mc-a-common.S
2.16 KB
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
/****************************************************************************
* mc-a-common.S: aarch64 motion compensation
*****************************************************************************
* Copyright (C) 2009-2024 x264 project
*
* Authors: David Conrad <lessen42@gmail.com>
* Janne Grunau <janne-x264@jannau.net>
* Mans Rullgard <mans@mansr.com>
* Stefan Groenroos <stefan.gronroos@gmail.com>
* David Chen <david.chen@myais.com.cn>
*
* This program 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.
*
* This program 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 this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at licensing@x264.com.
*****************************************************************************/
// This file contains the NEON macros and functions that are intended to be used by
// the SVE/SVE2 functions as well
#if BIT_DEPTH == 8
// 0 < weight < 64
.macro load_weights_add_add
mov w6, w6
.endm
// weight > 64
.macro load_weights_add_sub
neg w7, w7
.endm
// weight < 0
.macro load_weights_sub_add
neg w6, w6
.endm
function pixel_avg_w4_neon
1: subs w9, w9, #2
ld1 {v0.s}[0], [x2], x3
ld1 {v2.s}[0], [x4], x5
urhadd v0.8b, v0.8b, v2.8b
ld1 {v1.s}[0], [x2], x3
ld1 {v3.s}[0], [x4], x5
urhadd v1.8b, v1.8b, v3.8b
st1 {v0.s}[0], [x0], x1
st1 {v1.s}[0], [x0], x1
b.gt 1b
ret
endfunc
#else // BIT_DEPTH == 10
#endif