From f4b0d12f5b3fb2fe825fb2ac9b2d9d9374baa5c5 Mon Sep 17 00:00:00 2001 From: Christophe Gisquet Date: Fri, 21 Dec 2012 18:11:06 +0100 Subject: x86: sbrdsp: Implement SSE neg_odd_64 Timing on Arrandale: C SSE Win32: 57 44 Win64: 47 38 Unrolling and not storing mask both save some cycles. Signed-off-by: Diego Biurrun --- libavcodec/x86/sbrdsp_init.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'libavcodec/x86/sbrdsp_init.c') diff --git a/libavcodec/x86/sbrdsp_init.c b/libavcodec/x86/sbrdsp_init.c index 27fade133f..cb65a23f22 100644 --- a/libavcodec/x86/sbrdsp_init.c +++ b/libavcodec/x86/sbrdsp_init.c @@ -32,6 +32,7 @@ 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_neg_odd_64_sse(float *z); void ff_sbr_qmf_post_shuffle_sse(float W[32][2], const float *z); av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s) @@ -39,6 +40,7 @@ av_cold void ff_sbrdsp_init_x86(SBRDSPContext *s) int mm_flags = av_get_cpu_flags(); if (EXTERNAL_SSE(mm_flags)) { + s->neg_odd_64 = ff_sbr_neg_odd_64_sse; s->sum_square = ff_sbr_sum_square_sse; s->sum64x5 = ff_sbr_sum64x5_sse; s->hf_g_filt = ff_sbr_hf_g_filt_sse; -- cgit v1.2.3