aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/x86/hpeldsp_vp3.asm
blob: cba96d06cb7c7d660dacf444fce967d781a70942 (plain) (blame)
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
;******************************************************************************
;* SIMD-optimized halfpel functions for VP3
;*
;* 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 .text

; void ff_put_no_rnd_pixels8_x2_exact(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_NO_RND_PIXELS8_X2_EXACT 0
cglobal put_no_rnd_pixels8_x2_exact, 4,5
    lea          r4, [r2*3]
    pcmpeqb      m6, m6
.loop:
    mova         m0, [r1]
    mova         m2, [r1+r2]
    mova         m1, [r1+1]
    mova         m3, [r1+r2+1]
    pxor         m0, m6
    pxor         m2, m6
    pxor         m1, m6
    pxor         m3, m6
    PAVGB        m0, m1
    PAVGB        m2, m3
    pxor         m0, m6
    pxor         m2, m6
    mova       [r0], m0
    mova    [r0+r2], m2
    mova         m0, [r1+r2*2]
    mova         m1, [r1+r2*2+1]
    mova         m2, [r1+r4]
    mova         m3, [r1+r4+1]
    pxor         m0, m6
    pxor         m1, m6
    pxor         m2, m6
    pxor         m3, m6
    PAVGB        m0, m1
    PAVGB        m2, m3
    pxor         m0, m6
    pxor         m2, m6
    mova  [r0+r2*2], m0
    mova    [r0+r4], m2
    lea          r1, [r1+r2*4]
    lea          r0, [r0+r2*4]
    sub         r3d, 4
    jg .loop
    REP_RET
%endmacro

INIT_MMX mmxext
PUT_NO_RND_PIXELS8_X2_EXACT
INIT_MMX 3dnow
PUT_NO_RND_PIXELS8_X2_EXACT


; void ff_put_no_rnd_pixels8_y2_exact(uint8_t *block, const uint8_t *pixels, ptrdiff_t line_size, int h)
%macro PUT_NO_RND_PIXELS8_Y2_EXACT 0
cglobal put_no_rnd_pixels8_y2_exact, 4,5
    lea          r4, [r2*3]
    mova         m0, [r1]
    pcmpeqb      m6, m6
    add          r1, r2
    pxor         m0, m6
.loop:
    mova         m1, [r1]
    mova         m2, [r1+r2]
    pxor         m1, m6
    pxor         m2, m6
    PAVGB        m0, m1
    PAVGB        m1, m2
    pxor         m0, m6
    pxor         m1, m6
    mova       [r0], m0
    mova    [r0+r2], m1
    mova         m1, [r1+r2*2]
    mova         m0, [r1+r4]
    pxor         m1, m6
    pxor         m0, m6
    PAVGB        m2, m1
    PAVGB        m1, m0
    pxor         m2, m6
    pxor         m1, m6
    mova  [r0+r2*2], m2
    mova    [r0+r4], m1
    lea          r1, [r1+r2*4]
    lea          r0, [r0+r2*4]
    sub         r3d, 4
    jg .loop
    REP_RET
%endmacro

INIT_MMX mmxext
PUT_NO_RND_PIXELS8_Y2_EXACT
INIT_MMX 3dnow
PUT_NO_RND_PIXELS8_Y2_EXACT