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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
;******************************************************************************
;* x86 optimized Format Conversion Utils
;* Copyright (c) 2008 Loren Merritt
;* Copyright (c) 2012 Justin Ruggles <justin.ruggles@gmail.com>
;*
;* 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"
%include "x86util.asm"
SECTION_TEXT
;------------------------------------------------------------------------------
; void ff_conv_s16_to_s32(int32_t *dst, const int16_t *src, int len);
;------------------------------------------------------------------------------
INIT_XMM sse2
cglobal conv_s16_to_s32, 3,3,3, dst, src, len
lea lenq, [2*lend]
lea dstq, [dstq+2*lenq]
add srcq, lenq
neg lenq
.loop:
mova m2, [srcq+lenq]
pxor m0, m0
pxor m1, m1
punpcklwd m0, m2
punpckhwd m1, m2
mova [dstq+2*lenq ], m0
mova [dstq+2*lenq+mmsize], m1
add lenq, mmsize
jl .loop
REP_RET
;-----------------------------------------------------------------------------
; void ff_conv_fltp_to_flt_6ch(float *dst, float *const *src, int len,
; int channels);
;-----------------------------------------------------------------------------
%macro CONV_FLTP_TO_FLT_6CH 0
cglobal conv_fltp_to_flt_6ch, 2,8,7, dst, src, src1, src2, src3, src4, src5, len
%if ARCH_X86_64
mov lend, r2d
%else
%define lend dword r2m
%endif
mov src1q, [srcq+1*gprsize]
mov src2q, [srcq+2*gprsize]
mov src3q, [srcq+3*gprsize]
mov src4q, [srcq+4*gprsize]
mov src5q, [srcq+5*gprsize]
mov srcq, [srcq]
sub src1q, srcq
sub src2q, srcq
sub src3q, srcq
sub src4q, srcq
sub src5q, srcq
.loop:
mova m0, [srcq ]
mova m1, [srcq+src1q]
mova m2, [srcq+src2q]
mova m3, [srcq+src3q]
mova m4, [srcq+src4q]
mova m5, [srcq+src5q]
%if cpuflag(sse4)
SBUTTERFLYPS 0, 1, 6
SBUTTERFLYPS 2, 3, 6
SBUTTERFLYPS 4, 5, 6
blendps m6, m4, m0, 1100b
movlhps m0, m2
movhlps m4, m2
blendps m2, m5, m1, 1100b
movlhps m1, m3
movhlps m5, m3
movaps [dstq ], m0
movaps [dstq+16], m6
movaps [dstq+32], m4
movaps [dstq+48], m1
movaps [dstq+64], m2
movaps [dstq+80], m5
%else ; mmx
SBUTTERFLY dq, 0, 1, 6
SBUTTERFLY dq, 2, 3, 6
SBUTTERFLY dq, 4, 5, 6
movq [dstq ], m0
movq [dstq+ 8], m2
movq [dstq+16], m4
movq [dstq+24], m1
movq [dstq+32], m3
movq [dstq+40], m5
%endif
add srcq, mmsize
add dstq, mmsize*6
sub lend, mmsize/4
jg .loop
%if mmsize == 8
emms
RET
%else
REP_RET
%endif
%endmacro
INIT_MMX mmx
CONV_FLTP_TO_FLT_6CH
INIT_XMM sse4
CONV_FLTP_TO_FLT_6CH
%if HAVE_AVX
INIT_XMM avx
CONV_FLTP_TO_FLT_6CH
%endif
|
