1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-12 19:18:44 +02:00
FFmpeg/libavresample/x86/dither.asm
Michael Niedermayer 75afbe2ab4 Merge commit '1fb8f6a44f06e48386450fe0363aefc02583d24a'
* commit '1fb8f6a44f06e48386450fe0363aefc02583d24a':
  x86: lavr: add SSE2 quantize() for dithering
  doc/APIchanges: fill in missing dates and hashes.
  rtpdec_vp8: Request a keyframe if RTP packets are lost

Conflicts:
	doc/APIchanges

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-01-09 12:14:56 +01:00

54 lines
1.9 KiB
NASM

;******************************************************************************
;* x86 optimized dithering format conversion
;* Copyright (c) 2012 Justin Ruggles <justin.ruggles@gmail.com>
;*
;* 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 "libavutil/x86/x86util.asm"
SECTION_RODATA 32
pf_s16_scale: times 4 dd 32753.0
SECTION_TEXT
;------------------------------------------------------------------------------
; void ff_quantize(int16_t *dst, float *src, float *dither, int len);
;------------------------------------------------------------------------------
INIT_XMM sse2
cglobal quantize, 4,4,3, dst, src, dither, len
lea lenq, [2*lend]
add dstq, lenq
lea srcq, [srcq+2*lenq]
lea ditherq, [ditherq+2*lenq]
neg lenq
mova m2, [pf_s16_scale]
.loop:
mulps m0, m2, [srcq+2*lenq]
mulps m1, m2, [srcq+2*lenq+mmsize]
addps m0, [ditherq+2*lenq]
addps m1, [ditherq+2*lenq+mmsize]
cvtps2dq m0, m0
cvtps2dq m1, m1
packssdw m0, m1
mova [dstq+lenq], m0
add lenq, mmsize
jl .loop
REP_RET