243 Commits

Author SHA1 Message Date
fbarchard@google.com
b0abc62c21 Fix for UYVYToI422 AVX2 version
BUG=269
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/32329004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1197 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-13 00:15:11 +00:00
fbarchard@google.com
a9734a4492 ARGBMirror for AVX had wrong loop counting. This fixes it to match windows, and reenables the function.
BUG=269
TESTED=try bots
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/33639004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1196 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-12 22:43:55 +00:00
fbarchard@google.com
08daa3e22b Disable AVX2 code that fails on GCC unittests until issues can be resolved.
BUG=269
TESTED=sde-external-7.8.0-2014-10-02-mac/sde -ast -hsw -- out/Release/libyuv_unittest

Review URL: https://webrtc-codereview.appspot.com/29219004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1195 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-12 19:30:15 +00:00
fbarchard@google.com
233a931cb6 Port ARGBToUV to AVX2.
BUG=269
TESTED=ncval
R=brucedawson@google.com, tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/35449004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1194 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-10 22:48:58 +00:00
fbarchard@google.com
e0bb4c26e2 Interpolate Row ported to AVX2 GCC/NaCL.
BUG=269
TESTED=nacl build
R=brucedawson@google.com, tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/25329004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1193 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-09 22:21:53 +00:00
fbarchard@google.com
044938f485 convert ARGB to UV for SSSE3 use single asm block.
BUG=378
TESTED=nacl build
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/28179004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1191 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-06 19:23:12 +00:00
fbarchard@google.com
540e8af80c remove add 16 from ARGBToYJ and add rounding, for consistency with Windows version. row.h header macros sorted alphabetically.
BUG=269
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/32579005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1185 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-02 22:37:47 +00:00
fbarchard@google.com
b036cf700b ARGBToYRow_AVX2 and ARGBToYJRow_AVX2 ported to GCC.
BUG=269
TESTED=try bots
R=brucedawson@google.com, tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/30299004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1184 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-02 22:00:08 +00:00
fbarchard@google.com
d0bfd10147 I422ToRGBARow_AVX2 ported to GCC.
BUG=269
TESTED=nacl build
R=brucedawson@google.com

Review URL: https://webrtc-codereview.appspot.com/32259004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1183 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-02 18:59:33 +00:00
fbarchard@google.com
702e237d5f I422ToABGR_AVX2 port from Visual C to GCC/NaCL.
BUG=269
TESTED=builds with nacl compiler.
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/33449004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1182 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-02 03:54:08 +00:00
fbarchard@google.com
0c472f9d42 gcc port of I422ToARGB_AVX2 from Visual C. Uses Macros for read of I422 and conversion from YUV to RGB. Shares constants from I422ToBGRA structure.
BUG=269
TESTED=nacl builds.
R=brucedawson@google.com, tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/27279004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1181 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-12-02 00:22:56 +00:00
fbarchard@google.com
ef14972df0 MergeUV AVX2 use vextractf128 to store results to avoid shuffling.
BUG=none
TESTED=intel sde on unittests
R=brucedawson@google.com

Review URL: https://webrtc-codereview.appspot.com/33369004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1178 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-22 03:33:33 +00:00
fbarchard@google.com
147f7b70f5 Quick fix for build gcc - remove unused argument kARGBShuffleMirror from ARGBMirror SSE2.
BUG=none
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/30209004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1177 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-22 01:12:19 +00:00
fbarchard@google.com
ef67597b48 ARGBMirror use SSE2 pshufd instruction instead of SSSE3 pshufb.
BUG=269
TESTED=local benchmark for ARGBMirror
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/32509004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1176 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-21 19:25:14 +00:00
fbarchard@google.com
91f240c5db Move sub before branch for loops.
Remove CopyRow_x86
Add CopyRow_Any versions for AVX, SSE2 and Neon.
BUG=269
TESTED=local build
R=harryjin@google.com, tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/26209004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1175 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-20 21:14:27 +00:00
fbarchard@google.com
813bf9f97d Change lea macros from memaccess to memlea to fix nacl 64 bit build errors.
BUG=381
TESTED=local nacl build and validate
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/32129004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1174 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-19 23:02:04 +00:00
fbarchard@google.com
db7a7f61ff Port ARGBMirror AVX2 code to gcc/NaCL.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/24329004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1173 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-19 20:03:37 +00:00
fbarchard@google.com
55db4ec23b port lea removal for mirror to gcc
BUG=none
TESTED=none
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/27209004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1169 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-17 20:06:40 +00:00
fbarchard@google.com
5822505e0a Remove extra unaligned loop from alphablender. Both aligned and unaligned loops were the same, so remove the extra.
BUG=none
TESTED=try bots.
R=brucedawson@google.com, harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/29059004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1166 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-17 18:33:07 +00:00
fbarchard@google.com
35508d0979 Mirror_AVX2 ported to GCC.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/32079004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1164 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-13 23:11:10 +00:00
fbarchard@google.com
91000425a3 ARGBUnattenuate_AVX2 ported to GCC. Minor cleanup of constants to use broadcast to make 16 byte constant instead of 32 byte.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/30999004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1163 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-13 17:57:33 +00:00
fbarchard@google.com
f8c334473b ARGBAttenuate_AVX2 ported to GCC.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/29049004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1162 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-12 18:38:06 +00:00
fbarchard@google.com
a843cafbe4 ARGBMultiply_AVX2 ported to GCC.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/27139005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1160 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-11 20:33:33 +00:00
fbarchard@google.com
0387df5186 ARGBSubtract_AVX2 ported to GCC.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/27129004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1159 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-11 19:12:38 +00:00
fbarchard@google.com
9e9e26d60a ARGBAdd ported AVX2 ported to GCC.
BUG=269
TESTED=try bots
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/32449004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1158 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-11 19:01:29 +00:00
fbarchard@google.com
10d9c0d0a7 MergeUV for AVX2 ported to gcc. Add missing vzeroupper to all avx2 functions.
BUG=none
TESTED=ncval for nacl
R=brucedawson@google.com, harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/25059005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1157 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-10 19:19:12 +00:00
fbarchard@google.com
d1885bcc73 SplitUVRow_AVX2 ported to GCC/NaCL.
BUG=269
TESTED=validator for nacl.
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/28979004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1156 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-06 01:39:26 +00:00
fbarchard@google.com
bb3a4b41e9 vextractf128 requuires a constant argument for which dqword to extract, so add a new macro.
BUG=none
TESTED=local build on clang for osx
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/30869004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1153 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-04 21:05:55 +00:00
fbarchard@google.com
3f87404769 Port YUY2ToUV, YUY2ToUV422, UYVYToUV and UYVYToUV422 to AVX2 on GCC/Nacl.
BUG=269
TESTED=ncval
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/26029004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1152 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-04 18:24:10 +00:00
fbarchard@google.com
067892c5a1 Port YUY2ToYRow_AVX2 and UYVYToYRow_AVX2 to gcc/NaCL from Windows AVX code.
BUG=269
TESTED=ncval
R=brucedawson@google.com, harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/25039004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1151 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-11-03 18:30:17 +00:00
fbarchard@google.com
260e3b2273 now that libyuv requires newer nacl compiler, bundles can be assumed and bundle align macro can be removed. no impact on code gen.
BUG=none
TESTED=validator still passes
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/30019004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1150 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-30 20:02:03 +00:00
fbarchard@google.com
51b78880c5 gcc version of I422ToBGRA_AVX2. Original copied from https://webrtc-codereview.appspot.com/28729004/ and compatible with, but unrelated to windows version.
BUG=269
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/29849004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1131 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-21 02:18:11 +00:00
fbarchard@google.com
4d46be3930 Declare CopyRow_AVX as using xmm usage, not ymm. Should resolve chromium build error for Android Atom.
BUG=libyuv:369
TESTED=untested
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/31609004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1118 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-09 17:54:43 +00:00
fbarchard@google.com
205c1440cf Use movdqu then pavgb to allow unaligned memory for rgb subsampling code. Allows this assembly to be used for unaligned pointers as well as aligned ones with no performance hit when memory is aligned on a modern cpu.
BUG=365
TESTED=libyuvTest.ARGBToI420_Unaligned (453 ms)
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/30679004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1116 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-07 19:47:06 +00:00
fbarchard@google.com
883ce64a34 ifdefs for UV functions to resolve link error on osx
BUG=365
TESTED=mac local build
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/24859004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1115 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-07 17:24:14 +00:00
fbarchard@google.com
008ce53ac4 pavgb with memory op requires alignment. This CL disables conversions that use pavgb, and resolves scale by 3/8 unittest for checking alignment works. The 3/8 code used a pavgb with a memory operand. tests are added for scaling and allow unaligning on purpose.
BUG=365
TESTED=local change to force unaligned memory fails on some conversions and scaling code.
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/29699004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1114 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-07 01:57:34 +00:00
fbarchard@google.com
ca308327d2 Remove unaligned functions, since most function support unaligned memory now. This reduces complexity and improves performance for unaligned cases because C code can be avoided, and overhead is less. Downside is old cpus (core2 and earlier) will be slower for aligned memory case. Except mips, which has alignment requirement, but remove unaligned variant.
BUG=365
TESTED=unittest builds and passes locally
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/24839004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1113 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-07 00:59:31 +00:00
fbarchard@google.com
b720049a54 Make row functions used for planarfunctions and convert use movdqu to relax alignment constraint. Step 1 - make functions unaligned.
BUG=365
TESTED=libyuv_unittest passes
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/26709004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1111 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-03 21:11:37 +00:00
fbarchard@google.com
d83f63a3b4 InterpolateRow used for scale handle unaligned memory. Remove HalfRow which is not used.
BUG=367
TESTED=unittest on I422ToI420
R=harryjin@google.com

Review URL: https://webrtc-codereview.appspot.com/28639004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1107 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-03 17:37:11 +00:00
fbarchard@google.com
455ae94c60 Make rotate SIMD allow unaligned pointers.
BUG=365
TESTED=libyuv_unittest
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/22899004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1102 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-10-02 17:56:48 +00:00
fbarchard@google.com
1fb68cda67 port/fix CopyRow_AVX to gcc
BUG=363
TESTED=osx build
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/28619004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1098 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-09-30 00:39:41 +00:00
fbarchard@google.com
d33bf86b25 CopyRow_AVX which supports unaligned pointers for Sandy Bridge CPU.
BUG=363
TESTED=out\release\libyuv_unittest --gtest_filter=*ARGBToARGB_*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/31489004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@1097 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-09-29 23:53:18 +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
5dba58cb1e FixedDiv1 using a single 64/32 divide. Removes size restriction from slope.
BUG=302
TESTED=libyuv scale tests
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/6489004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@940 16f28f9a-4ce2-e073-06de-1de4eb20be90
2014-01-02 22:32:09 +00:00
fbarchard@google.com
b14f46fa30 NaCL pepper_33 port of scale and compare using lock/unlock. Remove less useful scaling tests and change default size to a multiple of 16 for better assembly coverage.
BUG=none
TESTED=ncval
R=nfullagar@google.com

Review URL: https://webrtc-codereview.appspot.com/5939005

git-svn-id: http://libyuv.googlecode.com/svn/trunk@917 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-12-17 18:27:06 +00:00
nfullagar@google.com
6f0a1dca2c First pass using bundle_lock / bundle_unlock from binutils update.
Remove hand placed BUNDLEALIGN and add new asm directives into
psuedo-instruction macros. Moving forward, this will make for easier and
more consistent psuedo-instruction alignment with bundle boundaries.
This is mostly a NaCl CL but does include a few changes that will slightly
change loop alignments in non-NaCl builds.
BUG=253
TEST=trybots,ncval
R=fbarchard@google.com

Review URL: https://webrtc-codereview.appspot.com/4889004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@913 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-12-13 22:40:53 +00:00
fbarchard@google.com
0287a3cb53 Fix for I422ToARGB which used movq instead of movd
BUG=293
TESTED=LIBYUV_DISABLE_ASM=1 valgrind out/Debug/remoting_unittests --single-process-tests --gtest_filter=*YuvToRgb*
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/5669004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@911 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-12-12 01:59:45 +00:00
fbarchard@google.com
545a51c1d3 use scale for subsampling to handle odd source width to even destination width.
BUG=289
TEST=drmemory
R=nfullagar@google.com, ryanpetrie@google.com

Review URL: https://webrtc-codereview.appspot.com/4779004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@884 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-12-03 00:27:29 +00:00
fbarchard@google.com
0014ce0056 test odd width and fix for unaligned used on odd width conversion.
BUG=283
TESTED=try bots
R=tpsiaki@google.com

Review URL: https://webrtc-codereview.appspot.com/4729004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@883 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-12-02 20:07:29 +00:00
fbarchard@google.com
c2295807bd Reduce alignment for loops from 16 bytes to 4 bytes. Reduces outer loop overhead without hurting innerloop time.
BUG=none
TESTED=try bots
R=fbarchard@chromium.org, mflodman@webrtc.org

Review URL: https://webrtc-codereview.appspot.com/4659004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@880 16f28f9a-4ce2-e073-06de-1de4eb20be90
2013-12-02 15:57:39 +00:00