c6963a220d
* qatar/master: proresdsp: port x86 assembly to cpuflags. lavr: x86: improve non-SSE4 version of S16_TO_S32_SX macro lavfi: better channel layout negotiation alac: check for truncated packets alac: reverse lpc coeff order, simplify filter lavr: add x86-optimized mixing functions x86: add support for fmaddps fma4 instruction with abstraction to avx/sse tscc2: fix typo in array index build: use COMPILE template for HOSTOBJS build: do full flag handling for all compiler-type tools eval: fix printing of NaN in eval fate test. build: Rename aandct component to more descriptive aandcttables mpegaudio: bury inline asm under HAVE_INLINE_ASM. x86inc: automatically insert vzeroupper for YMM functions. rtmp: Check the buffer length of ping packets rtmp: Allow having more unknown data at the end of a chunk size packet without failing rtmp: Prevent reading outside of an allocate buffer when receiving server bandwidth packets Conflicts: Makefile configure libavcodec/x86/proresdsp.asm libavutil/eval.c Merged-by: Michael Niedermayer <michaelni@gmx.at>
95 lines
2.7 KiB
NASM
95 lines
2.7 KiB
NASM
;*****************************************************************************
|
|
;* x86-optimized Float DSP functions
|
|
;*
|
|
;* Copyright 2006 Loren Merritt
|
|
;*
|
|
;* This file is part of FFmpeg.
|
|
;*
|
|
;* FFmpeg 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.
|
|
;*
|
|
;* FFmpeg 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 FFmpeg; if not, write to the Free Software
|
|
;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
;******************************************************************************
|
|
|
|
%include "x86inc.asm"
|
|
%include "x86util.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
|
|
REP_RET
|
|
%endmacro
|
|
|
|
INIT_XMM sse
|
|
VECTOR_FMUL
|
|
%if HAVE_AVX
|
|
INIT_YMM avx
|
|
VECTOR_FMUL
|
|
%endif
|
|
|
|
;------------------------------------------------------------------------------
|
|
; void ff_vector_fmac_scalar(float *dst, const float *src, float mul, int len)
|
|
;------------------------------------------------------------------------------
|
|
|
|
%macro VECTOR_FMAC_SCALAR 0
|
|
%if UNIX64
|
|
cglobal vector_fmac_scalar, 3,3,3, dst, src, len
|
|
%else
|
|
cglobal vector_fmac_scalar, 4,4,3, dst, src, mul, len
|
|
%endif
|
|
%if WIN64
|
|
SWAP 0, 2
|
|
%endif
|
|
%if ARCH_X86_32
|
|
VBROADCASTSS m0, mulm
|
|
%else
|
|
shufps xmm0, xmm0, 0
|
|
%if cpuflag(avx)
|
|
vinsertf128 m0, m0, xmm0, 1
|
|
%endif
|
|
%endif
|
|
lea lenq, [lend*4-2*mmsize]
|
|
.loop
|
|
mulps m1, m0, [srcq+lenq ]
|
|
mulps m2, m0, [srcq+lenq+mmsize]
|
|
addps m1, m1, [dstq+lenq ]
|
|
addps m2, m2, [dstq+lenq+mmsize]
|
|
mova [dstq+lenq ], m1
|
|
mova [dstq+lenq+mmsize], m2
|
|
sub lenq, 2*mmsize
|
|
jge .loop
|
|
REP_RET
|
|
%endmacro
|
|
|
|
INIT_XMM sse
|
|
VECTOR_FMAC_SCALAR
|
|
%if HAVE_AVX
|
|
INIT_YMM avx
|
|
VECTOR_FMAC_SCALAR
|
|
%endif
|