blob: 3063acbb3e3fa73d4092cdcdbd4d51392b56328e (
plain)
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
|
/*
* Copyright (c) 2023 The WebM project authors. All Rights Reserved.
*
* Use of this source code is governed by a BSD-style license
* that can be found in the LICENSE file in the root of the source
* tree. An additional intellectual property rights grant can be found
* in the file PATENTS. All contributing project authors may
* be found in the AUTHORS file in the root of the source tree.
*/
#include <arm_neon.h>
#include <assert.h>
#include "./vpx_dsp_rtcd.h"
#include "./vpx_config.h"
void vpx_highbd_comp_avg_pred_neon(uint16_t *comp_pred, const uint16_t *pred,
int width, int height, const uint16_t *ref,
int ref_stride) {
int i = height;
if (width > 8) {
do {
int j = 0;
do {
const uint16x8_t p = vld1q_u16(pred + j);
const uint16x8_t r = vld1q_u16(ref + j);
uint16x8_t avg = vrhaddq_u16(p, r);
vst1q_u16(comp_pred + j, avg);
j += 8;
} while (j < width);
comp_pred += width;
pred += width;
ref += ref_stride;
} while (--i != 0);
} else if (width == 8) {
do {
const uint16x8_t p = vld1q_u16(pred);
const uint16x8_t r = vld1q_u16(ref);
uint16x8_t avg = vrhaddq_u16(p, r);
vst1q_u16(comp_pred, avg);
comp_pred += width;
pred += width;
ref += ref_stride;
} while (--i != 0);
} else {
assert(width == 4);
do {
const uint16x4_t p = vld1_u16(pred);
const uint16x4_t r = vld1_u16(ref);
uint16x4_t avg = vrhadd_u16(p, r);
vst1_u16(comp_pred, avg);
comp_pred += width;
pred += width;
ref += ref_stride;
} while (--i != 0);
}
}
|
