diff options
author | Jason Garrett-Glaser <darkshikari@gmail.com> | 2011-01-15 00:34:25 +0300 |
---|---|---|
committer | Jason Garrett-Glaser <darkshikari@gmail.com> | 2011-01-15 00:34:25 +0300 |
commit | 19fb234e4af1ff9f58ff2fdd604ac6f6bb87ad6b (patch) | |
tree | 220be84d79d9c771c1afeab43fdd2aaa82fea01d /libavcodec/dsputil.h | |
parent | 6c18f1cda2e2b2471ebf75d30d552cb0cb61b6ad (diff) |
H.264: split luma dc idct out and implement MMX/SSE2 versions
About 2.5x the speed.
NOTE: the way that the asm code handles large qmuls is a bit suboptimal.
If x264-style dequant was used (separate shift and qmul values), it might
be possible to get some extra speed.
Originally committed as revision 26336 to svn://svn.ffmpeg.org/ffmpeg/trunk
Diffstat (limited to 'libavcodec/dsputil.h')
-rw-r--r-- | libavcodec/dsputil.h | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/libavcodec/dsputil.h b/libavcodec/dsputil.h index 6c56a65885..0efbad918a 100644 --- a/libavcodec/dsputil.h +++ b/libavcodec/dsputil.h @@ -64,6 +64,10 @@ void ff_h264_idct_add16intra_c(uint8_t *dst, const int *blockoffset, DCTELEM *bl void ff_h264_idct8_add4_c(uint8_t *dst, const int *blockoffset, DCTELEM *block, int stride, const uint8_t nnzc[6*8]); void ff_h264_idct_add8_c(uint8_t **dest, const int *blockoffset, DCTELEM *block, int stride, const uint8_t nnzc[6*8]); +void ff_h264_luma_dc_dequant_idct_c(DCTELEM *output, DCTELEM *input, int qmul); +void ff_svq3_luma_dc_dequant_idct_c(DCTELEM *output, DCTELEM *input, int qp); +void ff_svq3_add_idct_c(uint8_t *dst, DCTELEM *block, int stride, int qp, int dc); + void ff_vector_fmul_window_c(float *dst, const float *src0, const float *src1, const float *win, float add_bias, int len); void ff_float_to_int16_c(int16_t *dst, const float *src, long len); |