Allow users to set LIBYUV_DISABLE_${FEATURE} environment variables to
disable individual architecture extensions.
Change-Id: I555dd64311789bd6d760e48045ac6734177a730b
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5712929
Reviewed-by: Justin Green <greenjustin@google.com>
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
sde -spr -- libyuv_test -- --gunit_filter=*Cpu*
Note: Google Test filter = *Cpu*
[==========] Running 4 tests from 2 test suites.
[----------] Global test environment set-up.
[----------] 3 tests from LibYUVBaseTest
[ RUN ] LibYUVBaseTest.TestCpuHas
Cpu Flags 0x57fff9
Has X86 0x8
Has SSE2 0x10
Has SSSE3 0x20
Has SSE41 0x40
Has SSE42 0x80
Has AVX 0x100
Has AVX2 0x200
Has ERMS 0x400
Has FMA3 0x800
Has F16C 0x1000
Has AVX512BW 0x2000
Has AVX512VL 0x4000
Has AVX512VNNI 0x8000
Has AVX512VBMI 0x10000
Has AVX512VBMI2 0x20000
Has AVX512VBITALG 0x40000
Has AVX10 0x0
HAS AVXVNNI 0x100000
Has AVXVNNIINT8 0x0
Has AMXINT8 0x400000
[ OK ] LibYUVBaseTest.TestCpuHas (34 ms)
Bug: b/324356616
Change-Id: I5129b8946363a501bdd570e6dba3936c54aacd6c
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/5283433
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
- Add kCpuHasAVXVNNI flag
- Remove deprecated GFNI detect to make space.
Meteor Lake has AVX-VNNI but not AVX512
~/intelsde/sde -mtl -- blaze-bin/third_party/libyuv/libyuv_test --gunit_filter=*CpuHas
doyuv3
Note: Google Test filter = *CpuHas
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from LibYUVBaseTest
[ RUN ] LibYUVBaseTest.TestCpuHas
Cpu Flags 0x203ff1
Has X86 0x10
Has SSE2 0x20
Has SSSE3 0x40
Has SSE41 0x80
Has SSE42 0x100
Has AVX 0x200
Has AVX2 0x400
Has ERMS 0x800
Has FMA3 0x1000
Has F16C 0x2000
Has AVX512BW 0x0
Has AVX512VL 0x0
Has AVX512VNNI 0x0
Has AVX512VBMI 0x0
Has AVX512VBMI2 0x0
Has AVX512VBITALG 0x0
Has AVX512VPOPCNTDQ 0x0
HAS AVXVNNI 0x200000
Has AVXVNNIINT8 0x0
AVX-VNNI detect
- Add kCpuHasAVXVNNI flag
- Remove deprecated GFNI detect to make space.
https://bugs.chromium.org/p/libyuv/issues/detail?id=967
Meteor Lake has AVX-VNNI but not AVX512
~/intelsde/sde -mtl -- blaze-bin/third_party/libyuv/libyuv_test --gunit_filter=*CpuHas
doyuv3
Note: Google Test filter = *CpuHas
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from LibYUVBaseTest
[ RUN ] LibYUVBaseTest.TestCpuHas
Cpu Flags 0x203ff1
Has X86 0x10
Has SSE2 0x20
Has SSSE3 0x40
Has SSE41 0x80
Has SSE42 0x100
Has AVX 0x200
Has AVX2 0x400
Has ERMS 0x800
Has FMA3 0x1000
Has F16C 0x2000
Has AVX512BW 0x0
Has AVX512VL 0x0
Has AVX512VNNI 0x0
Has AVX512VBMI 0x0
Has AVX512VBMI2 0x0
Has AVX512VBITALG 0x0
Has AVX512VPOPCNTDQ 0x0
HAS AVXVNNI 0x200000
Has AVXVNNIINT8 0x0
Running on all cpus the following report avx-vnni
grep 'AVXVNNI 0x2' */*
adl/libyuv64.txt:HAS AVXVNNI 0x200000
gnr/libyuv64.txt:HAS AVXVNNI 0x200000
grr/libyuv64.txt:HAS AVXVNNI 0x200000
mtl/libyuv64.txt:HAS AVXVNNI 0x200000
rpl/libyuv64.txt:HAS AVXVNNI 0x200000
spr/libyuv64.txt:HAS AVXVNNI 0x200000
srf/libyuv64.txt:HAS AVXVNNI 0x200000
while these support avx512 vnni
grep 'VNNI 0x1' */*
clx/libyuv64.txt:Has AVX512VNNI 0x10000
cpx/libyuv64.txt:Has AVX512VNNI 0x10000
gnr/libyuv64.txt:Has AVX512VNNI 0x10000
icl/libyuv64.txt:Has AVX512VNNI 0x10000
icx/libyuv64.txt:Has AVX512VNNI 0x10000
spr/libyuv64.txt:Has AVX512VNNI 0x10000
tgl/libyuv64.txt:Has AVX512VNNI 0x10000
and these support avx-vnni-int8
grep AVXVNNIINT8.0x4 */*
grr/libyuv64.txt:Has AVXVNNIINT8 0x400000
srf/libyuv64.txt:Has AVXVNNIINT8 0x400000
Bug: libyuv:967
Change-Id: I84cd71d1b320e7c284173eb695fc1d3b72d14ddb
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4912017
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
Reviewed-by: richard winterton <rrwinterton@gmail.com>
- Add kCpuHasAVXVNNIINT8 flag
- Move mips flags up a bit to make space.
~/intelsde/sde -srf -- blaze-bin/third_party/libyuv/libyuv_test --gunit_filter=*CpuHas
Note: Google Test filter = *CpuHas
[==========] Running 1 test from 1 test suite.
[----------] Global test environment set-up.
[----------] 1 test from LibYUVBaseTest
[ RUN ] LibYUVBaseTest.TestCpuHas
Cpu Flags 0x403ff1
Has X86 0x10
Has SSE2 0x20
Has SSSE3 0x40
Has SSE41 0x80
Has SSE42 0x100
Has AVX 0x200
Has AVX2 0x400
Has ERMS 0x800
Has FMA3 0x1000
Has F16C 0x2000
Has AVX512BW 0x0
Has AVX512VL 0x0
Has AVX512VNNI 0x0
Has AVX512VBMI 0x0
Has AVX512VBMI2 0x0
Has AVX512VBITALG 0x0
Has AVX512VPOPCNTDQ 0x0
Has AVXVNNIINT8 0x400000
Has GFNI 0x0
[ OK ] LibYUVBaseTest.TestCpuHas (32 ms)
INT8 supported on srf and grr
-srf Set chip-check and CPUID for Intel(R) Sierra Forest CPU
-grr Set chip-check and CPUID for Intel(R) Grand Ridge CPU
Bug: b/303434603
Change-Id: I628007929ff0518b2b36e1469b4d9aed71a9fa8f
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/4912015
Reviewed-by: richard winterton <rrwinterton@gmail.com>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
1. Add supports for LSX and LASX.
2. Three optimization functions are added in loongarch/row_lasx.cc file:
I422ToARGBRow_LASX,I422ToRGBARow_LASX,I422AlphaToARGBRow_LASX.
Bug: libyuv:912, Bug: libyuv:913
Change-Id: I043c2704f99a5215724b5c0b7f97e6bf5f7a199b
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/3329189
Reviewed-by: Frank Barchard <fbarchard@chromium.org>
Commit-Queue: Frank Barchard <fbarchard@chromium.org>
Rename yuvconstants to .c and use round from math.h
Bug: libyuv:882, b/180472591
Change-Id: I70720bf3e0833ba00df0d721f12020fba0b07a03
Reviewed-on: https://chromium-review.googlesource.com/c/libyuv/libyuv/+/2706966
Reviewed-by: Mirko Bonadei <mbonadei@chromium.org>
Move getenv to unittest.cc to allow libyuv to be
run in sandbox for x86, x64 and aarch64
Bug: libyuv:767
Test: unittests still run and respect environment variables
Change-Id: I84cb1717977828776142b51c029774b3e6b142a3
Reviewed-on: https://chromium-review.googlesource.com/969645
Reviewed-by: richard winterton <rrwinterton@gmail.com>
When command line --libyuv_cpu_info is used the individual tests
used to need to set the cpumask. This CL moves that to the init
for each test class so the individual tests dont need to set it.
TBR=kjellander@chromium.org
BUG=libyuv:720
TEST=LibYUVBaseTest.TestCpuHas
Change-Id: I6ae180388debf6cf76be6df5b81cfffeb35ee2eb
Reviewed-on: https://chromium-review.googlesource.com/662367
Reviewed-by: Cheng Wang <wangcheng@google.com>
cpu_info_ is zero for uninitialized state and all bits are off, disabling all cpu optimizations.
the 1 bit indicates cpu_info_ is initialized avoiding calling the detection code again for performance.
MaskCpuFlags initializes the cpu ignoring existing flags, then masks with the supplied flags and stores to cpu_info_.
As a mask, -1 has no effect, enabling all cpu features that were detected, but nothing that wasnt detected.
Setting to 0 will cause the next call to re-initialize the cpu, which is same as enabling all features.
Setting mask to 1 will turn off all cpu features but keep the initialized bit on, so the next detection call wont reinitialize and the cpu features are all disabled.
So normal behavior for command line and programatic masking is:
1 = C
-1 = SIMD
TBR=harryjin@google.com
BUG=libyuv:600
TESTED=out64/Release/bin/run_libyuv_unittest -s libyuv_unittest --verbose --release --gtest_filter=*ARGBExtractAlpha* -a "--libyuv_width=1280 --libyuv_height=720 --libyuv_repeat=9999 --libyuv_flags=1 --libyuv_cpu_info=1"
Review URL: https://codereview.chromium.org/2042933002 .
blur requires memory be aligned. change the unittest allocator to guarantee 64 byte alignment.
re-enable blur any test that fails if memory is unaligned.
TBR=harryjin@google.com
BUG=libyuv:596,libyuv:594
TESTED=local build passes with row.h removed from tests.
Review URL: https://codereview.chromium.org/2019753002 .
internal math of the fastrand function uses a multiply
and add that overflows a signed int. This triggers a
ubsan failure:
../../unit_test/../unit_test/unit_test.h:60:33: runtime error: signed integer overflow: 56248274 * 214013 cannot be represented in type 'int'
This change casts the intermediate math to unsigned
int to avoid the overflow.
For more info on ubsan, see
http://dev.chromium.org/developers/testing/undefinedbehaviorsanitizer
TESTED=Passing compilation using:
GYP_DEFINES="ubsan=1"
GYP_DEFINES="ubsan_vptr=1"
R=harryjin@google.com, pbos@webrtc.org
BUG=libyuv:563
Review URL: https://codereview.chromium.org/1662453003 .
cpu flags of 1 disables SIMD and uses C. This used to be 0, but the change
in auto init behavior means that 0 now means uninitialized, and will cause
auto detect to reinit the cpu info. A value of 1 disables the auto init.
TBR=harryjin@google.com
BUG=none
Review URL: https://codereview.chromium.org/1408753004 .
in order to compare C and Neon code, a new command line flag is added.
historically environment variables controlled cpu features, but on
android apk it is easier to pass a command line option to disable cpu
optimizations.
R=harryjin@google.com
BUG=libyuv:516
Review URL: https://codereview.chromium.org/1407193009 .
Allows us to ignore flags passed on to us by Chromium build bots
without having to explicitly disable them. (Thanks pbos!)
TESTED=webrtc ran modules_unittests with a bogus flag did not result in an
error.
R=kjellander@chromium.org
BUG=libyuv:507
Review URL: https://codereview.chromium.org/1417573002 .
A hang in color conversion on arm occurs somewhere in yuv to rgb.
Breaking the color test into its own category of test will help
run selective tests to narrow down the issue.
R=harryjin@google.com
BUG=libyuv:506
Review URL: https://codereview.chromium.org/1405543003 .
random / rand is slow and impacts performance testing.
Although its only called to clear a frame once, a typical profile shows
it high in the overall profile, when doing 1000 frames for a benchmark.
95.10% libyuv_unittest libyuv_unittest [.] YUY2ToARGBRow_SSSE3
2.01% libyuv_unittest libc-2.19.so [.] __random_r
1.13% libyuv_unittest libc-2.19.so [.] __random
Replace random is a faster version for unittests.
set LIBYUV_WIDTH=1280
set LIBYUV_HEIGHT=720
set LIBYUV_REPEAT=999
set LIBYUV_FLAGS=-1
out\release\libyuv_unittest --gtest_filter=*YUY2ToARGB* | findms
Was
libyuvTest.YUY2ToARGB_Opt (497 ms)
Now
libyuvTest.YUY2ToARGB_Opt (454 ms)
R=harryjin@google.com
BUG=none
Review URL: https://codereview.chromium.org/1361813002 .
