highperfocused/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

x86/vf_v360: use a faster horizontal add in remap4_8bit_line_avx2

Browse Source 
Signed-off-by: James Almer <jamrial@gmail.com>
This commit is contained in:
James Almer
2019-09-06 11:18:45 -03:00
parent 2200cf1aca
commit 4857688732
1 changed files with 4 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
libavfilter/x86/vf_v360.asm
View File

@@ -130,14 +130,11 @@ cglobal remap4_8bit_line, 7, 9, 11, dst, width, src, in_linesize, u, v, ker, x,
pmulld m4, m5 pmulld m4, m5
paddd m2, m4 paddd m2, m4
vextracti128 xm1, m2, 1 HADDD m2, m1
paddd m1, m2 psrld m2, m2, 0xe
phaddd m1, m1 packuswb m2, m2
phaddd m1, m1
psrld m1, m1, 0xe
packuswb m1, m1
pextrb [dstq+xq], xm1, 0 pextrb [dstq+xq], xm2, 0
add xq, 1 add xq, 1
add yq, 32 add yq, 32