1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
;******************************************************************************
;* 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
|
