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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
|
;******************************************************************************
;* Vorbis x86 optimizations
;* Copyright (C) 2006 Loren Merritt <lorenm@u.washington.edu>
;*
;* 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
pdw_80000000: times 4 dd 0x80000000
SECTION .text
%if ARCH_X86_32
INIT_MMX 3dnow
cglobal vorbis_inverse_coupling, 3, 3, 6, mag, ang, block_size
pxor m7, m7
lea magq, [magq+block_sizeq*4]
lea angq, [angq+block_sizeq*4]
neg block_sizeq
.loop:
mova m0, [magq+block_sizeq*4]
mova m1, [angq+block_sizeq*4]
mova m2, m0
mova m3, m1
pfcmpge m2, m7 ; m <= 0.0
pfcmpge m3, m7 ; a <= 0.0
pslld m2, 31 ; keep only the sign bit
pxor m1, m2
mova m4, m3
pand m3, m1
pandn m4, m1
pfadd m3, m0 ; a = m + ((a < 0) & (a ^ sign(m)))
pfsub m0, m4 ; m = m + ((a > 0) & (a ^ sign(m)))
mova [angq+block_sizeq*4], m3
mova [magq+block_sizeq*4], m0
add block_sizeq, 2
jl .loop
femms
RET
%endif
INIT_XMM sse
cglobal vorbis_inverse_coupling, 3, 4, 6, mag, ang, block_size, cntr
mova m5, [pdw_80000000]
xor cntrq, cntrq
align 16
.loop:
mova m0, [magq+cntrq*4]
mova m1, [angq+cntrq*4]
xorps m2, m2
xorps m3, m3
cmpleps m2, m0 ; m <= 0.0
cmpleps m3, m1 ; a <= 0.0
andps m2, m5 ; keep only the sign bit
xorps m1, m2
mova m4, m3
andps m3, m1
andnps m4, m1
addps m3, m0 ; a = m + ((a < 0) & (a ^ sign(m)))
subps m0, m4 ; m = m + ((a > 0) & (a ^ sign(m)))
mova [angq+cntrq*4], m3
mova [magq+cntrq*4], m0
add cntrq, 4
cmp cntrq, block_sizeq
jl .loop
RET
|
