Scott LaVarnway 62ab5e99c1 vpx: [x86] add vp9_block_error_fp_avx2() ...

SSE2 asm vs AVX2 intrinsics speed gains:
blocksize   16: ~1.00
blocksize   64: ~1.17
blocksize  256: ~1.67
blocksize 1024: ~1.81

Change-Id: I2a86db239cf57e3ff617890ccb2d236aba83ad5e

2017-11-09 05:02:31 -08:00

..

temporal_filter_sse4.c

vp[89],vpx_dsp: add missing includes

2017-06-21 19:00:15 -07:00

vp9_dct_intrin_sse2.c

Remove the unnecessary cast of (int16_t)cospi_{1...31}_64

2017-09-20 14:13:26 -07:00

vp9_dct_sse2.asm

bitdepth conversion: really use num elements

2017-02-16 15:02:48 +00:00

vp9_dct_ssse3.c

Remove the unnecessary cast of (int16_t)cospi_{1...31}_64

2017-09-20 14:13:26 -07:00

vp9_denoiser_sse2.c

vp9/encoder: apply clang-format

2016-08-02 16:47:11 -07:00

vp9_diamond_search_sad_avx.c

Refactor mv limits.

2016-08-08 11:54:00 -07:00

vp9_error_avx2.c

vpx: [x86] add vp9_block_error_fp_avx2()

2017-11-09 05:02:31 -08:00

vp9_error_sse2.asm

block error sse2: sum in 32 bits when possible

2017-05-01 09:59:18 -07:00

vp9_frame_scale_ssse3.c

Add 4 to 3 scaling SSSE3 optimization

2017-10-16 15:42:42 -07:00

vp9_highbd_block_error_intrin_sse2.c

vp9/encoder: apply clang-format

2016-08-02 16:47:11 -07:00

vp9_quantize_sse2.c

quantize fp: ignore skip_block in x86

2017-08-21 14:33:41 -07:00

vp9_quantize_ssse3_x86_64.asm

quantize fp: ignore skip_block in x86

2017-08-21 14:33:41 -07:00