levytamar82 7045aec00a SAD32xh and SAD64xh for AVX2 ...

All sad function that process above 32 consecutive elements are optimized
for AVX2:
vp9_sad64x64
vp9_sad64x32
vp9_sad32x64
vp9_sad32x32
vp9_sad32x16
vp9_sad64x64_avg
vp9_sad64x32_avg
vp9_sad32x64_avg
vp9_sad32x32_avg
vp9_sad32x16_avg
The functions that appeared as a hotspot is vp9_sad32x32 and vp9_sad64x64
vp9_sad32x32 was optimized by 68% and vp9_sad64x64 was optimized by 90%
both of them gave and overall ~2.3% user level gain

Change-Id: Iccf86b375a2b54c5fbbe685902ead0c9a561b9fd

2014-10-19 13:59:10 -07:00

..

vp9_dct32x32_avx2.c

vp9_short_fdct32x32_rd vp9_short_fdct32x32 optimized for AVX2

2013-11-21 14:19:49 -08:00

vp9_dct32x32_sse2.c

Moving pair_set_epi32 macro into vp9_dct32x32_sse2.c.

2014-05-01 16:45:49 -07:00

vp9_dct_avx2.c

Fix bug 805

2014-07-28 15:46:01 -07:00

vp9_dct_mmx.asm

Add an x86inc MMX fwht4x4.

2014-05-08 12:01:27 -07:00

vp9_dct_sse2.c

Removing duplicated code.

2014-09-02 17:57:35 -07:00

vp9_dct_ssse3_x86_64.asm

Fix potential overflow issue in SSSE3 forward 8x8 2D-DCT

2014-06-03 14:21:47 -07:00

vp9_error_intrin_avx2.c

AVX2 To VP9 Block Error Optimization

2014-05-14 11:51:07 -07:00

vp9_error_sse2.asm

Make coefficient skip condition an explicit RD choice.

2013-06-28 10:28:49 -07:00

vp9_quantize_ssse3_x86_64.asm

Re-design quantization process for 32x32 transform block

2014-07-08 16:55:28 -07:00

vp9_sad4d_intrin_avx2.c

Fix bug 806

2014-08-07 14:13:30 -07:00

vp9_sad4d_sse2.asm

Implement SSE version for sad4x8x4d and SSE2 version for sad8x4x4d.

2013-06-12 17:40:01 -04:00

vp9_sad_intrin_avx2.c

SAD32xh and SAD64xh for AVX2

2014-10-19 13:59:10 -07:00

vp9_sad_sse2.asm

Add averaging-SAD functions for 8-point comp-inter motion search.

2013-06-25 12:57:28 -07:00

vp9_sad_sse3.asm

Merge master branch into experimental

2013-03-01 11:06:05 -08:00

vp9_sad_sse4.asm

this commit converts all sad ptrs to uint32

2013-02-28 08:46:35 -08:00

vp9_sad_ssse3.asm

add private to assembly files to insure proper chromebuild

2012-12-20 09:40:18 -08:00

vp9_ssim_opt_x86_64.asm

Renames x86_64 specific asm files

2014-05-21 13:55:56 -07:00

vp9_subpel_variance_impl_intrin_avx2.c

32 Align Load bug

2014-08-14 14:07:28 -07:00

vp9_subpel_variance.asm

Remove TEXTREL from 32bit encoder

2013-11-07 13:39:40 -08:00

vp9_subtract_sse2.asm

Remove emms - that shouldn't be there.

2013-06-21 14:45:04 -07:00

vp9_temporal_filter_apply_sse2.asm

Fixed a crash windows build

2014-05-28 15:50:50 -07:00

vp9_variance_avx2.c

Cleaning up vp9_variance_avx2.c.

2014-09-02 11:01:29 -07:00

vp9_variance_impl_intrin_avx2.c

AVX2 Variance Optimization

2014-01-08 12:05:53 -07:00

vp9_variance_sse2.c

Replacing vp9_get_mb_ss_sse2 asm implementation with intrinsics.

2014-09-06 00:10:25 -07:00