diff options
author | Christophe Gisquet <christophe.gisquet@gmail.com> | 2012-11-25 07:55:28 +0100 |
---|---|---|
committer | Diego Biurrun <diego@biurrun.de> | 2013-01-06 13:57:01 +0100 |
commit | 4f50646697606df39317b93c2a427603b77636ee (patch) | |
tree | 45780067d1134a3ad5e6be14d2e8d7968be994e4 | |
parent | 44a0036d10579ed91e48df24859e54b08a582742 (diff) | |
download | ffmpeg-4f50646697606df39317b93c2a427603b77636ee.tar.gz |
x86: sbrdsp: Implement SSE qmf_post_shuffle
255 to 174 cycles on Arrandale / Win64. Unrolling yields no gain.
Signed-off-by: Diego Biurrun <diego@biurrun.de>
-rw-r--r-- | libavcodec/x86/sbrdsp.asm | 20 | ||||
-rw-r--r-- | libavcodec/x86/sbrdsp_init.c | 2 |
2 files changed, 22 insertions, 0 deletions
diff --git a/libavcodec/x86/sbrdsp.asm b/libavcodec/x86/sbrdsp.asm index 063c24f95c..ae8449065c 100644 --- a/libavcodec/x86/sbrdsp.asm +++ b/libavcodec/x86/sbrdsp.asm @@ -24,6 +24,7 @@ SECTION_RODATA ; mask equivalent for multiply by -1.0 1.0 ps_mask times 2 dd 1<<31, 0 +ps_neg times 4 dd 1<<31 SECTION_TEXT @@ -203,3 +204,22 @@ cglobal sbr_sum64x5, 1,2,4,z cmp zq, r1q jne .loop REP_RET + +INIT_XMM sse +cglobal sbr_qmf_post_shuffle, 2,3,4,W,z + lea r2q, [zq + (64-4)*4] + mova m3, [ps_neg] +.loop: + mova m1, [zq] + xorps m0, m3, [r2q] + shufps m0, m0, m0, q0123 + unpcklps m2, m0, m1 + unpckhps m0, m0, m1 + mova [Wq + 0], m2 + mova [Wq + 16], m0 + add Wq, 32 + sub r2q, 16 + add zq, 16 + cmp zq, r2q + jl .loop + REP_RET diff --git a/libavcodec/x86/sbrdsp_init.c b/libavcodec/x86/sbrdsp_init.c index 264b455b3e..747817bb21 100644 --- a/libavcodec/x86/sbrdsp_init.c +++ b/libavcodec/x86/sbrdsp_init.c @@ -31,6 +31,7 @@ void ff_sbr_hf_g_filt_sse(float (*Y)[2], const float (*X_high)[40][2], void ff_sbr_hf_gen_sse(float (*X_high)[2], const float (*X_low)[2], const float alpha0[2], const float alpha1[2], float bw, int start, int end); +void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z); void ff_sbrdsp_init_x86(SBRDSPContext *s) { @@ -41,5 +42,6 @@ void ff_sbrdsp_init_x86(SBRDSPContext *s) s->sum64x5 = ff_sbr_sum64x5_sse; s->hf_g_filt = ff_sbr_hf_g_filt_sse; s->hf_gen = ff_sbr_hf_gen_sse; + s->qmf_post_shuffle = ff_sbr_qmf_post_shuffle_sse; } } |