1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-28 20:53:54 +02:00

x86/hevc_deblock: load less data in hevc_h_loop_filter_luma_8

Reading 8 bytes is enough.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This commit is contained in:
James Almer 2014-07-28 16:17:35 -03:00 committed by Michael Niedermayer
parent f137876182
commit 664e9e4331

View File

@ -799,14 +799,14 @@ cglobal hevc_h_loop_filter_luma_8, 4, 15, 16, pix, stride, beta, tc, count, pix0
mov pix0q, pixq
sub pix0q, src3strideq
sub pix0q, strideq
movdqu m0, [pix0q]; p3
movdqu m1, [pix0q + strideq]; p2
movdqu m2, [pix0q + 2 * strideq]; p1
movdqu m3, [pix0q + src3strideq]; p0
movdqu m4, [pixq]; q0
movdqu m5, [pixq + strideq]; q1
movdqu m6, [pixq + 2 * strideq]; q2
movdqu m7, [pixq + src3strideq]; q3
movq m0, [pix0q]; p3
movq m1, [pix0q + strideq]; p2
movq m2, [pix0q + 2 * strideq]; p1
movq m3, [pix0q + src3strideq]; p0
movq m4, [pixq]; q0
movq m5, [pixq + strideq]; q1
movq m6, [pixq + 2 * strideq]; q2
movq m7, [pixq + src3strideq]; q3
pxor m8, m8
punpcklbw m0, m8
punpcklbw m1, m8