Manojkumar Bhosale 83f460be33 Add MSA optimized ARGB Multiply/Add/Subtract row functions
R=fbarchard@google.com
BUG=libyuv:634

Performance Gain (vs C vectorized)
ARGBMultiplyRow_MSA       - 1.4x
ARGBAddRow_MSA            - 8.6x
ARGBSubtractRow_MSA       - 8.6x

ARGBMultiplyRow_Any_MSA   - 1.35x
ARGBAddRow_Any_MSA        - 7.3x
ARGBSubtractRow_Any_MSA   - 7.2x

Performance Gain (vs C non-vectorized)
ARGBMultiplyRow_MSA       - 4.4x
ARGBAddRow_MSA            - 27x
ARGBSubtractRow_MSA       - 22x

ARGBMultiplyRow_Any_MSA   - 3.5x
ARGBAddRow_Any_MSA        - 23x
ARGBSubtractRow_Any_MSA   - 18x

Review URL: https://codereview.chromium.org/2529983002 .
2016-12-02 15:21:10 +05:30
..
basic_types.h clang-format libyuv 2016-11-07 17:37:23 -08:00
compare_row.h clang-format libyuv 2016-11-07 17:37:23 -08:00
compare.h clang-format libyuv 2016-11-07 17:37:23 -08:00
convert_argb.h clang-format libyuv 2016-11-07 17:37:23 -08:00
convert_from_argb.h clang-format libyuv 2016-11-07 17:37:23 -08:00
convert_from.h clang-format libyuv 2016-11-07 17:37:23 -08:00
convert.h clang-format libyuv 2016-11-07 17:37:23 -08:00
cpu_id.h Add f16c (halffloat) cpuid 2016-10-14 16:34:08 -07:00
macros_msa.h clang-format libyuv 2016-11-07 17:37:23 -08:00
mjpeg_decoder.h clang-format libyuv 2016-11-07 17:37:23 -08:00
planar_functions.h clang-format libyuv 2016-11-07 17:37:23 -08:00
rotate_argb.h clang-format libyuv 2016-11-07 17:37:23 -08:00
rotate_row.h clang-format libyuv 2016-11-07 17:37:23 -08:00
rotate.h clang-format libyuv 2016-11-07 17:37:23 -08:00
row.h Add MSA optimized ARGB Multiply/Add/Subtract row functions 2016-12-02 15:21:10 +05:30
scale_argb.h clang-format libyuv 2016-11-07 17:37:23 -08:00
scale_row.h clang-format libyuv 2016-11-07 17:37:23 -08:00
scale.h clang-format libyuv 2016-11-07 17:37:23 -08:00
version.h Add MSA optimized ARGBToRGB565Row_MSA, ARGBToARGB1555Row_MSA, ARGBToARGB4444Row_MSA, ARGBToUV444Row_MSA functions 2016-11-22 10:47:55 -08:00
video_common.h clang-format libyuv 2016-11-07 17:37:23 -08:00