coffee/libyuv
1
0
Fork 0
mirror of https://chromium.googlesource.com/libyuv/libyuv synced 2025-12-10 02:36:46 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,403 Commits 3 Branches 0 Tags BSD-3-Clause 60 MiB
Commit Graph

1092 Commits

Author SHA1 Message Date
Frank Barchard
97b35daf75 disable faulty avx2 in argb conversions and box filter. and extend temporary buffer to 128 for an avx2 any function. 
R=harryjin@google.com
BUG=libyuv:462
TESTED=libyuv_unittest run on haswell laptop

Review URL: https://webrtc-codereview.appspot.com/53759004.
 2015-07-07 15:40:24 -07:00
Frank Barchard
9487b9d6d8 any allow for avx2 32 pixels at a time of argb 
R=harryjin@google.com
BUG=libyuv:461

Review URL: https://webrtc-codereview.appspot.com/54779004.
 2015-07-01 17:50:48 -07:00
Frank Barchard
cff11a17d6 remove tools from git that were previously checkin by accident. 
R=harryjin@google.com, brucedawson@chromium.org

BUG=none
TESTED=untested

Review URL: https://webrtc-codereview.appspot.com/56619004.
 2015-06-30 10:45:24 -07:00
Frank Barchard
82180e8296 rgb24toyuv use 1 or 2 steps consistently. 
R=bcornell@google.com, impjdi@google.com
BUG=libyuv:459

Review URL: https://webrtc-codereview.appspot.com/52149004.
 2015-06-29 16:51:05 -07:00
Frank Barchard
0686f26938 blend remove alignment 1 pixel loop for less overhead. 
R=tpsiaki@google.com
BUG=none
TESTED=libyuvTest.ARGBBlend_Opt

Review URL: https://webrtc-codereview.appspot.com/50289005.
 2015-06-24 11:34:12 -07:00
Frank Barchard
553c7f85f1 mirror odd width with simd 
R=harryjin@google.com
BUG=libyuv:448

Review URL: https://webrtc-codereview.appspot.com/54769004.
 2015-06-23 17:53:02 -07:00
Frank Barchard
6a9ef1ea36 any 1 to 2 with stride use SIMD 
R=harryjin@google.com
BUG=libyuv:448

Review URL: https://webrtc-codereview.appspot.com/54759004.
 2015-06-23 17:08:08 -07:00
Frank Barchard
6dde4f14bd argb to uv read 4 not 8 
R=harryjin@google.com
BUG=libyuv:457

Review URL: https://webrtc-codereview.appspot.com/52139004.
 2015-06-23 14:48:37 -07:00
Frank Barchard
54100b91c1 copy 2 rows for interpolate and use SIMD. 
R=harryjin@google.com
BUG=libyuv:448

Review URL: https://webrtc-codereview.appspot.com/50279004.
 2015-06-23 10:41:46 -07:00
Frank Barchard
3b5d726a4f 1 to 1 any functions with a parameter use memcpy. 
R=harryjin@google.com
BUG=libyuv:448

Review URL: https://webrtc-codereview.appspot.com/57619004.
 2015-06-22 15:08:20 -07:00
Frank Barchard
a0fca88b1d remove fmemcpy and bump version 
R=harryjin@google.com
BUG=libyuv:448

Review URL: https://webrtc-codereview.appspot.com/50269004.
 2015-06-19 17:58:17 -07:00
Frank Barchard
cae07fb0e0 bump subsampling up 
BUG=455
TESTED=libyuvTest.ARGBToYUY2_Random
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/58419004.
 2015-06-12 15:25:03 -07:00
Frank Barchard
03da5420bc use SIMD for I420ToARGB odd widths in a temporary buffer instead of using C for remainder. 
Enter a description of the change.

use SIMD for I420ToARGB odd widths in a temporary buffer instead of using C for remainder.  Currently the C code does not exactly match the SIMD code, so an odd width produces different pixels than an even width, causing a subtle artifact.  By using SIMD consistently, there is no difference in even and odd widths.  Also the SIMD performance is faster, so even with overhead of memcpy, performance improves.

BUG=447
TESTED=out\release\libyuv_unittest.exe --gtest_filter=*I420ToARGB*
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/55579004.
 2015-06-11 16:38:52 -07:00
fbarchard@google.com
05416e2d9a Box filter for YUV use rows with accumulation buffer for better memory behavior. The old code would do columns accumulated into registers, and then store the result once. This was slow from a memory point of view. The new code does a row of source at a time, updating an accumulation buffer every row. The accumulation buffer is small, and should fit cache. Before each accumulation of N rows, the buffer needs to be reset to zero. If the memset is a bottleneck, it would be faster to do the first row without an add, storing to the accumulation buffer, and then add for the remaining rows. 
BUG=425
TESTED=out\release\libyuv_unittest --gtest_filter=*ScaleTo1x1*
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/52659004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1428 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-06-09 01:05:18 +00:00
fbarchard@google.com
b07de879b6 enable intrinsics for clangcl if -mssse3 is enabled. 
BUG=451
TESTED=untested
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/52699004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1427 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-06-08 22:48:18 +00:00
fbarchard@google.com
b3d3db1b33 align clangcl using declspec instead of gcc style vector 
BUG=451
TESTED=clang=1 build on windows
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/57549004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1425 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-06-08 21:37:37 +00:00
fbarchard@google.com
d3d8e0d933 make source for planar tests contiguous to test planar functions coalesce into a single low level call. 
BUG=431
TESTED=SetPlane unittest
R=bcornell@google.com

Review URL: https://webrtc-codereview.appspot.com/51999004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1419 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-06-01 23:28:59 +00:00
fbarchard@google.com
e787144c2d adjust dimensions for scale factor tests to ensure the scale factor tested is actually used. 
BUG=none
TESTED=set LIBYUV_WIDTH=1918 libyuvTest.ScaleDownBy3by4_None
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/47349004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1416 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-30 00:45:08 +00:00
fbarchard@google.com
bd2d903e1b odd width support for ARGBSobel functions. Improves performance for images that are not a multiple of 8 pixels. 
BUG=444
TESTED=libyuvTest.ARGBSobel_Opt
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/54589004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1415 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-28 22:22:28 +00:00
fbarchard@google.com
cfce47efc8 Change Sobel to use JPeg Luma calculation instead of extracting G channel. Using luma produces a better sobel that respects all 3 channels of RGB. Historically the G channel was used to improve performance, and because the luma of I420 is a constrained range, hurting quality. Using the JPeg variation of YUV, the luma is more accurate, including cross platform, better optimized for AVX2 and odd widths, and full range. 
BUG=444
TESTED=ARGBSobelXY_Opt
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/57479004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1414 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-27 22:32:26 +00:00
fbarchard@google.com
535a7140f2 Scale Down by factor tests scale down to specified ratio rather than up. This ensures the alignment constrains on the destination dont cause a different factor to be used. 
BUG=431
TESTED=libyuvTest.ScaleDownBy3_Bilinear
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/47309004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1413 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-26 23:22:01 +00:00
fbarchard@google.com
7c09264ffc odd width support for scale by even scale factor and box scale down by 4. scale down by 4 uses scale down by 2 internally. 
BUG=431
TESTED=libyuvTest.ARGBScaleDownBy4_Bilinear

Review URL: https://webrtc-codereview.appspot.com/57399004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1412 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-26 17:56:51 +00:00
fbarchard@google.com
c38aeec322 scale down by 2 on argb images support odd widths using _any function. 
BUG=431
TESTED=libyuvTest.ARGBScaleDownBy2_Bilinear

Review URL: https://webrtc-codereview.appspot.com/52569004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1410 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-22 21:39:21 +00:00
fbarchard@google.com
3666015261 add nacl macros for arm to YUV422TORGB_SETUP_REG. 
BUG=415
TESTED=ncval.exe newlib/Release/nacltest_arm.nexe
R=bcornell@google.com

Review URL: https://webrtc-codereview.appspot.com/46229005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1406 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-12 21:33:32 +00:00
fbarchard@google.com
7be3bc65a1 enable speed optimization for libyuv 
BUG=439
TESTED=out\release\libyuv_unittest --gtest_filter=*I420ToARGB_Opt
R=bcornell@google.com

Review URL: https://webrtc-codereview.appspot.com/55389004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1405 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-11 21:58:42 +00:00
fbarchard@google.com
b33dc47b54 sobel use LL for constants to be passed in as int64 
BUG=437
TESTED=local ios build

Review URL: https://webrtc-codereview.appspot.com/47129004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1404 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-06 02:34:16 +00:00
fbarchard@google.com
b0f8352245 row_neon64 additional fixes for warning on ios where int doesnt match %2 size which is 64 bit by default. change size to explicitely 32 bit with %w2. 
BUG=437
TESTED=try bots

Review URL: https://webrtc-codereview.appspot.com/43349004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1401 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-05-05 17:26:57 +00:00
fbarchard@google.com
ab6b224675 fix for arm builds where tmp for assembly produces an error if its uninitialized. 
BUG=libyuv:432
TESTED=try bots
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/49249004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1392 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-30 18:21:19 +00:00
fbarchard@google.com
9f4636e298 AVX2 port of ScaleDownBy4. 
BUG=314
TESTED=out\release\libyuv_unittest --gtest_filter=*.ScaleDownBy4*

Review URL: https://webrtc-codereview.appspot.com/46159004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1390 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-30 01:58:32 +00:00
fbarchard@google.com
f995021f35 Work around casting warnings in scale_neon64.cc for ios 64 bit. 
BUG=430
TESTED=untested
R=bcornell@google.com

Review URL: https://webrtc-codereview.appspot.com/49799004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1382 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-28 00:02:46 +00:00
fbarchard@google.com
4e78b8dc2e scale to 3/4 or 3/8 with odd width destinations efficiently. previously if width was not multiple of what the simd loop would do (24), scaling would fall back on slower C code. This change allows SIMD to be used for most of the scaling and C for the remainder, improving efficiency. 
BUG=314
TESTED=set LIBYUV_WIDTH=1896 & ScaleDownBy3by4_*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/48249004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1380 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-27 21:56:08 +00:00
fbarchard@google.com
c8a2c236a0 NaCl/GYP: remove references to prep_toolchain from libyuv. prep_toolchain is now a no-op. 
BUG=none
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/49769004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1378 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-22 17:42:21 +00:00
fbarchard@google.com
2b7f6b7dee ScaleAddRows_Any_SSE2 functions for handling odd widths. 
BUG=425
TESTED=out\release\libyuv_unittest_old --gtest_filter=*.ScaleDownBy3_*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/45219004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1377 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-22 00:51:56 +00:00
fbarchard@google.com
01db3d1d1d Remove declspec(align(32)) from AVX2 functions. 
BUG=422
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/43229004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1374 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-20 22:57:04 +00:00
fbarchard@google.com
812f59ed40 box and point sampling use scaledownby4 but linear and bilinear do not. 
BUG=427
TESTED=out\release\libyuv_unittest --gtest_filter=*.ScaleDownBy4_*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/51689004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1373 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-17 18:04:09 +00:00
fbarchard@google.com
8eb887f56f add empty header for backwards compatibility. 
BUG=none
TESTED=lint passes

Review URL: https://webrtc-codereview.appspot.com/46919004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1371 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-15 23:09:09 +00:00
fbarchard@google.com
c9986313ac lsl by 2 requires a number sign for xcode on ios 64 bit build. add the # sign for ios compatibility. remove legacy x86 asm files that are unused. the unused files cause complications in build systems that build all files. 
BUG=libyuv:423
TESTED=try bots
R=noahric@google.com

Review URL: https://webrtc-codereview.appspot.com/45119004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1369 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-14 19:57:33 +00:00
fbarchard@google.com
32ad6e0e12 Remove unused variable 'I422ToRGB565Row' that breaks osx builds. 
BUG=426
TESTED=untested

Review URL: https://webrtc-codereview.appspot.com/48079004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1368 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-14 02:50:35 +00:00
fbarchard@google.com
013e812275 Port box filter to AVX2. 
BUG=libyuv:425
TESTED=c:\intelsde\sde -ast -hsw -- out\release\libyuv_unittest.exe --gtest_catch_exceptions=0 --gtest_filter=*libyuvTest.ScaleTo640x360_Box
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/43149004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1367 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-14 00:21:15 +00:00
fbarchard@google.com
b5ea79d845 add rows handle height of 1 using a more general while-style loop. 
BUG=none
TESTED=try bots

Review URL: https://webrtc-codereview.appspot.com/45999004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1366 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-13 18:56:08 +00:00
fbarchard@google.com
c7161d1c36 Remove code alignment declspec from Visual C versions for vs2014 compatibility. 
BUG=422
TESTED=local vs2013 build still passes.

Review URL: https://webrtc-codereview.appspot.com/45959004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1365 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-12 23:54:26 +00:00
fbarchard@google.com
1eb51bcf01 Fix bug in YUV to RGB for gcc/clang and enable affected functions. 
BUG=393
TESTED=sde -ast -hsw -- out\release\libyuv_unittest.exe --gtest_catch_exceptions=0 --gtest_filter=*I422ToARGB*

Review URL: https://webrtc-codereview.appspot.com/48019004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1364 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-08 02:32:33 +00:00
fbarchard@google.com
bb5a009d11 ARGB4444ToARGB and ARGB1555ToARGB ported to AVX2. 
BUG=421
TESTED=out\release\libyuv_unittest --gtest_filter=*ARGB4444ToARGB*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/48009004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1363 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-07 23:52:57 +00:00
fbarchard@google.com
8b9f908134 RGB565ToARGB AVX2 vzeroupper before the ret, not after. 
BUG=421
TESTED=out\release\libyuv_unittest --gtest_filter=*RGB565ToARGB*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/51549004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1362 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-07 22:53:12 +00:00
yang.zhang@arm.com
5f609856de Add ScaleARGBFilterCols_NEON for ARM32/64 
ARM32/64 NEON versions of ScaleARGBFilterCols_NEON are implemented.

BUG=319
TESTED=libyuvTest.* on ARM32/64 with Android
R=fbarchard@google.com

Change-Id: Ifea62bc25d846bf16cb51d13b408de7bf58dccd4

Review URL: https://webrtc-codereview.appspot.com/46699004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1361 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-07 03:45:29 +00:00
fbarchard@google.com
2827277496 port RGB565ToARGB to AVX2. 
BUG=421
TESTED=out\release\libyuv_unittest --gtest_filter=*RGB565ToARGB*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/49609004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1357 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-06 19:24:23 +00:00
fbarchard@google.com
e2ea106068 shift for arm wants a # sign for nacl and ios. 
BUG=420
TESTED=d:/src/nacl_sdk/pepper_canary/toolchain/win_arm_newlib/bin/arm-nacl-g++ -o newlib/Release/source/scale_neon_arm.o -c source/scale_neon.cc -g -O2 -pthread -MMD -DNDEBUG  -Id:/src/nacl_sdk/pepper_canary/include -Id:/src/nacl_sdk/pepper_canary/include/newlib  -I./include
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/47949004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1356 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-03 23:28:44 +00:00
fbarchard@google.com
44b6ba91e4 Scale down by 4 for odd number of destination pixels using 'any' that handles SIMD for multiple of 8 pixels, and C for the remainder. 
BUG=314
TESTED=local test with width odd

Review URL: https://webrtc-codereview.appspot.com/49599004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1355 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-03 22:12:53 +00:00
fbarchard@google.com
62a9fe303c code style cleanup of scale functions. no functional change. 
BUG=none
TESTED=lint
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/48839004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1354 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-04-02 21:23:52 +00:00
fbarchard@google.com
c70c7c02ff scale to half size optimization for avx2 - use pmaddubsw instruction to horizontally add bytes, then pavgw to round and divide by 2. 
BUG=314
TESTED=libyuvTest.ScaleDownBy2*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/45909004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1352 16f28f9a-4ce2-e073-06de-1de4eb20be90
 2015-03-31 23:59:27 +00:00