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

1 files changed, 6 insertions, 0 deletions

diff --git a/libavcodec/dsputil.c b/libavcodec/dsputil.c
index 88fe5e0d41..ce83096431 100644
--- a/libavcodec/dsputil.c
+++ b/libavcodec/dsputil.c
@@ -41,6 +41,9 @@ void ff_spatial_dwt(int *buffer, int width, int height, int stride, int type, in
 /* vorbis.c */
 void vorbis_inverse_coupling(float *mag, float *ang, int blocksize);
 
+/* flacenc.c */
+void ff_flac_compute_autocorr(const int32_t *data, int len, int lag, double *autoc);
+
 uint8_t ff_cropTbl[256 + 2 * MAX_NEG_CROP] = {0, };
 uint32_t ff_squareTbl[512] = {0, };
 
@@ -4132,6 +4135,9 @@ void dsputil_init(DSPContext* c, AVCodecContext *avctx)
 #ifdef CONFIG_VORBIS_DECODER
     c->vorbis_inverse_coupling = vorbis_inverse_coupling;
 #endif
+#ifdef CONFIG_FLAC_ENCODER
+    c->flac_compute_autocorr = ff_flac_compute_autocorr;
+#endif
     c->vector_fmul = vector_fmul_c;
     c->vector_fmul_reverse = vector_fmul_reverse_c;
     c->vector_fmul_add_add = ff_vector_fmul_add_add_c;