RepoMirrors/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2025-03-04 11:38:19 +00:00
Code Issues Projects Releases Wiki Activity

x86: sbrdsp: implement SSE qmf_deint_bfly

Browse Source 
From 312 to 89/68 (sse/sse2) cycles on Arrandale and Win64.
Sandybridge: 68/47 cycles.

Having a loop counter is a 7 cycle gain.
Unrolling is another 7 cycle gain.
Working in reverse scan is another 6 cycles.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
This commit is contained in:
Christophe Gisquet 2013-04-07 20:20:33 +00:00 committed by Michael Niedermayer
parent 1adf54de56
commit e2946e5c34
2 changed files with 49 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
libavcodec/x86/sbrdsp.asm
View File

@ -242,3 +242,45 @@ cglobal sbr_neg_odd_64, 1,2,4,z
cmp zq, r1q cmp zq, r1q
jne .loop jne .loop
REP_RET REP_RET
; sbr_qmf_deint_bfly(float *v, const float *src0, const float *src1)
%macro SBR_QMF_DEINT_BFLY 0
cglobal sbr_qmf_deint_bfly, 3,5,8, v,src0,src1,vrev,c
mov cq, 64*4-2*mmsize
lea vrevq, [vq + 64*4]
.loop:
mova m0, [src0q+cq]
mova m1, [src1q]
mova m4, [src0q+cq+mmsize]
mova m5, [src1q+mmsize]
%if cpuflag(sse2)
pshufd m2, m0, q0123
pshufd m3, m1, q0123
pshufd m6, m4, q0123
pshufd m7, m5, q0123
%else
shufps m2, m0, m0, q0123
shufps m3, m1, m1, q0123
shufps m6, m4, m4, q0123
shufps m7, m5, m5, q0123
%endif
addps m5, m2
subps m0, m7
addps m1, m6
subps m4, m3
mova [vrevq], m1
mova [vrevq+mmsize], m5
mova [vq+cq], m0
mova [vq+cq+mmsize], m4
add src1q, 2*mmsize
add vrevq, 2*mmsize
sub cq, 2*mmsize
jge .loop
REP_RET
%endmacro
INIT_XMM sse
SBR_QMF_DEINT_BFLY
INIT_XMM sse2
SBR_QMF_DEINT_BFLY

7
libavcodec/x86/sbrdsp_init.c
View File

@ -34,6 +34,8 @@ void ff_sbr_hf_gen_sse(float (*X_high)[2], const float (*X_low)[2],
float bw, int start, int end); float bw, int start, int end);
void ff_sbr_neg_odd_64_sse(float *z); 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_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);
av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s) av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
{ {
@ -46,5 +48,10 @@ av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s)
s->hf_g_filt = ff_sbr_hf_g_filt_sse; s->hf_g_filt = ff_sbr_hf_g_filt_sse;
s->hf_gen = ff_sbr_hf_gen_sse; s->hf_gen = ff_sbr_hf_gen_sse;
s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse; s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse;
s->qmf_deint_bfly = ff_sbr_qmf_deint_bfly_sse;
}
if (EXTERNAL_SSE2(mm_flags)) {
s->qmf_deint_bfly = ff_sbr_qmf_deint_bfly_sse2;
} }
} }