virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-11-26 19:01:44 +02:00
Code Issues Releases Activity

x86: sbrdsp: implement SSE2 qmf_pre_shuffle

Browse Source 
From 253 to 51 cycles on Arrandale and Win64.
44 cycles on SandyBridge.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This commit is contained in:
Christophe Gisquet 2013-04-09 22:54:25 +00:00 committed by Michael Niedermayer
parent d2e051e30c
commit 2383068cbf
2 changed files with 32 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
libavcodec/x86/sbrdsp.asm
View File

@ -284,3 +284,33 @@ SBR_QMF_DEINT_BFLY
INIT_XMM sse2
SBR_QMF_DEINT_BFLY
INIT_XMM sse2
cglobal sbr_qmf_pre_shuffle, 1,4,7,z
%define OFFSET (32*4-2*mmsize)
mov r3q, OFFSET
lea r1q, [zq + (32+1)*4]
lea r2q, [zq + 64*4]
mova m6, [ps_neg]
.loop:
movu m0, [r1q]
movu m2, [r1q + mmsize]
movu m1, [zq + r3q + 4 + mmsize]
movu m3, [zq + r3q + 4]
pxor m2, m6
pxor m0, m6
pshufd m2, m2, q0123
pshufd m0, m0, q0123
SBUTTERFLY dq, 2, 3, 5
SBUTTERFLY dq, 0, 1, 4
mova [r2q + 2*r3q + 0*mmsize], m2
mova [r2q + 2*r3q + 1*mmsize], m3
mova [r2q + 2*r3q + 2*mmsize], m0
mova [r2q + 2*r3q + 3*mmsize], m1
add r1q, 2*mmsize
sub r3q, 2*mmsize
jge .loop
mova m2, [zq]
movq [r2q], m2
REP_RET

2
libavcodec/x86/sbrdsp_init.c
View File

@ -36,6 +36,7 @@ void ff_sbr_neg_odd_64_sse(float *z);
void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z);
void ff_sbr_qmf_deint_bfly_sse(float *v, const float *src0, const float *src1);
void ff_sbr_qmf_deint_bfly_sse2(float *v, const float *src0, const float *src1);
void ff_sbr_qmf_pre_shuffle_sse2(float *z);
av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
{
@ -53,5 +54,6 @@ av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
if (EXTERNAL_SSE2(mm_flags)) {
s->qmf_deint_bfly = ff_sbr_qmf_deint_bfly_sse2;
s->qmf_pre_shuffle = ff_sbr_qmf_pre_shuffle_sse2;
}
}