aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/synth_filter.h
diff options
context:
space:
mode:
authorChristophe Gisquet <christophe.gisquet@gmail.com>2014-02-14 16:00:48 +0000
committerMichael Niedermayer <michaelni@gmx.at>2014-02-28 20:34:40 +0100
commit2cdbcc004837ce092a14f326f24d97a29512a2c3 (patch)
tree7fc4341ce3da5c0aae72033134c5daf7745408fd /libavcodec/synth_filter.h
parent5333e0dd66c5695fc708bc9d7af4bf8750674b8f (diff)
downloadffmpeg-2cdbcc004837ce092a14f326f24d97a29512a2c3.tar.gz
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: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/synth_filter.h')
-rw-r--r--libavcodec/synth_filter.h1
1 files changed, 1 insertions, 0 deletions
diff --git a/libavcodec/synth_filter.h b/libavcodec/synth_filter.h
index 33edcc437f..b63fd779b5 100644
--- a/libavcodec/synth_filter.h
+++ b/libavcodec/synth_filter.h
@@ -33,5 +33,6 @@ typedef struct SynthFilterContext {
void ff_synth_filter_init(SynthFilterContext *c);
void ff_synth_filter_init_arm(SynthFilterContext *c);
+void ff_synth_filter_init_x86(SynthFilterContext *c);
#endif /* AVCODEC_SYNTH_FILTER_H */