From 08e3ea60ff4059341b74be04a428a38f7c3630b0 Mon Sep 17 00:00:00 2001 From: Christophe Gisquet Date: Fri, 14 Feb 2014 15:03:09 +0000 Subject: x86: synth filter float: implement SSE2 version Timings for Arrandale: C SSE win32: 2108 334 win64: 1152 322 Factorizing the inner loop with a call/jmp is a >15 cycles cost, even with the jmp destination being aligned. Unrolling for ARCH_X86_64 is a 20 cycles gain. Signed-off-by: Janne Grunau --- libavcodec/synth_filter.c | 1 + 1 file changed, 1 insertion(+) (limited to 'libavcodec/synth_filter.c') diff --git a/libavcodec/synth_filter.c b/libavcodec/synth_filter.c index 8e6f1202fe..d0ace4040e 100644 --- a/libavcodec/synth_filter.c +++ b/libavcodec/synth_filter.c @@ -61,4 +61,5 @@ av_cold void ff_synth_filter_init(SynthFilterContext *c) c->synth_filter_float = synth_filter_float; if (ARCH_ARM) ff_synth_filter_init_arm(c); + if (ARCH_X86) ff_synth_filter_init_x86(c); } -- cgit v1.2.3