diff options
| author | James Almer <jamrial@gmail.com> | 2014-09-26 20:46:41 -0300 |
|---|---|---|
| committer | James Almer <jamrial@gmail.com> | 2014-09-26 20:48:40 -0300 |
| commit | 26cd7b1e1ad54dca688b5d62081cd79c4f56a387 (patch) | |
| tree | ff459d20a195abd07abb0eb30c7f066919c78c8f /libavcodec/x86/fmtconvert_init.c | |
| parent | b7a55388706b81db2e8ec0b8b093edf9deede21e (diff) | |
| download | ffmpeg-26cd7b1e1ad54dca688b5d62081cd79c4f56a387.tar.gz | |
x86/fmtconvert: add ff_int32_to_float_fmul_array8_{sse,sse2}
About two times faster than the c wrapper.
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
Diffstat (limited to 'libavcodec/x86/fmtconvert_init.c')
| -rw-r--r-- | libavcodec/x86/fmtconvert_init.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/libavcodec/x86/fmtconvert_init.c b/libavcodec/x86/fmtconvert_init.c index d300dfd864..cbb96e2530 100644 --- a/libavcodec/x86/fmtconvert_init.c +++ b/libavcodec/x86/fmtconvert_init.c @@ -32,6 +32,10 @@ void ff_int32_to_float_fmul_scalar_sse (float *dst, const int32_t *src, float mul, int len); void ff_int32_to_float_fmul_scalar_sse2(float *dst, const int32_t *src, float mul, int len); +void ff_int32_to_float_fmul_array8_sse (FmtConvertContext *c, float *dst, const int32_t *src, + const float *mul, int len); +void ff_int32_to_float_fmul_array8_sse2(FmtConvertContext *c, float *dst, const int32_t *src, + const float *mul, int len); void ff_float_to_int16_3dnow(int16_t *dst, const float *src, long len); void ff_float_to_int16_sse (int16_t *dst, const float *src, long len); @@ -134,12 +138,14 @@ av_cold void ff_fmt_convert_init_x86(FmtConvertContext *c, AVCodecContext *avctx } if (EXTERNAL_SSE(cpu_flags)) { c->int32_to_float_fmul_scalar = ff_int32_to_float_fmul_scalar_sse; + c->int32_to_float_fmul_array8 = ff_int32_to_float_fmul_array8_sse; c->float_to_int16 = ff_float_to_int16_sse; c->float_to_int16_interleave = float_to_int16_interleave_sse; c->float_interleave = float_interleave_sse; } if (EXTERNAL_SSE2(cpu_flags)) { c->int32_to_float_fmul_scalar = ff_int32_to_float_fmul_scalar_sse2; + c->int32_to_float_fmul_array8 = ff_int32_to_float_fmul_array8_sse2; c->float_to_int16 = ff_float_to_int16_sse2; c->float_to_int16_interleave = float_to_int16_interleave_sse2; } |