diff options
| author | Justin Ruggles <justin.ruggles@gmail.com> | 2012-05-21 12:58:41 -0400 |
|---|---|---|
| committer | Justin Ruggles <justin.ruggles@gmail.com> | 2012-06-08 13:14:38 -0400 |
| commit | d5a7229ba4aabc2b6407c731d9175879ae54c5ea (patch) | |
| tree | 0596aaae9622f0f7b7e5d689b20ab3dc82f59897 /libavutil/x86/float_dsp.asm | |
| parent | 98db4e2a4e35ccc2406004216270ceaa1c6a7d00 (diff) | |
| download | ffmpeg-d5a7229ba4aabc2b6407c731d9175879ae54c5ea.tar.gz | |
Add a float DSP framework to libavutil
Move vector_fmul() from DSPContext to AVFloatDSPContext.
Diffstat (limited to 'libavutil/x86/float_dsp.asm')
| -rw-r--r-- | libavutil/x86/float_dsp.asm | 55 |
1 files changed, 55 insertions, 0 deletions
diff --git a/libavutil/x86/float_dsp.asm b/libavutil/x86/float_dsp.asm new file mode 100644 index 0000000000..53be7ab99a --- /dev/null +++ b/libavutil/x86/float_dsp.asm @@ -0,0 +1,55 @@ +;***************************************************************************** +;* x86-optimized Float DSP functions +;* +;* This file is part of Libav. +;* +;* Libav is free software; you can redistribute it and/or +;* modify it under the terms of the GNU Lesser General Public +;* License as published by the Free Software Foundation; either +;* version 2.1 of the License, or (at your option) any later version. +;* +;* Libav is distributed in the hope that it will be useful, +;* but WITHOUT ANY WARRANTY; without even the implied warranty of +;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +;* Lesser General Public License for more details. +;* +;* You should have received a copy of the GNU Lesser General Public +;* License along with Libav; if not, write to the Free Software +;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA +;****************************************************************************** + +%include "x86inc.asm" + +SECTION .text + +;----------------------------------------------------------------------------- +; void vector_fmul(float *dst, const float *src0, const float *src1, int len) +;----------------------------------------------------------------------------- +%macro VECTOR_FMUL 0 +cglobal vector_fmul, 4,4,2, dst, src0, src1, len + lea lenq, [lend*4 - 2*mmsize] +ALIGN 16 +.loop + mova m0, [src0q + lenq] + mova m1, [src0q + lenq + mmsize] + mulps m0, m0, [src1q + lenq] + mulps m1, m1, [src1q + lenq + mmsize] + mova [dstq + lenq], m0 + mova [dstq + lenq + mmsize], m1 + + sub lenq, 2*mmsize + jge .loop +%if mmsize == 32 + vzeroupper + RET +%else + REP_RET +%endif +%endmacro + +INIT_XMM sse +VECTOR_FMUL +%if HAVE_AVX +INIT_YMM avx +VECTOR_FMUL +%endif |