diff options
| author | Christophe Gisquet <christophe.gisquet@gmail.com> | 2013-04-07 20:20:33 +0000 |
|---|---|---|
| committer | Michael Niedermayer <michaelni@gmx.at> | 2013-04-08 02:26:34 +0200 |
| commit | e2946e5c3482ab78913bfa5527a6fa9ea4e70bb4 (patch) | |
| tree | e5964637887b5189cd2b2f1f3719fcb03cc57694 /libavcodec/x86/sbrdsp.asm | |
| parent | 1adf54de56be13a6df51c5d42f0ecf2e1ec0c648 (diff) | |
| download | ffmpeg-e2946e5c3482ab78913bfa5527a6fa9ea4e70bb4.tar.gz | |
x86: sbrdsp: implement SSE qmf_deint_bfly
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>
Diffstat (limited to 'libavcodec/x86/sbrdsp.asm')
| -rw-r--r-- | libavcodec/x86/sbrdsp.asm | 42 |
1 files changed, 42 insertions, 0 deletions
diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm index 2900469dbd..273e950563 100644 --- a/libavcodec/x86/sbrdsp.asm +++ b/libavcodec/x86/sbrdsp.asm @@ -242,3 +242,45 @@ cglobal sbr_neg_odd_64, 1,2,4,z cmp zq, r1q jne .loop 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 |