diff options
| author | Michael Niedermayer <michaelni@gmx.at> | 2013-05-04 10:06:10 +0200 |
|---|---|---|
| committer | Michael Niedermayer <michaelni@gmx.at> | 2013-05-04 10:07:43 +0200 |
| commit | 711c8ee71d719d6d89a523618f078bb17dbe1abf (patch) | |
| tree | b3f74bd4807eade81577b24b2b5c601c110d498f /libavcodec/x86 | |
| parent | f18d2dff1194b34b79dc7641aafe54d1df349e40 (diff) | |
| parent | 4a7af92cc80ced8498626401ed21f25ffe6740c8 (diff) | |
| download | ffmpeg-711c8ee71d719d6d89a523618f078bb17dbe1abf.tar.gz | |
Merge commit '4a7af92cc80ced8498626401ed21f25ffe6740c8'
* commit '4a7af92cc80ced8498626401ed21f25ffe6740c8':
sbrdsp: Unroll and use integer operations
sbrdsp: Unroll sbr_autocorrelate_c
x86: sbrdsp: Implement SSE2 qmf_deint_bfly
Conflicts:
libavcodec/sbrdsp.c
libavcodec/x86/sbrdsp.asm
libavcodec/x86/sbrdsp_init.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/x86')
| -rw-r--r-- | libavcodec/x86/sbrdsp.asm | 48 |
1 files changed, 24 insertions, 24 deletions
diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm index 1ce5777602..c4c95780ee 100644 --- a/libavcodec/x86/sbrdsp.asm +++ b/libavcodec/x86/sbrdsp.asm @@ -252,36 +252,36 @@ cglobal sbr_neg_odd_64, 1,2,4,z ; 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] + 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] + 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 + 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 + 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 + 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], m0 mova [vq+cq+mmsize], m4 - add src1q, 2*mmsize - add vrevq, 2*mmsize - sub cq, 2*mmsize - jge .loop + add src1q, 2*mmsize + add vrevq, 2*mmsize + sub cq, 2*mmsize + jge .loop REP_RET %endmacro |