diff options
| author | Loren Merritt <lorenm@u.washington.edu> | 2006-08-10 19:06:25 +0000 |
|---|---|---|
| committer | Loren Merritt <lorenm@u.washington.edu> | 2006-08-10 19:06:25 +0000 |
| commit | eb4825b5d43bb6ecfae4d64688f9e2d2ac075263 (patch) | |
| tree | 13acab1d16846859f7636ea19f796d02e2ea6da4 /libavcodec/dsputil.h | |
| parent | 60ae06e77e6e654b19529e89f8f067abd9a3d71a (diff) | |
| download | ffmpeg-eb4825b5d43bb6ecfae4d64688f9e2d2ac075263.tar.gz | |
sse and 3dnow implementations of float->int conversion and mdct windowing.
15% faster vorbis.
Originally committed as revision 5975 to svn://svn.ffmpeg.org/ffmpeg/trunk
Diffstat (limited to 'libavcodec/dsputil.h')
| -rw-r--r-- | libavcodec/dsputil.h | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/libavcodec/dsputil.h b/libavcodec/dsputil.h index 1083c39c71..5c31a87dcf 100644 --- a/libavcodec/dsputil.h +++ b/libavcodec/dsputil.h @@ -58,6 +58,10 @@ void ff_h264_idct_dc_add_c(uint8_t *dst, DCTELEM *block, int stride); void ff_h264_lowres_idct_add_c(uint8_t *dst, int stride, DCTELEM *block); void ff_h264_lowres_idct_put_c(uint8_t *dst, int stride, DCTELEM *block); +void ff_vector_fmul_add_add_c(float *dst, const float *src0, const float *src1, + const float *src2, int src3, int blocksize, int step); +void ff_float_to_int16_c(int16_t *dst, const float *src, int len); + /* encoding scans */ extern const uint8_t ff_alternate_horizontal_scan[64]; extern const uint8_t ff_alternate_vertical_scan[64]; @@ -307,7 +311,17 @@ typedef struct DSPContext { void (*h261_loop_filter)(uint8_t *src, int stride); + /* assume len is a multiple of 4, and arrays are 16-byte aligned */ void (*vorbis_inverse_coupling)(float *mag, float *ang, int blocksize); + void (*vector_fmul)(float *dst, const float *src, int len); + /* assume len is a multiple of 8, and arrays are 16-byte aligned */ + void (*vector_fmul_reverse)(float *dst, const float *src0, const float *src1, int len); + /* assume len is a multiple of 8, and src arrays are 16-byte aligned */ + void (*vector_fmul_add_add)(float *dst, const float *src0, const float *src1, const float *src2, int src3, int len, int step); + + /* C version: convert floats from the range [384.0,386.0] to ints in [-32768,32767] + * asm versions: convert floats from [-32768.0,32767.0] without rescaling */ + void (*float_to_int16)(int16_t *dst, const float *src, int len); /* (I)DCT */ void (*fdct)(DCTELEM *block/* align 16*/); |