aac5773f
 hucm
功能基本完成，接口待打磨
|
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
|
;******************************************************************************
;* optimized bswap buffer functions
;* Copyright (c) 2008 Loren Merritt
;* Copyright (c) 2003-2013 Michael Niedermayer
;* Copyright (c) 2013 Daniel Kang
;*
;* 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
pb_bswap32: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
cextern pb_80
SECTION .text
; %1 = aligned/unaligned
%macro BSWAP_LOOPS 1
mov r3d, r2d
sar r2d, 3
jz .left4_%1
%if cpuflag(avx2)
sar r2d, 1
jz .left8_%1
%endif
.loop8_%1:
mov%1 m0, [r1 + 0]
mov%1 m1, [r1 + mmsize]
%if cpuflag(ssse3)||cpuflag(avx2)
pshufb m0, m2
pshufb m1, m2
mov%1 [r0 + 0], m0
mov%1 [r0 + mmsize], m1
%else
pshuflw m0, m0, 10110001b
pshuflw m1, m1, 10110001b
pshufhw m0, m0, 10110001b
pshufhw m1, m1, 10110001b
mova m2, m0
mova m3, m1
psllw m0, 8
psllw m1, 8
psrlw m2, 8
psrlw m3, 8
por m2, m0
por m3, m1
mov%1 [r0 + 0], m2
mov%1 [r0 + 16], m3
%endif
add r0, mmsize*2
add r1, mmsize*2
dec r2d
jnz .loop8_%1
%if cpuflag(avx2)
.left8_%1:
mov r2d, r3d
test r3d, 8
jz .left4_%1
mov%1 m0, [r1]
pshufb m0, m2
mov%1 [r0 + 0], m0
add r1, mmsize
add r0, mmsize
%endif
.left4_%1:
mov r2d, r3d
test r3d, 4
jz .left
mov%1 xm0, [r1]
%if cpuflag(ssse3)
pshufb xm0, xm2
mov%1 [r0], xm0
%else
pshuflw m0, m0, 10110001b
pshufhw m0, m0, 10110001b
mova m2, m0
psllw m0, 8
psrlw m2, 8
por m2, m0
mov%1 [r0], m2
%endif
add r1, 16
add r0, 16
%endmacro
; void ff_bswap_buf(uint32_t *dst, const uint32_t *src, int w);
%macro BSWAP32_BUF 0
%if cpuflag(ssse3)||cpuflag(avx2)
cglobal bswap32_buf, 3,4,3
mov r3, r1
VBROADCASTI128 m2, [pb_bswap32]
%else
cglobal bswap32_buf, 3,4,5
mov r3, r1
%endif
or r3, r0
test r3, mmsize - 1
jz .start_align
BSWAP_LOOPS u
jmp .left
.start_align:
BSWAP_LOOPS a
.left:
%if cpuflag(ssse3)
test r2d, 2
jz .left1
movq xm0, [r1]
pshufb xm0, xm2
movq [r0], xm0
add r1, 8
add r0, 8
.left1:
test r2d, 1
jz .end
mov r2d, [r1]
bswap r2d
mov [r0], r2d
%else
and r2d, 3
jz .end
.loop2:
mov r3d, [r1]
bswap r3d
mov [r0], r3d
add r1, 4
add r0, 4
dec r2d
jnz .loop2
%endif
.end:
RET
%endmacro
INIT_XMM sse2
BSWAP32_BUF
INIT_XMM ssse3
BSWAP32_BUF
%if HAVE_AVX2_EXTERNAL
INIT_YMM avx2
BSWAP32_BUF
%endif
|
