diff options
| author | Justin Ruggles <justin.ruggles@gmail.com> | 2011-01-30 15:06:46 +0000 |
|---|---|---|
| committer | Michael Niedermayer <michaelni@gmx.at> | 2011-02-04 03:08:09 +0100 |
| commit | fe2ff6d24745f0739bfde9061092c1268557310b (patch) | |
| tree | 9cbcf8b2472dd7612dd84c8b6b237d9d02b4daf9 /libavcodec/x86/dsputil_yasm.asm | |
| parent | a35d782d28ef0497f2b65eb300c2e6a6028fc165 (diff) | |
| download | ffmpeg-fe2ff6d24745f0739bfde9061092c1268557310b.tar.gz | |
Separate format conversion DSP functions from DSPContext.
This will be beneficial for use with the audio conversion API without
requiring it to depend on all of dsputil.
Signed-off-by: Mans Rullgard <mans@mansr.com>
(cherry picked from commit c73d99e672329c8f2df290736ffc474c360ac4ae)
Diffstat (limited to 'libavcodec/x86/dsputil_yasm.asm')
| -rw-r--r-- | libavcodec/x86/dsputil_yasm.asm | 69 |
1 files changed, 0 insertions, 69 deletions
diff --git a/libavcodec/x86/dsputil_yasm.asm b/libavcodec/x86/dsputil_yasm.asm index 099f0a80df..b1b37e1fb9 100644 --- a/libavcodec/x86/dsputil_yasm.asm +++ b/libavcodec/x86/dsputil_yasm.asm @@ -30,75 +30,6 @@ pb_zz11zz55zz99zzdd: db -1,-1,1,1,-1,-1,5,5,-1,-1,9,9,-1,-1,13,13 section .text align=16 -%macro PSWAPD_SSE 2 - pshufw %1, %2, 0x4e -%endmacro -%macro PSWAPD_3DN1 2 - movq %1, %2 - psrlq %1, 32 - punpckldq %1, %2 -%endmacro - -%macro FLOAT_TO_INT16_INTERLEAVE6 1 -; void float_to_int16_interleave6_sse(int16_t *dst, const float **src, int len) -cglobal float_to_int16_interleave6_%1, 2,7,0, dst, src, src1, src2, src3, src4, src5 -%ifdef ARCH_X86_64 - %define lend r10d - mov lend, r2d -%else - %define lend dword r2m -%endif - mov src1q, [srcq+1*gprsize] - mov src2q, [srcq+2*gprsize] - mov src3q, [srcq+3*gprsize] - mov src4q, [srcq+4*gprsize] - mov src5q, [srcq+5*gprsize] - mov srcq, [srcq] - sub src1q, srcq - sub src2q, srcq - sub src3q, srcq - sub src4q, srcq - sub src5q, srcq -.loop: - cvtps2pi mm0, [srcq] - cvtps2pi mm1, [srcq+src1q] - cvtps2pi mm2, [srcq+src2q] - cvtps2pi mm3, [srcq+src3q] - cvtps2pi mm4, [srcq+src4q] - cvtps2pi mm5, [srcq+src5q] - packssdw mm0, mm3 - packssdw mm1, mm4 - packssdw mm2, mm5 - pswapd mm3, mm0 - punpcklwd mm0, mm1 - punpckhwd mm1, mm2 - punpcklwd mm2, mm3 - pswapd mm3, mm0 - punpckldq mm0, mm2 - punpckhdq mm2, mm1 - punpckldq mm1, mm3 - movq [dstq ], mm0 - movq [dstq+16], mm2 - movq [dstq+ 8], mm1 - add srcq, 8 - add dstq, 24 - sub lend, 2 - jg .loop - emms - RET -%endmacro ; FLOAT_TO_INT16_INTERLEAVE6 - -%define pswapd PSWAPD_SSE -FLOAT_TO_INT16_INTERLEAVE6 sse -%define cvtps2pi pf2id -%define pswapd PSWAPD_3DN1 -FLOAT_TO_INT16_INTERLEAVE6 3dnow -%undef pswapd -FLOAT_TO_INT16_INTERLEAVE6 3dn2 -%undef cvtps2pi - - - %macro SCALARPRODUCT 1 ; int scalarproduct_int16(int16_t *v1, int16_t *v2, int order, int shift) cglobal scalarproduct_int16_%1, 3,3,4, v1, v2, order, shift |