor Browser.app/Contents/Resources/browser/omni.ja"' }) %] [% END %] -[% IF c("var/windows") %] - cp $rootdir/msvcr100.dll Browser/ - cp $gcclibs/libssp-0.dll Browser/ -[% END %] - mkdir -p [% dest_dir _ '/' _ c('filename') %] [%

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 1463509 - SOCKS support for Alternative Services r=valentin
by gk＠torproject.org 14 Jun '18

14 Jun '18

commit 8a68f975ee5faa39efa26a79062476ab50dd18ab Author: Patrick McManus <mcmanus(a)ducksong.com> Date: Tue May 22 13:50:56 2018 -0400 Bug 1463509 - SOCKS support for Alternative Services r=valentin MozReview-Commit-ID: 1oXnQuzOqsC --HG-- extra : rebase_source : 84bfaec48c5fc216da6586e7f06f118292d3fb17 --- netwerk/base/nsSocketTransport2.cpp | 32 +++++++++++++++++++++-------- netwerk/protocol/http/AlternateServices.cpp | 8 +++++++- netwerk/protocol/http/AlternateServices.h | 4 ++++ netwerk/protocol/http/nsHttpChannel.cpp | 5 ++--- 4 files changed, 37 insertions(+), 12 deletions(-) diff --git a/netwerk/base/nsSocketTransport2.cpp b/netwerk/base/nsSocketTransport2.cpp index df01e62f55d3..aa9232f4698c 100644 --- a/netwerk/base/nsSocketTransport2.cpp +++ b/netwerk/base/nsSocketTransport2.cpp @@ -1170,7 +1170,7 @@ nsSocketTransport::BuildSocket(PRFileDesc *&fd, bool &proxyTransparent, bool &us uint32_t controlFlags = 0; uint32_t i; - for (i=0; i<mTypeCount; ++i) { + for (i = 0; i < mTypeCount; ++i) { nsCOMPtr<nsISocketProvider> provider; SOCKET_LOG((" pushing io layer [%u:%s]\n", i, mTypes[i])); @@ -1199,12 +1199,30 @@ nsSocketTransport::BuildSocket(PRFileDesc *&fd, bool &proxyTransparent, bool &us // if this is the first type, we'll want the // service to allocate a new socket + // Most layers _ESPECIALLY_ PSM want the origin name here as they + // will use it for secure checks, etc.. and any connection management + // differences between the origin name and the routed name can be + // taken care of via DNS. However, SOCKS is a special case as there is + // no DNS. in the case of SOCKS and PSM the PSM is a separate layer + // and receives the origin name. + const char *socketProviderHost = host; + int32_t socketProviderPort = port; + if (mProxyTransparentResolvesHost && + (!strcmp(mTypes[0], "socks") || !strcmp(mTypes[0], "socks4"))) { + SOCKET_LOG(("SOCKS %d Host/Route override: %s:%d -> %s:%d\n", + mHttpsProxy, + socketProviderHost, socketProviderPort, + mHost.get(), mPort)); + socketProviderHost = mHost.get(); + socketProviderPort = mPort; + } + // when https proxying we want to just connect to the proxy as if // it were the end host (i.e. expect the proxy's cert) rv = provider->NewSocket(mNetAddr.raw.family, - mHttpsProxy ? mProxyHost.get() : host, - mHttpsProxy ? mProxyPort : port, + mHttpsProxy ? mProxyHost.get() : socketProviderHost, + mHttpsProxy ? mProxyPort : socketProviderPort, proxyInfo, mOriginAttributes, controlFlags, mTlsFlags, &fd, getter_AddRefs(secinfo)); @@ -1213,8 +1231,7 @@ nsSocketTransport::BuildSocket(PRFileDesc *&fd, bool &proxyTransparent, bool &us NS_NOTREACHED("NewSocket succeeded but failed to create a PRFileDesc"); rv = NS_ERROR_UNEXPECTED; } - } - else { + } else { // the socket has already been allocated, // so we just want the service to add itself // to the stack (such as pushing an io layer) @@ -1245,9 +1262,8 @@ nsSocketTransport::BuildSocket(PRFileDesc *&fd, bool &proxyTransparent, bool &us secCtrl->SetNotificationCallbacks(callbacks); // remember if socket type is SSL so we can ProxyStartSSL if need be. usingSSL = isSSL; - } - else if ((strcmp(mTypes[i], "socks") == 0) || - (strcmp(mTypes[i], "socks4") == 0)) { + } else if ((strcmp(mTypes[i], "socks") == 0) || + (strcmp(mTypes[i], "socks4") == 0)) { // since socks is transparent, any layers above // it do not have to worry about proxy stuff proxyInfo = nullptr; diff --git a/netwerk/protocol/http/AlternateServices.cpp b/netwerk/protocol/http/AlternateServices.cpp index 2ce3d333d60d..f4cfa800715b 100644 --- a/netwerk/protocol/http/AlternateServices.cpp +++ b/netwerk/protocol/http/AlternateServices.cpp @@ -46,6 +46,12 @@ SchemeIsHTTPS(const nsACString &originScheme, bool &outIsHTTPS) return NS_OK; } +bool +AltSvcMapping::AcceptableProxy(nsProxyInfo *proxyInfo) +{ + return !proxyInfo || proxyInfo->IsDirect() || proxyInfo->IsSOCKS(); +} + void AltSvcMapping::ProcessHeader(const nsCString &buf, const nsCString &originScheme, const nsCString &originHost, int32_t originPort, @@ -59,7 +65,7 @@ AltSvcMapping::ProcessHeader(const nsCString &buf, const nsCString &originScheme return; } - if (proxyInfo && !proxyInfo->IsDirect()) { + if (!AcceptableProxy(proxyInfo)) { LOG(("AltSvcMapping::ProcessHeader ignoring due to proxy\n")); return; } diff --git a/netwerk/protocol/http/AlternateServices.h b/netwerk/protocol/http/AlternateServices.h index 051f010801b4..688586ba5b89 100644 --- a/netwerk/protocol/http/AlternateServices.h +++ b/netwerk/protocol/http/AlternateServices.h @@ -66,6 +66,10 @@ public: nsIInterfaceRequestor *callbacks, nsProxyInfo *proxyInfo, uint32_t caps, const OriginAttributes &originAttributes); + // AcceptableProxy() decides whether a particular proxy configuration (pi) is suitable + // for use with Alt-Svc. No proxy (including a null pi) is suitable. + static bool AcceptableProxy(nsProxyInfo *pi); + const nsCString &AlternateHost() const { return mAlternateHost; } const nsCString &OriginHost() const { return mOriginHost; } uint32_t OriginPort() const { return mOriginPort; } diff --git a/netwerk/protocol/http/nsHttpChannel.cpp b/netwerk/protocol/http/nsHttpChannel.cpp index 28ff7709863e..35b4b4dfeb1e 100644 --- a/netwerk/protocol/http/nsHttpChannel.cpp +++ b/netwerk/protocol/http/nsHttpChannel.cpp @@ -6163,9 +6163,8 @@ nsHttpChannel::BeginConnect() RefPtr<AltSvcMapping> mapping; if (!mConnectionInfo && mAllowAltSvc && // per channel !(mLoadFlags & LOAD_FRESH_CONNECTION) && - (scheme.EqualsLiteral("http") || - scheme.EqualsLiteral("https")) && - (!proxyInfo || proxyInfo->IsDirect()) && + AltSvcMapping::AcceptableProxy(proxyInfo) && + (scheme.EqualsLiteral("http") || scheme.EqualsLiteral("https")) && (mapping = gHttpHandler->GetAltServiceMapping(scheme, host, port, mPrivateBrowsing,

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Revert "Bug 23916: Add new MAR signing key"
by gk＠torproject.org 13 Jun '18

13 Jun '18

commit d77a0ec835e8ee8e4beab614722c02fa7fd96119 Author: Georg Koppen <gk(a)torproject.org> Date: Wed Jun 13 08:58:27 2018 +0000 Revert "Bug 23916: Add new MAR signing key" This reverts commit e984b8c54c7592057c060f7a2e13b378a355b1d0. --- toolkit/mozapps/update/updater/release_primary.der | Bin 1229 -> 1225 bytes toolkit/mozapps/update/updater/release_secondary.der | Bin 1229 -> 1225 bytes 2 files changed, 0 insertions(+), 0 deletions(-) diff --git a/toolkit/mozapps/update/updater/release_primary.der b/toolkit/mozapps/update/updater/release_primary.der index cce786025698..1d94f88ad73b 100644 Binary files a/toolkit/mozapps/update/updater/release_primary.der and b/toolkit/mozapps/update/updater/release_primary.der differ diff --git a/toolkit/mozapps/update/updater/release_secondary.der b/toolkit/mozapps/update/updater/release_secondary.der index caf3eca56804..474706c4b73c 100644 Binary files a/toolkit/mozapps/update/updater/release_secondary.der and b/toolkit/mozapps/update/updater/release_secondary.der differ

1 0

[tor-browser/tor-browser-60.0.1esr-8.0-1] Bug 26045: Add new MAR signing keys
by gk＠torproject.org 13 Jun '18

13 Jun '18

commit 1f78032d48850e0197608ac1d9906a095e2a4c06 Author: Georg Koppen <gk(a)torproject.org> Date: Wed Jun 13 09:03:59 2018 +0000 Bug 26045: Add new MAR signing keys We need to have new MAR singning keys for our watershed update: both keys we shipped so far need to get replaced by news ones, now using SHA-384 as their hash algorithm. --- toolkit/mozapps/update/updater/release_primary.der | Bin 1225 -> 1229 bytes toolkit/mozapps/update/updater/release_secondary.der | Bin 1225 -> 1229 bytes 2 files changed, 0 insertions(+), 0 deletions(-) diff --git a/toolkit/mozapps/update/updater/release_primary.der b/toolkit/mozapps/update/updater/release_primary.der index 1d94f88ad73b..ec74f89dc807 100644 Binary files a/toolkit/mozapps/update/updater/release_primary.der and b/toolkit/mozapps/update/updater/release_primary.der differ diff --git a/toolkit/mozapps/update/updater/release_secondary.der b/toolkit/mozapps/update/updater/release_secondary.der index 474706c4b73c..0103a171de88 100644 Binary files a/toolkit/mozapps/update/updater/release_secondary.der and b/toolkit/mozapps/update/updater/release_secondary.der differ

1 0

[tor-browser-build/master] Bug 26354: check for SSE2 support before updating Linux users
by gk＠torproject.org 13 Jun '18

13 Jun '18

commit 17d7ca8fb2be71b72b429c59fed8a10c042a4a49 Author: Nicolas Vigier <boklm(a)torproject.org> Date: Tue Jun 12 20:09:56 2018 +0200 Bug 26354: check for SSE2 support before updating Linux users We were setting the minSupportedInstructionSet attribute for the win32 updates only. We now set it on all platforms. --- projects/release/update_responses_config.yml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/projects/release/update_responses_config.yml b/projects/release/update_responses_config.yml index 1a9b0cf..6861124 100644 --- a/projects/release/update_responses_config.yml +++ b/projects/release/update_responses_config.yml @@ -38,8 +38,7 @@ versions: osx32: osx64 migrate_langs: pt-PT: pt-BR - win32: - minSupportedInstructionSet: SSE2 + minSupportedInstructionSet: SSE2 osx32: minSupportedOSVersion: 13.0.0 osx64:

1 0

[tor-browser-build/master] Merge remote-tracking branch 'boklm/bug_26354'
by gk＠torproject.org 13 Jun '18

13 Jun '18

commit f606f5d9d55a171e0a6f57ad58e1052c9f7c149d Merge: 3cab74a 17d7ca8 Author: Georg Koppen <gk(a)torproject.org> Date: Wed Jun 13 09:35:34 2018 +0000 Merge remote-tracking branch 'boklm/bug_26354' projects/release/update_responses_config.yml | 3 +-- projects/tor-browser/RelativeLink/start-tor-browser | 5 +++++ 2 files changed, 6 insertions(+), 2 deletions(-)

1 0

[tor-browser-build/master] Bug 26354: check for SSE2 support in start-tor-browser
by gk＠torproject.org 13 Jun '18

13 Jun '18

commit fb3315fbc961f924012dcf97d346ce9527f85505 Author: Nicolas Vigier <boklm(a)torproject.org> Date: Tue Jun 12 20:02:49 2018 +0200 Bug 26354: check for SSE2 support in start-tor-browser --- projects/tor-browser/RelativeLink/start-tor-browser | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/projects/tor-browser/RelativeLink/start-tor-browser b/projects/tor-browser/RelativeLink/start-tor-browser index 0590eed..6639f44 100755 --- a/projects/tor-browser/RelativeLink/start-tor-browser +++ b/projects/tor-browser/RelativeLink/start-tor-browser @@ -96,6 +96,11 @@ if [ "`id -u`" -eq 0 ]; then exit 1 fi +if ! grep -q '^flags\s*:.* sse2' /proc/cpuinfo; then + complain "Tor Browser requires a CPU with SSE2 support. Exiting." + exit 1 +fi + tbb_usage () { printf "\nTor Browser Script Options\n" printf " --verbose Display Tor and Firefox output in the terminal\n"

1 0

[tor-browser-build/master] Bug 26234: add update_responses option to specify rewrite rules
by gk＠torproject.org 13 Jun '18

13 Jun '18

commit 3cab74acf8a2f2a311c133544ccc8c00a43e00a2 Author: Nicolas Vigier <boklm(a)torproject.org> Date: Mon Jun 11 17:49:03 2018 +0200 Bug 26234: add update_responses option to specify rewrite rules Add the htaccess_rewrite_rules option which can be used to specify rewrite rules to be added to the generated .htaccess files. --- tools/update-responses/update_responses | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/update-responses/update_responses b/tools/update-responses/update_responses index 1df35b3..77b9c96 100755 --- a/tools/update-responses/update_responses +++ b/tools/update-responses/update_responses @@ -376,6 +376,7 @@ sub write_htaccess { my $flags = "[last]"; foreach my $channel (@channels) { my $htaccess = "RewriteEngine On\n"; + $htaccess .= $config->{htaccess_rewrite_rules}{$channel} // ''; my $version = $config->{channels}{$channel}; my $migrate_langs = $config->{versions}{$version}{migrate_langs} // {}; my $files = $config->{versions}{$version}{files};

1 0

[tor-browser-build/maint-7.5] Release preparations for 7.5.5
by gk＠torproject.org 08 Jun '18

08 Jun '18

commit d0e565d00e236e331f8ebf040b4225b6875d471f Author: Georg Koppen <gk(a)torproject.org> Date: Fri Jun 8 21:25:47 2018 +0000 Release preparations for 7.5.5 Changelog update and versions bump --- projects/firefox/config | 4 ++-- projects/tor-browser/Bundle-Data/Docs/ChangeLog.txt | 5 +++++ rbm.conf | 4 ++-- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/projects/firefox/config b/projects/firefox/config index 886cfdc..e91d1ca 100644 --- a/projects/firefox/config +++ b/projects/firefox/config @@ -1,13 +1,13 @@ # vim: filetype=yaml sw=2 version: '[% c("abbrev") %]' filename: 'firefox-[% c("version") %]-[% c("var/osname") %]-[% c("var/build_id") %]' -git_hash: 'tor-browser-[% c("var/firefox_version") %]-[% c("var/torbrowser_branch") %]-1-build2' +git_hash: 'tor-browser-[% c("var/firefox_version") %]-[% c("var/torbrowser_branch") %]-1-build1' tag_gpg_id: 1 git_url: https://git.torproject.org/tor-browser.git gpg_keyring: torbutton.gpg var: - firefox_platform_version: 52.8.0 + firefox_platform_version: 52.8.1 firefox_version: '[% c("var/firefox_platform_version") %]esr' torbrowser_branch: 7.5 torbrowser_update_channel: alpha diff --git a/projects/tor-browser/Bundle-Data/Docs/ChangeLog.txt b/projects/tor-browser/Bundle-Data/Docs/ChangeLog.txt index 7f5a736..5d52b10 100644 --- a/projects/tor-browser/Bundle-Data/Docs/ChangeLog.txt +++ b/projects/tor-browser/Bundle-Data/Docs/ChangeLog.txt @@ -1,3 +1,8 @@ +Tor Browser 7.5.5 -- June 10 2018 + * All platforms + * Update Firefox to 52.8.1esr + * Bug 26098: Remove amazon-meek + Tor Browser 7.5.4 -- May 9 2018 * All platforms * Update Firefox to 52.8.0esr diff --git a/rbm.conf b/rbm.conf index ca427f9..4329958 100644 --- a/rbm.conf +++ b/rbm.conf @@ -15,10 +15,10 @@ buildconf: git_signtag_opt: '-s' var: - torbrowser_version: '7.5.4' + torbrowser_version: '7.5.5' torbrowser_build: 'build1' torbrowser_incremental_from: - - 7.5.3 + - 7.5.4 project_name: tor-browser multi_lingual: 0 build_mar: 1

1 0

[tor-browser-build/master] Bug 24632: Install xz-utils for macOS MAR file creation
by gk＠torproject.org 07 Jun '18

07 Jun '18

commit aabed936170b9ea88df2037e8d452dc5d9915f20 Author: Georg Koppen <gk(a)torproject.org> Date: Thu Jun 7 10:39:48 2018 +0000 Bug 24632: Install xz-utils for macOS MAR file creation --- projects/tor-browser/config | 1 + 1 file changed, 1 insertion(+) diff --git a/projects/tor-browser/config b/projects/tor-browser/config index 62ed70c..225a0bb 100644 --- a/projects/tor-browser/config +++ b/projects/tor-browser/config @@ -24,6 +24,7 @@ targets: - python - bzip2 - faketime + - xz-utils windows: var: arch_deps:

1 0

[tor-browser-build/master] Bug 24632: Make sure to use "Tor Browser.app" for `browserdir` on macOS
by gk＠torproject.org 07 Jun '18

07 Jun '18

commit fcb2a3707af71bcd564bf0dd8a563835eeea6b9b Author: Georg Koppen <gk(a)torproject.org> Date: Thu Jun 7 10:40:47 2018 +0000 Bug 24632: Make sure to use "Tor Browser.app" for `browserdir` on macOS --- projects/tor-browser/build | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/projects/tor-browser/build b/projects/tor-browser/build index d807633..19aa657 100644 --- a/projects/tor-browser/build +++ b/projects/tor-browser/build @@ -311,7 +311,7 @@ cp $rootdir/[% c('input_files_by_name/firefox') %]/mar-tools-*.zip "$OUTDIR"/ SET xpi = '$rootdir/' _ c('input_files_by_name/firefox-langpacks') _ '/' _ lang _ '.xpi'; SET tbdir = '$distdir/tor-browser_' _ lang; IF c("var/osx"); - SET browserdir = tbdir _ '/TorBrowser.app'; + SET browserdir = tbdir _ '/Tor Browser.app'; ELSIF c("var/windows"); SET browserdir = tbdir _ '/Tor Browser/Browser'; ELSE;

1 0

[tor-browser-build/master] Bug 26153: Enable selfrando for 64bit only for now
by gk＠torproject.org 07 Jun '18

07 Jun '18

commit 8b30ee00debb11a1c165435d304a406c8408f216 Author: Georg Koppen <gk(a)torproject.org> Date: Thu Jun 7 06:02:16 2018 +0000 Bug 26153: Enable selfrando for 64bit only for now The 32bit toolchain is not able to link libxul anymore with selfrando enabled as the linker is running out of address space. We therefore disable selfrando for 32bit for now. --- rbm.conf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/rbm.conf b/rbm.conf index b3dd729..de5102d 100644 --- a/rbm.conf +++ b/rbm.conf @@ -165,7 +165,7 @@ targets: # We only build snowflake for linux on the alpha and nightly channels for now. snowflake: '[% c("var/alpha") || c("var/nightly") %]' fteproxy: 1 - selfrando: '[% ! c("var/release") %]' + selfrando: '[% c("var/linux-x86_64") && ! c("var/release") %]' container: suite: wheezy deps:

1 0

[tor-browser-build/master] Merge remote-tracking branch 'boklm/bug_22242'
by gk＠torproject.org 06 Jun '18

06 Jun '18

commit 2dfbef2eecb1ca19467b095b16c18f9c78d28445 Merge: 4074cbc 6063d5c Author: Georg Koppen <gk(a)torproject.org> Date: Wed Jun 6 19:09:08 2018 +0000 Merge remote-tracking branch 'boklm/bug_22242' projects/firefox/build | 6 +++++- projects/firefox/config | 4 +++- rbm.conf | 1 + 3 files changed, 9 insertions(+), 2 deletions(-) diff --cc projects/firefox/config index 97efc7b,21efac7..6cb17c7 --- a/projects/firefox/config +++ b/projects/firefox/config @@@ -83,11 -84,9 +85,11 @@@ input_files enable: '[% c("var/linux") %]' - project: selfrando name: selfrando - enable: '[% c("var/linux") && ! c("var/release") %]' + enable: '[% c("var/selfrando") %]' - filename: fix-info-plist.py enable: '[% c("var/osx") %]' + - filename: no-dmg.patch + enable: '[% c("var/osx") %]' - URL: https://people.torproject.org/~gk/mirrors/sources/msvcr100.dll sha256sum: 8793353461826fbd48f25ea8b835be204b758ce7510db2af631b28850355bd18 enable: '[% c("var/windows-i686") %]' diff --cc rbm.conf index 28ce6f9,c1b49f0..b3dd729 --- a/rbm.conf +++ b/rbm.conf @@@ -162,9 -162,11 +162,10 @@@ targets var: linux: 1 compiler: gcc - # We only build snowflake for linux and osx on the alpha and nightly - # channels for now. + # We only build snowflake for linux on the alpha and nightly channels for now. snowflake: '[% c("var/alpha") || c("var/nightly") %]' fteproxy: 1 + selfrando: '[% ! c("var/release") %]' container: suite: wheezy deps:

1 0

[tor-browser-build/master] Bug 22242: use chrpath to remove RUNPATH added by selfrando
by gk＠torproject.org 06 Jun '18

06 Jun '18

commit 6063d5c6433a294176593a070138350cc723dbfa Author: Nicolas Vigier <boklm(a)torproject.org> Date: Wed May 23 16:39:25 2018 +0200 Bug 22242: use chrpath to remove RUNPATH added by selfrando At the same time we add a var/selfrando variable to make it easier to enable/disable selfrando. --- projects/firefox/build | 6 +++++- projects/firefox/config | 4 +++- rbm.conf | 1 + 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/projects/firefox/build b/projects/firefox/build index a7441bd..ea3826d 100644 --- a/projects/firefox/build +++ b/projects/firefox/build @@ -23,7 +23,7 @@ mkdir -p /var/tmp/build export PATH="/var/tmp/dist/binutils/bin:$PATH" [% END -%] -[% IF c("var/linux") && ! c("var/release") -%] +[% IF c("var/selfrando") -%] tar -C /var/tmp/dist -xf $rootdir/[% c('input_files_by_name/selfrando') %] # Selfrando wrapper export PATH="/var/tmp/dist/selfrando/Tools/TorBrowser/tc-wrapper/:$PATH" @@ -161,6 +161,10 @@ cd $distdir objcopy --only-keep-debug $LIB Debug/$LIB strip $LIB objcopy --add-gnu-debuglink=./Debug/$LIB $LIB + [% IF c("var/selfrando") -%] + # remove RUNPATH added by selfrando (see #22242) + chrpath -d $LIB + [% END -%] done [% END %] diff --git a/projects/firefox/config b/projects/firefox/config index 4458d48..21efac7 100644 --- a/projects/firefox/config +++ b/projects/firefox/config @@ -48,6 +48,8 @@ targets: - libx11-xcb-dev # We built GCC but not the libmpc2, thus we need to install it - libmpc2 + # needed to remove RUNPATH added by selfrando (see #22242) + - chrpath linux-x86_64: var: martools_filename: mar-tools-linux64.zip @@ -82,7 +84,7 @@ input_files: enable: '[% c("var/linux") %]' - project: selfrando name: selfrando - enable: '[% c("var/linux") && ! c("var/release") %]' + enable: '[% c("var/selfrando") %]' - filename: fix-info-plist.py enable: '[% c("var/osx") %]' - URL: https://people.torproject.org/~gk/mirrors/sources/msvcr100.dll diff --git a/rbm.conf b/rbm.conf index bb53bcb..c1b49f0 100644 --- a/rbm.conf +++ b/rbm.conf @@ -166,6 +166,7 @@ targets: # channels for now. snowflake: '[% c("var/alpha") || c("var/nightly") %]' fteproxy: 1 + selfrando: '[% ! c("var/release") %]' container: suite: wheezy deps:

1 0

[tor-browser-build/master] Bug 26153: Selfrando builds broken for Firefox 60 ESR
by gk＠torproject.org 06 Jun '18

06 Jun '18

commit d161cb720ea36ccd547acd385752fe353279761f Author: Sukhbir Singh <sukhbir(a)torproject.org> Date: Wed Jun 6 11:01:19 2018 -0400 Bug 26153: Selfrando builds broken for Firefox 60 ESR This commit fixes #26153 by bumping the selfrando version to 0.4.2 --- projects/firefox/build | 14 +++++++------- projects/firefox/config | 6 +++--- projects/selfrando/config | 2 +- 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/projects/firefox/build b/projects/firefox/build index 62186d1..cbd9250 100644 --- a/projects/firefox/build +++ b/projects/firefox/build @@ -40,13 +40,13 @@ EOF export PATH="/var/tmp/dist/binutils/bin:$PATH" [% END -%] -#[% IF c("var/linux") && ! c("var/release") -%] -# tar -C /var/tmp/dist -xf $rootdir/[% c('input_files_by_name/selfrando') %] -# # Selfrando wrapper -# export PATH="/var/tmp/dist/selfrando/Tools/TorBrowser/tc-wrapper/:$PATH" -# # We need to avoid the shuffling while building as this breaks compilation -# export SELFRANDO_skip_shuffle= -#[% END -%] +[% IF c("var/linux") && ! c("var/release") -%] + tar -C /var/tmp/dist -xf $rootdir/[% c('input_files_by_name/selfrando') %] + # Selfrando wrapper + export PATH="/var/tmp/dist/selfrando/Tools/TorBrowser/tc-wrapper/:$PATH" + # We need to avoid the shuffling while building as this breaks compilation + export SELFRANDO_skip_shuffle= +[% END -%] [% IF c("var/linux") %] mkdir -p /var/tmp/dist diff --git a/projects/firefox/config b/projects/firefox/config index d6b8313..418daa3 100644 --- a/projects/firefox/config +++ b/projects/firefox/config @@ -81,9 +81,9 @@ input_files: - project: binutils name: binutils enable: '[% c("var/linux") %]' -# - project: selfrando -# name: selfrando -# enable: '[% c("var/linux") && ! c("var/release") %]' + - project: selfrando + name: selfrando + enable: '[% c("var/linux") && ! c("var/release") %]' - filename: fix-info-plist.py enable: '[% c("var/osx") %]' - URL: https://people.torproject.org/~gk/mirrors/sources/msvcr100.dll diff --git a/projects/selfrando/config b/projects/selfrando/config index 07195f7..82acc23 100644 --- a/projects/selfrando/config +++ b/projects/selfrando/config @@ -1,6 +1,6 @@ # vim: filetype=yaml sw=2 filename: '[% project %]-[% c("version") %]-[% c("var/osname") %]-[% c("var/build_id") %].tar.gz' -version: 0.4.1 +version: 0.4.2 git_hash: 'tb-v[% c("version") %]' git_url: https://github.com/immunant/selfrando.git gpg_keyring: selfrando.gpg

1 0

[tor-browser-build/master] Merge remote-tracking branch 'sukhe/bug-26153'
by gk＠torproject.org 06 Jun '18

06 Jun '18

commit 4074cbc2a727daf51ff9fdab29e0a0da3ec078aa Merge: e76952c d161cb7 Author: Georg Koppen <gk(a)torproject.org> Date: Wed Jun 6 19:02:02 2018 +0000 Merge remote-tracking branch 'sukhe/bug-26153' projects/firefox/build | 14 +++++++------- projects/firefox/config | 6 +++--- projects/selfrando/config | 2 +- 3 files changed, 11 insertions(+), 11 deletions(-) diff --cc projects/firefox/build index 8278c14,cbd9250..83a7691 --- a/projects/firefox/build +++ b/projects/firefox/build @@@ -40,15 -40,15 +40,15 @@@ EO export PATH="/var/tmp/dist/binutils/bin:$PATH" [% END -%] - #[% IF c("var/linux") && ! c("var/release") -%] - # tar -C /var/tmp/dist -xf $rootdir/[% c('input_files_by_name/selfrando') %] - # # Selfrando wrapper - # export PATH="/var/tmp/dist/selfrando/Tools/TorBrowser/tc-wrapper/:$PATH" - # # We need to avoid the shuffling while building as this breaks compilation - # export SELFRANDO_skip_shuffle= - #[% END -%] + [% IF c("var/linux") && ! c("var/release") -%] + tar -C /var/tmp/dist -xf $rootdir/[% c('input_files_by_name/selfrando') %] + # Selfrando wrapper + export PATH="/var/tmp/dist/selfrando/Tools/TorBrowser/tc-wrapper/:$PATH" + # We need to avoid the shuffling while building as this breaks compilation + export SELFRANDO_skip_shuffle= + [% END -%] -[% IF c("var/linux") %] +[% IF ! c("var/windows") %] mkdir -p /var/tmp/dist tar -C /var/tmp/dist -xf [% c('input_files_by_name/rust') %] export PATH="/var/tmp/dist/rust/bin:$PATH" diff --cc projects/firefox/config index 927fb0b,418daa3..97efc7b --- a/projects/firefox/config +++ b/projects/firefox/config @@@ -81,13 -81,11 +81,13 @@@ input_files - project: binutils name: binutils enable: '[% c("var/linux") %]' - # - project: selfrando - # name: selfrando - # enable: '[% c("var/linux") && ! c("var/release") %]' + - project: selfrando + name: selfrando + enable: '[% c("var/linux") && ! c("var/release") %]' - filename: fix-info-plist.py enable: '[% c("var/osx") %]' + - filename: no-dmg.patch + enable: '[% c("var/osx") %]' - URL: https://people.torproject.org/~gk/mirrors/sources/msvcr100.dll sha256sum: 8793353461826fbd48f25ea8b835be204b758ce7510db2af631b28850355bd18 enable: '[% c("var/windows-i686") %]'

1 0

Jump to page: