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
|
;*****************************************************************************
;* x86-optimized functions for maskedmerge filter
;*
;* Copyright (C) 2015 Paul B Mahol
;*
;* 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"
%if ARCH_X86_64
SECTION_RODATA
pw_128: times 8 dw 128
pw_256: times 8 dw 256
SECTION .text
INIT_XMM sse2
cglobal maskedmerge8, 10, 11, 7, 0, bsrc, osrc, msrc, dst, blinesize, olinesize, mlinesize, dlinesize, w, h
mova m4, [pw_256]
mova m5, [pw_128]
pxor m6, m6
add bsrcq, wq
add osrcq, wq
add msrcq, wq
add dstq, wq
neg wq
.nextrow:
mov r10q, wq
%define x r10q
.loop:
movh m0, [bsrcq + x]
movh m1, [osrcq + x]
movh m3, [msrcq + x]
mova m2, m4
punpcklbw m0, m6
punpcklbw m1, m6
punpcklbw m3, m6
psubw m2, m3
pmullw m2, m0
pmullw m1, m3
paddw m1, m2
paddw m1, m5
psrlw m1, 8
packuswb m1, m1
movh [dstq + x], m1
add r10q, mmsize / 2
jl .loop
add bsrcq, blinesizeq
add osrcq, olinesizeq
add msrcq, mlinesizeq
add dstq, dlinesizeq
sub hd, 1
jg .nextrow
REP_RET
%endif
|
