diff options
| author | Loren Merritt <lorenm@u.washington.edu> | 2007-09-29 22:31:18 +0000 |
|---|---|---|
| committer | Loren Merritt <lorenm@u.washington.edu> | 2007-09-29 22:31:18 +0000 |
| commit | 6810b93a81a8c0e845dc2bb90f9e2d35eac17cd1 (patch) | |
| tree | 5727ef05fe765c427001d23f416c23c7bafc0867 /libavcodec/dsputil.h | |
| parent | fdf885983c878e6976a72311c56a0efefa725d11 (diff) | |
| download | ffmpeg-6810b93a81a8c0e845dc2bb90f9e2d35eac17cd1.tar.gz | |
sse2 version of compute_autocorr().
4x faster than c (somehow, even though doubles only allow 2x simd).
overal flac encoding: 15-50% faster on core2, 4-11% on k8, 3-13% on p4.
Originally committed as revision 10621 to svn://svn.ffmpeg.org/ffmpeg/trunk
Diffstat (limited to 'libavcodec/dsputil.h')
| -rw-r--r-- | libavcodec/dsputil.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/libavcodec/dsputil.h b/libavcodec/dsputil.h index b91ea5a93b..3c6121c3b6 100644 --- a/libavcodec/dsputil.h +++ b/libavcodec/dsputil.h @@ -328,6 +328,8 @@ typedef struct DSPContext { /* assume len is a multiple of 4, and arrays are 16-byte aligned */ void (*vorbis_inverse_coupling)(float *mag, float *ang, int blocksize); + /* no alignment needed */ + void (*flac_compute_autocorr)(const int32_t *data, int len, int lag, double *autoc); /* assume len is a multiple of 8, and arrays are 16-byte aligned */ void (*vector_fmul)(float *dst, const float *src, int len); void (*vector_fmul_reverse)(float *dst, const float *src0, const float *src1, int len); |