Yunqing Wang df8e156432 Modify HORIZx16 macro in subpixel filter functions ...

Interleaved the instructions, reduced register dependency, and
prefetched the source data. This improved the decoder speed
by 0.6% - 2%.

Change-Id: I568067aa0c629b2e58219326899c82aedf7eccca

2013-10-01 12:49:25 -07:00

..

vp9_asm_stubs.c

Revert "Improved 8t filters"

2013-09-13 15:13:06 -07:00

vp9_copy_sse2.asm

Replace copy_memNxM functions with a generic copy/avg function.

2013-07-10 18:27:24 -07:00

vp9_idct_intrin_sse2.c

Optimize 32x32 2D inverse DCT for speed-up

2013-07-31 17:13:31 -07:00

vp9_intrapred_sse2.asm

Fix x86inc.asm to build PIC code correctly

2013-09-18 13:45:46 -07:00

vp9_intrapred_ssse3.asm

Fix x86inc.asm to build PIC code correctly

2013-09-18 13:45:46 -07:00

vp9_loopfilter_intrin_sse2.c

Improved mb_lpf_horizontal_edge_w_sse2_8

2013-08-29 08:30:17 -04:00

vp9_loopfilter_mmx.asm

Removing unused simple loopfilter code.

2013-05-10 11:04:43 -07:00

vp9_postproc_mmx.asm

Code cleanup: lower case variable names.

2013-03-20 16:41:30 -07:00

vp9_postproc_sse2.asm

Code cleanup: lower case variable names.

2013-03-20 16:41:30 -07:00

vp9_postproc_x86.h

google style guide include guards

2012-11-30 07:30:59 -08:00

vp9_subpixel_8t_ssse3.asm

Modify HORIZx16 macro in subpixel filter functions

2013-10-01 12:49:25 -07:00