xenia-project/FFmpeg
1
0
Fork 0
mirror of https://github.com/xenia-project/FFmpeg.git synced 2024-11-24 12:09:55 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

x86/exrdsp: optimize ff_reorder_pixels_avx2()

Browse Source 
Tested with "checkasm --test=exrdsp -bench"

Before:
reorder_pixels_c: 5187.8
reorder_pixels_sse2: 377.0
reorder_pixels_avx2: 331.3

After:
reorder_pixels_c: 5181.5
reorder_pixels_sse2: 377.0
reorder_pixels_avx2: 313.8

Signed-off-by: James Almer <jamrial@gmail.com>
This commit is contained in:
Henrik Gramner 2017-09-17 22:52:13 -03:00 committed by James Almer
parent 3ffd3b7f5f
commit 18821e3ba1
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
libavcodec/x86/exrdsp.asm
View File

@ -39,16 +39,15 @@ cglobal reorder_pixels, 3,4,3, dst, src1, size, src2
neg sizeq ; size = offset for dst, src1, src2
.loop:
%if cpuflag(avx2)
vpermq m0, [src1q + sizeq], 0xd8; load first part
vpermq m1, [src2q + sizeq], 0xd8; load second part
%else
mova m0, [src1q+sizeq] ; load first part
movu m1, [src2q+sizeq] ; load second part
%endif
SBUTTERFLY bw, 0, 1, 2 ; interleaved
mova [dstq+2*sizeq ], m0 ; copy to dst
mova [dstq+2*sizeq+mmsize], m1
mova [dstq+2*sizeq ], xm0 ; copy to dst
mova [dstq+2*sizeq+16], xm1
%if cpuflag(avx2)
vperm2i128 m0, m0, m1, q0301
mova [dstq+2*sizeq+32], m0
%endif
add sizeq, mmsize
jl .loop
RET