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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
|
;*****************************************************************************
;* x86-optimized functions for yadif filter
;*
;* Copyright (C) 2006 Michael Niedermayer <michaelni@gmx.at>
;* Copyright (c) 2013 Daniel Kang <daniel.d.kang@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 General Public License as published by
;* the Free Software Foundation; either version 2 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 General Public License for more details.
;*
;* You should have received a copy of the GNU 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 "libavutil/x86/x86util.asm"
SECTION_RODATA
pb_1: times 16 db 1
pw_1: times 8 dw 1
SECTION .text
%macro CHECK 2
movu m2, [curq+mrefsq+%1]
movu m3, [curq+prefsq+%2]
mova m4, m2
mova m5, m2
pxor m4, m3
pavgb m5, m3
pand m4, [pb_1]
psubusb m5, m4
%if mmsize == 16
psrldq m5, 1
%else
psrlq m5, 8
%endif
punpcklbw m5, m7
mova m4, m2
psubusb m2, m3
psubusb m3, m4
pmaxub m2, m3
mova m3, m2
mova m4, m2
%if mmsize == 16
psrldq m3, 1
psrldq m4, 2
%else
psrlq m3, 8
psrlq m4, 16
%endif
punpcklbw m2, m7
punpcklbw m3, m7
punpcklbw m4, m7
paddw m2, m3
paddw m2, m4
%endmacro
%macro CHECK1 0
mova m3, m0
pcmpgtw m3, m2
pminsw m0, m2
mova m6, m3
pand m5, m3
pandn m3, m1
por m3, m5
mova m1, m3
%endmacro
%macro CHECK2 0
paddw m6, [pw_1]
psllw m6, 14
paddsw m2, m6
mova m3, m0
pcmpgtw m3, m2
pminsw m0, m2
pand m5, m3
pandn m3, m1
por m3, m5
mova m1, m3
%endmacro
%macro LOAD 2
movh m%1, %2
punpcklbw m%1, m7
%endmacro
%macro FILTER 3
.loop%1:
pxor m7, m7
LOAD 0, [curq+mrefsq]
LOAD 1, [curq+prefsq]
LOAD 2, [%2]
LOAD 3, [%3]
mova m4, m3
paddw m3, m2
psraw m3, 1
mova [rsp+ 0], m0
mova [rsp+16], m3
mova [rsp+32], m1
psubw m2, m4
ABS1 m2, m4
LOAD 3, [prevq+mrefsq]
LOAD 4, [prevq+prefsq]
psubw m3, m0
psubw m4, m1
ABS1 m3, m5
ABS1 m4, m5
paddw m3, m4
psrlw m2, 1
psrlw m3, 1
pmaxsw m2, m3
LOAD 3, [nextq+mrefsq]
LOAD 4, [nextq+prefsq]
psubw m3, m0
psubw m4, m1
ABS1 m3, m5
ABS1 m4, m5
paddw m3, m4
psrlw m3, 1
pmaxsw m2, m3
mova [rsp+48], m2
paddw m1, m0
paddw m0, m0
psubw m0, m1
psrlw m1, 1
ABS1 m0, m2
movu m2, [curq+mrefsq-1]
movu m3, [curq+prefsq-1]
mova m4, m2
psubusb m2, m3
psubusb m3, m4
pmaxub m2, m3
%if mmsize == 16
mova m3, m2
psrldq m3, 2
%else
pshufw m3, m2, q0021
%endif
punpcklbw m2, m7
punpcklbw m3, m7
paddw m0, m2
paddw m0, m3
psubw m0, [pw_1]
CHECK -2, 0
CHECK1
CHECK -3, 1
CHECK2
CHECK 0, -2
CHECK1
CHECK 1, -3
CHECK2
mova m6, [rsp+48]
cmp DWORD modem, 2
jge .end%1
LOAD 2, [%2+mrefsq*2]
LOAD 4, [%3+mrefsq*2]
LOAD 3, [%2+prefsq*2]
LOAD 5, [%3+prefsq*2]
paddw m2, m4
paddw m3, m5
psrlw m2, 1
psrlw m3, 1
mova m4, [rsp+ 0]
mova m5, [rsp+16]
mova m7, [rsp+32]
psubw m2, m4
psubw m3, m7
mova m0, m5
psubw m5, m4
psubw m0, m7
mova m4, m2
pminsw m2, m3
pmaxsw m3, m4
pmaxsw m2, m5
pminsw m3, m5
pmaxsw m2, m0
pminsw m3, m0
pxor m4, m4
pmaxsw m6, m3
psubw m4, m2
pmaxsw m6, m4
.end%1:
mova m2, [rsp+16]
mova m3, m2
psubw m2, m6
paddw m3, m6
pmaxsw m1, m2
pminsw m1, m3
packuswb m1, m1
movh [dstq], m1
add dstq, mmsize/2
add prevq, mmsize/2
add curq, mmsize/2
add nextq, mmsize/2
sub wd, mmsize/2
jg .loop%1
%endmacro
%macro YADIF 0
cglobal yadif_filter_line, 7, 7, 8, 16*5, dst, prev, cur, next, w, prefs, \
mrefs, parity, mode
test wq, wq
jle .ret
movsxdifnidn prefsq, prefsd
movsxdifnidn mrefsq, mrefsd
cmp DWORD paritym, 0
je .parity0
FILTER 1, prevq, curq
jmp .ret
.parity0:
FILTER 0, curq, nextq
.ret:
RET
%endmacro
INIT_XMM ssse3
YADIF
INIT_XMM sse2
YADIF
%if ARCH_X86_32
INIT_MMX mmxext
YADIF
%endif
|
