Closed GoogleCodeExporter closed 8 years ago
Original comment by fbarch...@google.com
on 26 Jan 2016 at 1:49
LIBYUV_FLAGS=-1 LIBYUV_WIDTH=1280 LIBYUV_HEIGHT=720 LIBYUV_REPEAT=1000 perf
record out/Release/libyuv_unittest --gtest_filter=*NV12To*RGB565*
perf report | grep Row_
55.32% libyuv_unittest libyuv_unittest [.] NV12ToARGBRow_SSSE3
42.03% libyuv_unittest libyuv_unittest [.] ARGBToRGB565Row_SSE2
0.77% libyuv_unittest libyuv_unittest [.] NV12ToRGB565Row_SSSE3
0.14% libyuv_unittest libyuv_unittest [.] NV12ToRGB565Row_Any_SSSE3
0.08% libyuv_unittest libyuv_unittest [.] RGB565ToARGBRow_SSE2
Original comment by fbarch...@google.com
on 10 Feb 2016 at 6:48
Was NV12ToRGB565_Opt (735 ms)
Now NV12ToRGB565_Opt (613 ms)
Original comment by fbarch...@google.com
on 10 Feb 2016 at 7:10
The following revision refers to this bug:
https://chromium.googlesource.com/libyuv/libyuv.git/+/0e554b18fe2a60f2a384d0dc86154b69bb7bc1b7
commit 0e554b18fe2a60f2a384d0dc86154b69bb7bc1b7
Author: Frank Barchard <fbarchard@google.com>
Date: Wed Feb 10 19:13:41 2016
port NV12ToRGB565Row_AVX2 to gcc
NV12ToRGB565Row for Intel is implemented as a 2 step conversion:
NV12ToARGBRow_SSSE3 and ARGBToRGB565Row_SSE2
NV12ToARGBRow has an AVX2 version, so this CL implements
NV12ToRGB565Row_AVX2 with call to NV12ToARGBRow_AVX2 and
ARGBToRGB565Row_SSE2.
R=harryjin@google.com
BUG=libyuv:554
Review URL: https://codereview.chromium.org/1687953002 .
[modify]
http://crrev.com/0e554b18fe2a60f2a384d0dc86154b69bb7bc1b7/include/libyuv/row.h
[modify]
http://crrev.com/0e554b18fe2a60f2a384d0dc86154b69bb7bc1b7/source/row_common.cc
Original comment by bugdroid1@chromium.org
on 10 Feb 2016 at 7:19
Original comment by fbarch...@google.com
on 10 Feb 2016 at 11:12
Original issue reported on code.google.com by
fbarch...@google.com
on 26 Jan 2016 at 1:45