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
|
/*
* Copyright (c) 2017 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 "./vp8_rtcd.h"
#include "vpx_ports/asmdefs_mmi.h"
#define COPY_MEM_16X2 \
"gsldlc1 %[ftmp0], 0x07(%[src]) \n\t" \
"gsldrc1 %[ftmp0], 0x00(%[src]) \n\t" \
"ldl %[tmp0], 0x0f(%[src]) \n\t" \
"ldr %[tmp0], 0x08(%[src]) \n\t" \
MMI_ADDU(%[src], %[src], %[src_stride]) \
"gssdlc1 %[ftmp0], 0x07(%[dst]) \n\t" \
"gssdrc1 %[ftmp0], 0x00(%[dst]) \n\t" \
"sdl %[tmp0], 0x0f(%[dst]) \n\t" \
"sdr %[tmp0], 0x08(%[dst]) \n\t" \
MMI_ADDU(%[dst], %[dst], %[dst_stride]) \
"gsldlc1 %[ftmp1], 0x07(%[src]) \n\t" \
"gsldrc1 %[ftmp1], 0x00(%[src]) \n\t" \
"ldl %[tmp1], 0x0f(%[src]) \n\t" \
"ldr %[tmp1], 0x08(%[src]) \n\t" \
MMI_ADDU(%[src], %[src], %[src_stride]) \
"gssdlc1 %[ftmp1], 0x07(%[dst]) \n\t" \
"gssdrc1 %[ftmp1], 0x00(%[dst]) \n\t" \
"sdl %[tmp1], 0x0f(%[dst]) \n\t" \
"sdr %[tmp1], 0x08(%[dst]) \n\t" \
MMI_ADDU(%[dst], %[dst], %[dst_stride])
#define COPY_MEM_8X2 \
"gsldlc1 %[ftmp0], 0x07(%[src]) \n\t" \
"gsldrc1 %[ftmp0], 0x00(%[src]) \n\t" \
MMI_ADDU(%[src], %[src], %[src_stride]) \
"ldl %[tmp0], 0x07(%[src]) \n\t" \
"ldr %[tmp0], 0x00(%[src]) \n\t" \
MMI_ADDU(%[src], %[src], %[src_stride]) \
\
"gssdlc1 %[ftmp0], 0x07(%[dst]) \n\t" \
"gssdrc1 %[ftmp0], 0x00(%[dst]) \n\t" \
MMI_ADDU(%[dst], %[dst], %[dst_stride]) \
"sdl %[tmp0], 0x07(%[dst]) \n\t" \
"sdr %[tmp0], 0x00(%[dst]) \n\t" \
MMI_ADDU(%[dst], %[dst], %[dst_stride])
void vp8_copy_mem16x16_mmi(unsigned char *src, int src_stride,
unsigned char *dst, int dst_stride) {
double ftmp[2];
uint64_t tmp[2];
uint8_t loop_count = 4;
/* clang-format off */
__asm__ volatile (
"1: \n\t"
COPY_MEM_16X2
COPY_MEM_16X2
MMI_ADDIU(%[loop_count], %[loop_count], -0x01)
"bnez %[loop_count], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[tmp0]"=&r"(tmp[0]), [tmp1]"=&r"(tmp[1]),
[loop_count]"+&r"(loop_count),
[dst]"+&r"(dst), [src]"+&r"(src)
: [src_stride]"r"((mips_reg)src_stride),
[dst_stride]"r"((mips_reg)dst_stride)
: "memory"
);
/* clang-format on */
}
void vp8_copy_mem8x8_mmi(unsigned char *src, int src_stride, unsigned char *dst,
int dst_stride) {
double ftmp[2];
uint64_t tmp[1];
uint8_t loop_count = 4;
/* clang-format off */
__asm__ volatile (
"1: \n\t"
COPY_MEM_8X2
MMI_ADDIU(%[loop_count], %[loop_count], -0x01)
"bnez %[loop_count], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[tmp0]"=&r"(tmp[0]), [loop_count]"+&r"(loop_count),
[dst]"+&r"(dst), [src]"+&r"(src)
: [src_stride]"r"((mips_reg)src_stride),
[dst_stride]"r"((mips_reg)dst_stride)
: "memory"
);
/* clang-format on */
}
void vp8_copy_mem8x4_mmi(unsigned char *src, int src_stride, unsigned char *dst,
int dst_stride) {
double ftmp[2];
uint64_t tmp[1];
/* clang-format off */
__asm__ volatile (
COPY_MEM_8X2
COPY_MEM_8X2
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[tmp0]"=&r"(tmp[0]),
[dst]"+&r"(dst), [src]"+&r"(src)
: [src_stride]"r"((mips_reg)src_stride),
[dst_stride]"r"((mips_reg)dst_stride)
: "memory"
);
/* clang-format on */
}
|
