x86/vf_v360: use a faster horizontal add in remap4_8bit_line_avx2

Signed-off-by: James Almer <jamrial@gmail.com>
5 years ago · 4857688732
parent 2200cf1aca
commit 4857688732
1 changed files with 4 additions and 7 deletions
--- a/libavfilter/x86/vf_v360.asm
+++ b/libavfilter/x86/vf_v360.asm
@ -130,14 +130,11 @@ cglobal remap4_8bit_line, 7, 9, 11, dst, width, src, in_linesize, u, v, ker, x,
        pmulld          m4, m5

        paddd           m2, m4
-        vextracti128   xm1, m2, 1
-        paddd           m1, m2
-        phaddd          m1, m1
-        phaddd          m1, m1
-        psrld           m1, m1, 0xe
-        packuswb        m1, m1
+        HADDD           m2, m1
+        psrld           m2, m2, 0xe
+        packuswb        m2, m2

-        pextrb   [dstq+xq], xm1, 0
+        pextrb   [dstq+xq], xm2, 0

        add   xq, 1
        add   yq, 32