53 Commits

Author SHA1 Message Date
Frank Barchard
e62309f259 clang-format libyuv
BUG=libyuv:654
R=kjellander@chromium.org

Review URL: https://codereview.chromium.org/2469353005 .
2016-11-07 17:37:23 -08:00
Frank Barchard
cda9d38a4e xmmword cast for clang
clangcl use compare_win for 32 bit, allowing fallback and enabling avx2 code for clang.
move defines/protos to compare_row.h
fix issue with odd width ARGBCopyAlpha functions by copying destination to temp buffer, then doing alpha copy, then copy back to destination.

R=harryjin@google.com
TBR=harryjin@google.com
BUG=libyuv:484

Review URL: https://webrtc-codereview.appspot.com/59379004.
2015-08-18 11:13:12 -07:00
Frank Barchard
baf6a3c1bd Using the visual C source allows clangcl to fallback seamlessly to visual c, and supports SSE41 and AVX2 versions.
R=harryjin@google.com
BUG=libyuv:469

Review URL: https://webrtc-codereview.appspot.com/58469004.
2015-08-17 10:47:43 -07:00
fbarchard@google.com
d28cd77f99 Enable assembly for clangcl build on Windows. Previously assembly was disabled so clangcl would work, but only with C code. As clangcl mimics both Visual C and GCC, ifdefs need to pick one or the other or often you'll end up with both. In this CL we disable most Visual C code and use the GCC versions which allow assembly for both 32 and 64 bit intel.
BUG=412
TESTED=clang=1 build on windows
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/51389004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1341 16f28f9a-4ce2-e073-06de-1de4eb20be90
2015-03-19 20:36:31 +00:00
fbarchard@google.com
a6025e8b6b ARGBDetect do 2 pixels at a time for improved performance.
BUG=375
TESTED=libyuvTest.BenchmarkARGBDetect_Opt
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/26049004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1155 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-05 23:23:17 +00:00
fbarchard@google.com
b661b3ee0d Detect Endian of ARGB image.
BUG=375
TESTED=libyuv builds, but no test app for it yet
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/32389004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1154 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-05 18:46:06 +00:00
fbarchard@google.com
9c4c82181b Remove alignment constraint for SSE2. Allows the optimized function to be used with unaligned memory, improving performance in that use case. Hurts performance on core2 and prior where memory was faster with movdqa instruction.
BUG=365
TESTED=psnr, ssim and djb2 unittests pass.
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/22859004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1100 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-09-30 18:53:34 +00:00
yang.zhang@arm.com
26f43db1ef AArch64:add SumSquareError_NEON armv8 assembly version
BUG=none
TESTED=libyuv_unittest
R=fbarchard@google.com

Review URL: https://webrtc-codereview.appspot.com/16259004/

the benckmarking result is as follows:
toolchain: gcc 4.9
hardware: A53

| count | C Times/NEON times |
| 16    | 3.35               |
| 128   | 6.63               |
| 512   | 7.47               |
| 1024  | 7.72               |

Change-Id: Ic10bf22d77d069a1a2074b68bd5a310c579ec490

Review URL: https://webrtc-codereview.appspot.com/21159004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1043 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-08-13 06:10:02 +00:00
fbarchard@google.com
9c6e52791f Port compare to C89 / Visual C.
BUG=303
TESTED=cl /c /TC /Iinclude source/compare.cc
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/7019006

git-svn-id: http://libyuv.googlecode.com/svn/trunk@966 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-01-13 18:57:30 +00:00
fbarchard@google.com
da443d7adc Remainder calc needs to be after blocks are done. Move calc to old location.
BUG=303
TESTED=Djb2 unittests
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/6849004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@960 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-01-09 20:29:27 +00:00
fbarchard@google.com
167d5d1c2f Porting parts of compare to c89
BUG=303
TESTED=try bots still build, gcc and vc direct for c testing.
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/6739004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@956 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-01-08 00:59:40 +00:00
fbarchard@google.com
a1f5254a95 Switch to c style casts for all source and includes.
BUG=303
TESTED=try
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/6629004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@952 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-01-07 03:03:00 +00:00
fbarchard@google.com
88c0b01cdd Use 64 bit Sum for planar function to remove size limitation
BUG=302
TESTED=out\release\libyuv_unittest --gtest_filter=*Psnr
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/6499004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@941 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-01-02 22:57:06 +00:00
fbarchard@google.com
095f33d870 Coalesce rows by changing width/height and dropping into code instead of recursing. Improve coalesce by setting stride to 0 so it can be used even on odd width images. Reduce unittests to improve time to run emulators.
BUG=277
TEST=unittests all build and pass
R=ryanpetrie@google.com

Review URL: https://webrtc-codereview.appspot.com/2589004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@819 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-10-21 19:29:10 +00:00
fbarchard@google.com
07c3fe2f61 Fix DrMemory errors in unittests that were not initializing memory.
BUG=263
TEST=set GYP_DEFINES=build_for_tool=drmemory target_arch=ia32 & drmemory out\debug\libyuv_unittest.exe --gtest_catch_exceptions=0 --gtest_filter=*
R=kjellander@webrtc.org

Review URL: https://webrtc-codereview.appspot.com/2270007

git-svn-id: http://libyuv.googlecode.com/svn/trunk@798 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-09-24 07:39:10 +00:00
fbarchard@google.com
823548cb3b AVX2 hash using vex128 as first step.
BUG=none
TEST=BenchmarkDjb2_Opt
R=ryanpetrie@google.com

Review URL: https://webrtc-codereview.appspot.com/2219004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@792 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-09-17 20:34:28 +00:00
fbarchard@google.com
0d41aee26b Port compare functions to Nacl
BUG=253
TEST=none
R=nfullagar@google.com

Review URL: https://webrtc-codereview.appspot.com/1998004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@752 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-08-08 23:52:34 +00:00
fbarchard@google.com
abfeea9b81 Math functions - add, substract, multiply and shade adapted to nacl friendly addressing.
BUG=253
TEST=out\release\libyuv_unittest --gtest_filter=*Add*
R=dingkai@google.com, nfullagar@chromium.org

Review URL: https://webrtc-codereview.appspot.com/1972004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@746 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-08-06 20:47:18 +00:00
fbarchard@google.com
9b4c00b908 Move vzeroupper to row functions to simplify caller and allow mix of avx2 and sse2. Impact reduced by row coalescing.
BUG=none
TEST=all tests pass with sde
Review URL: https://webrtc-codereview.appspot.com/1269009

git-svn-id: http://libyuv.googlecode.com/svn/trunk@641 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-04-04 05:54:59 +00:00
fbarchard@google.com
83a63e65a6 Change YUV_DISABLE_ASM to LIBYUV_DISABLE_NEON, LIBYUV_DISABLE_MIPS, LIBYUV_DISABLE_X86
BUG=189
TESTED=try
Review URL: https://webrtc-codereview.appspot.com/1113006

git-svn-id: http://libyuv.googlecode.com/svn/trunk@582 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-02-27 00:20:29 +00:00
fbarchard@google.com
3c7bb050bd Unattenuate AVX2
BUG=190
TEST=planar_test
Review URL: https://webrtc-codereview.appspot.com/1112004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@577 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-02-20 22:18:36 +00:00
fbarchard@google.com
408e574366 Use vmovd to avoid switch to sse mode
BUG=none
TEST=c:\intelsde\sde -hsw -- out\release\libyuv_unittest.exe --gtest_filter=*Psnr*
Review URL: https://webrtc-codereview.appspot.com/1097013

git-svn-id: http://libyuv.googlecode.com/svn/trunk@573 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-02-14 19:03:30 +00:00
fbarchard@google.com
f3ad618d40 Sum of Square Error ported to AVX2
BUG=187
TEST=compare_unittest
Review URL: https://webrtc-codereview.appspot.com/1099009

git-svn-id: http://libyuv.googlecode.com/svn/trunk@572 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-02-13 18:38:03 +00:00
fbarchard@google.com
cde587092f Replace two spaces with one after .
BUG=none
TEST=lint
Review URL: https://webrtc-codereview.appspot.com/1063010

git-svn-id: http://libyuv.googlecode.com/svn/trunk@553 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-01-28 00:02:35 +00:00
fbarchard@google.com
66fe097a2b Move compare modules into their own files, and scale for mips
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/920005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@434 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-10-22 16:18:53 +00:00
fbarchard@google.com
3f467451cf Move compare low levels into their own files, for consistency with NEON.
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/921004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@429 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-10-20 01:23:27 +00:00
fbarchard@google.com
64ce0ab544 Move Neon source to its own files.
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/860009

git-svn-id: http://libyuv.googlecode.com/svn/trunk@396 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-10-09 00:05:29 +00:00
fbarchard@google.com
fc7314e86b Add exports to allow libyuv to be built as a shared lib.
BUG=99
TEST=shared lib builds without impact and unittests link against import lib.
Review URL: https://webrtc-codereview.appspot.com/844005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@379 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-09-27 02:17:51 +00:00
fbarchard@google.com
142f6c4ed5 Move row.h to include and remove rotate_priv.h
BUG=93
TESTED=try server
Review URL: https://webrtc-codereview.appspot.com/811004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@360 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-09-18 20:56:51 +00:00
fbarchard@google.com
b0c9797589 Update Copyright notice to follow new chromium conventions.
BUG=63
TEST=none
Review URL: https://webrtc-codereview.appspot.com/730004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@314 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-08-08 19:04:24 +00:00
fbarchard@google.com
5bf29b59db p2align all loops, copy stride to local for scale, and copy last byte in bilinear more efficiently
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/547007

git-svn-id: http://libyuv.googlecode.com/svn/trunk@255 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-05-02 00:10:16 +00:00
fbarchard@google.com
5ff3a8fec5 ARGBBlendRow1_SSSE3 added to allow SSSE3 only alpha blending. Saves on SSE2 cpu dispatching
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/518002

git-svn-id: http://libyuv.googlecode.com/svn/trunk@251 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-04-24 19:43:45 +00:00
fbarchard@google.com
85ebc8e20b HashDjb2_SSE41 ported to gcc. gcc 4.5 required for pmulld instruction.
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/506002

git-svn-id: http://libyuv.googlecode.com/svn/trunk@248 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-04-23 20:09:35 +00:00
fbarchard@google.com
f86ba32b9d Unattenuate using a reciprocal
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/487006

git-svn-id: http://libyuv.googlecode.com/svn/trunk@241 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-04-18 00:35:55 +00:00
fbarchard@google.com
4d3bd8343b unaligned sse4 djb2 cleanup
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/486001

git-svn-id: http://libyuv.googlecode.com/svn/trunk@238 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-04-06 00:27:09 +00:00
fbarchard@google.com
ddf9051bd9 DJB2 hash with SSE4 pmulld
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/484002

git-svn-id: http://libyuv.googlecode.com/svn/trunk@237 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-04-05 20:44:03 +00:00
fbarchard@google.com
d2f4413d29 Remove old alpha blend, expose GetARGB2Blend, fix ComputeSumSquareErrorPlane on SSE2
BUG=29
TEST=none
Review URL: https://webrtc-codereview.appspot.com/469005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@234 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-04-04 21:53:27 +00:00
fbarchard@google.com
5b22506b14 With an asm() away lint, this cleans up most remaining issues.
BUG=none
TEST=lint filename
Review URL: https://webrtc-codereview.appspot.com/464001

git-svn-id: http://libyuv.googlecode.com/svn/trunk@230 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-03-29 02:19:26 +00:00
fbarchard@google.com
2b9c210803 lint fix test
BUG=none
TEST=gcl lint lintfix2
Review URL: https://webrtc-codereview.appspot.com/458003

git-svn-id: http://libyuv.googlecode.com/svn/trunk@220 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-03-22 22:36:44 +00:00
fbarchard@google.com
67be98bd44 psnr function was using C. unittest fixed and warnings improved
BUG=21,22
TEST=build\release\libyuv_unittest.exe  --gtest_filter=*
Review URL: https://webrtc-codereview.appspot.com/447013

git-svn-id: http://libyuv.googlecode.com/svn/trunk@218 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-03-19 16:49:12 +00:00
fbarchard@google.com
18184fd19d switch looping to jg from ja to allow non-multiple of 16 to underflow to a negative
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/453001

git-svn-id: http://libyuv.googlecode.com/svn/trunk@214 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-03-12 18:53:19 +00:00
fbarchard@google.com
bd4a849bcb fix for nv21 u, v order, align all loops, and make addrows support 1 row
BUG=17
TEST=none
Review URL: https://webrtc-codereview.appspot.com/435004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@208 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-03-07 19:19:03 +00:00
fbarchard@google.com
567244c003 minor fixups
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/388001

git-svn-id: http://libyuv.googlecode.com/svn/trunk@169 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-02-07 23:54:52 +00:00
fbarchard@google.com
79a06ac5fe omp friendly version of psnr
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/378007

git-svn-id: http://libyuv.googlecode.com/svn/trunk@167 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-02-06 22:33:09 +00:00
fbarchard@google.com
3e34b8e89d hash funtion for comparing images
BUG=none
TEST=none
Review URL: https://webrtc-codereview.appspot.com/380006

git-svn-id: http://libyuv.googlecode.com/svn/trunk@166 16f28f9a-4ce2-e073-06de-1de4eb20be90
2012-02-06 22:05:16 +00:00
fbarchard@google.com
fe5ff7ed54 clang on linux prefers no args for rep movsl/stosl. ifdef for C that removes namespace. extern c allows c++ to be used to compile, including with namespace, but C program can link libyuv
BUG=none
TEST=none
Review URL: http://webrtc-codereview.appspot.com/320004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@101 16f28f9a-4ce2-e073-06de-1de4eb20be90
2011-12-10 07:45:58 +00:00
fbarchard@google.com
1c5136d069 use IS_ALIGNED for width and stride to avoid mod that generates 6 instructions
BUG=none
TEST=disassemble to confirm smaller/simplier alignment checks
Review URL: http://webrtc-codereview.appspot.com/287001

git-svn-id: http://libyuv.googlecode.com/svn/trunk@91 16f28f9a-4ce2-e073-06de-1de4eb20be90
2011-11-22 18:15:17 +00:00
fbarchard@google.com
15c3d45cbe Change WIN32 to _M_IX86 and use YUV_DISABLE_ASM consistently
BUG=none
TEST=none
Review URL: http://webrtc-codereview.appspot.com/277008

git-svn-id: http://libyuv.googlecode.com/svn/trunk@84 16f28f9a-4ce2-e073-06de-1de4eb20be90
2011-11-17 22:13:17 +00:00
fbarchard@google.com
4cf70bd6db compare SumSquareError_SSE2 ported to gcc
BUG=none
TEST=media_unittest
Review URL: http://webrtc-codereview.appspot.com/279005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@79 16f28f9a-4ce2-e073-06de-1de4eb20be90
2011-11-15 18:44:31 +00:00
frkoenig@google.com
c82af4a59c Order includes.
Use the following order.
local
system
libyuv
Review URL: http://webrtc-codereview.appspot.com/270007

git-svn-id: http://libyuv.googlecode.com/svn/trunk@76 16f28f9a-4ce2-e073-06de-1de4eb20be90
2011-11-11 00:54:34 +00:00