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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
|
;*****************************************************************************
;* x86-optimized functions for pullup filter
;*
;* This file is part of FFmpeg.
;*
;* FFmpeg is free software; you can redistribute it and/or modify
;* it under the terms of the GNU General Public License as published by
;* the Free Software Foundation; either version 2 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 General Public License for more details.
;*
;* You should have received a copy of the GNU 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_TEXT
INIT_MMX mmx
cglobal pullup_filter_diff, 3, 5, 8, first, second, size
mov r3, 4
pxor m4, m4
pxor m7, m7
.loop:
movq m0, [firstq]
movq m2, [firstq]
add firstq, sizeq
movq m1, [secondq]
add secondq, sizeq
psubusb m2, m1
psubusb m1, m0
movq m0, m2
movq m3, m1
punpcklbw m0, m7
punpcklbw m1, m7
punpckhbw m2, m7
punpckhbw m3, m7
paddw m4, m0
paddw m4, m1
paddw m4, m2
paddw m4, m3
dec r3
jnz .loop
movq m3, m4
punpcklwd m4, m7
punpckhwd m3, m7
paddd m3, m4
movd eax, m3
psrlq m3, 32
movd r4, m3
add eax, r4d
RET
INIT_MMX mmx
cglobal pullup_filter_comb, 3, 5, 8, first, second, size
mov r3, 4
pxor m6, m6
pxor m7, m7
sub secondq, sizeq
.loop:
movq m0, [secondq]
movq m1, [secondq]
punpcklbw m0, m7
movq m2, [secondq+sizeq]
punpcklbw m1, m7
punpcklbw m2, m7
paddw m0, m0
paddw m1, m2
movq m2, m0
psubusw m0, m1
psubusw m1, m2
paddw m6, m0
paddw m6, m1
movq m0, [firstq]
movq m1, [secondq]
punpckhbw m0, m7
movq m2, [secondq+sizeq]
punpckhbw m1, m7
punpckhbw m2, m7
paddw m0, m0
paddw m1, m2
movq m2, m0
psubusw m0, m1
psubusw m1, m2
paddw m6, m0
paddw m6, m1
movq m0, [secondq+sizeq]
movq m1, [firstq]
punpcklbw m0, m7
movq m2, [firstq+sizeq]
punpcklbw m1, m7
punpcklbw m2, m7
paddw m0, m0
paddw m1, m2
movq m2, m0
psubusw m0, m1
psubusw m1, m2
paddw m6, m0
paddw m6, m1
movq m0, [secondq+sizeq]
movq m1, [firstq]
punpckhbw m0, m7
movq m2, [firstq+sizeq]
punpckhbw m1, m7
punpckhbw m2, m7
paddw m0, m0
paddw m1, m2
movq m2, m0
psubusw m0, m1
psubusw m1, m2
paddw m6, m0
paddw m6, m1
add firstq, sizeq
add secondq, sizeq
dec r3
jnz .loop
movq m5, m6
punpcklwd m6, m7
punpckhwd m5, m7
paddd m5, m6
movd eax, m5
psrlq m5, 32
movd r4, m5
add eax, r4d
RET
INIT_MMX mmx
cglobal pullup_filter_var, 3, 5, 8, first, second, size
mov r3, 3
pxor m4, m4
pxor m7, m7
.loop:
movq m0, [firstq]
movq m2, [firstq]
movq m1, [firstq+sizeq]
add firstq, sizeq
psubusb m2, m1
psubusb m1, m0
movq m0, m2
movq m3, m1
punpcklbw m0, m7
punpcklbw m1, m7
punpckhbw m2, m7
punpckhbw m3, m7
paddw m4, m0
paddw m4, m1
paddw m4, m2
paddw m4, m3
dec r3
jnz .loop
movq m3, m4
punpcklwd m4, m7
punpckhwd m3, m7
paddd m3, m4
movd eax, m3
psrlq m3, 32
movd r4, m3
add eax, r4d
shl eax, 2
RET
|
