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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
/*
* Copyright (c) 2016, Alliance for Open Media. All rights reserved
*
* This source code is subject to the terms of the BSD 2 Clause License and
* the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
* was not distributed with this source code in the LICENSE file, you can
* obtain it at www.aomedia.org/license/software. If the Alliance for Open
* Media Patent License 1.0 was not distributed with this source code in the
* PATENTS file, you can obtain it at www.aomedia.org/license/patent.
*/
#include <string.h>
#include "aom_dsp/mips/macros_msa.h"
static void copy_width8_msa(const uint8_t *src, int32_t src_stride,
uint8_t *dst, int32_t dst_stride, int32_t height) {
int32_t cnt;
uint64_t out0, out1, out2, out3, out4, out5, out6, out7;
v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
if (0 == height % 12) {
for (cnt = (height / 12); cnt--;) {
LD_UB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6, src7);
src += (8 * src_stride);
out0 = __msa_copy_u_d((v2i64)src0, 0);
out1 = __msa_copy_u_d((v2i64)src1, 0);
out2 = __msa_copy_u_d((v2i64)src2, 0);
out3 = __msa_copy_u_d((v2i64)src3, 0);
out4 = __msa_copy_u_d((v2i64)src4, 0);
out5 = __msa_copy_u_d((v2i64)src5, 0);
out6 = __msa_copy_u_d((v2i64)src6, 0);
out7 = __msa_copy_u_d((v2i64)src7, 0);
SD4(out0, out1, out2, out3, dst, dst_stride);
dst += (4 * dst_stride);
SD4(out4, out5, out6, out7, dst, dst_stride);
dst += (4 * dst_stride);
LD_UB4(src, src_stride, src0, src1, src2, src3);
src += (4 * src_stride);
out0 = __msa_copy_u_d((v2i64)src0, 0);
out1 = __msa_copy_u_d((v2i64)src1, 0);
out2 = __msa_copy_u_d((v2i64)src2, 0);
out3 = __msa_copy_u_d((v2i64)src3, 0);
SD4(out0, out1, out2, out3, dst, dst_stride);
dst += (4 * dst_stride);
}
} else if (0 == height % 8) {
for (cnt = height >> 3; cnt--;) {
LD_UB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6, src7);
src += (8 * src_stride);
out0 = __msa_copy_u_d((v2i64)src0, 0);
out1 = __msa_copy_u_d((v2i64)src1, 0);
out2 = __msa_copy_u_d((v2i64)src2, 0);
out3 = __msa_copy_u_d((v2i64)src3, 0);
out4 = __msa_copy_u_d((v2i64)src4, 0);
out5 = __msa_copy_u_d((v2i64)src5, 0);
out6 = __msa_copy_u_d((v2i64)src6, 0);
out7 = __msa_copy_u_d((v2i64)src7, 0);
SD4(out0, out1, out2, out3, dst, dst_stride);
dst += (4 * dst_stride);
SD4(out4, out5, out6, out7, dst, dst_stride);
dst += (4 * dst_stride);
}
} else if (0 == height % 4) {
for (cnt = (height / 4); cnt--;) {
LD_UB4(src, src_stride, src0, src1, src2, src3);
src += (4 * src_stride);
out0 = __msa_copy_u_d((v2i64)src0, 0);
out1 = __msa_copy_u_d((v2i64)src1, 0);
out2 = __msa_copy_u_d((v2i64)src2, 0);
out3 = __msa_copy_u_d((v2i64)src3, 0);
SD4(out0, out1, out2, out3, dst, dst_stride);
dst += (4 * dst_stride);
}
} else if (0 == height % 2) {
for (cnt = (height / 2); cnt--;) {
LD_UB2(src, src_stride, src0, src1);
src += (2 * src_stride);
out0 = __msa_copy_u_d((v2i64)src0, 0);
out1 = __msa_copy_u_d((v2i64)src1, 0);
SD(out0, dst);
dst += dst_stride;
SD(out1, dst);
dst += dst_stride;
}
}
}
static void copy_16multx8mult_msa(const uint8_t *src, int32_t src_stride,
uint8_t *dst, int32_t dst_stride,
int32_t height, int32_t width) {
int32_t cnt, loop_cnt;
const uint8_t *src_tmp;
uint8_t *dst_tmp;
v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
for (cnt = (width >> 4); cnt--;) {
src_tmp = src;
dst_tmp = dst;
for (loop_cnt = (height >> 3); loop_cnt--;) {
LD_UB8(src_tmp, src_stride, src0, src1, src2, src3, src4, src5, src6,
src7);
src_tmp += (8 * src_stride);
ST_UB8(src0, src1, src2, src3, src4, src5, src6, src7, dst_tmp,
dst_stride);
dst_tmp += (8 * dst_stride);
}
src += 16;
dst += 16;
}
}
static void copy_width16_msa(const uint8_t *src, int32_t src_stride,
uint8_t *dst, int32_t dst_stride, int32_t height) {
int32_t cnt;
v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
if (0 == height % 12) {
for (cnt = (height / 12); cnt--;) {
LD_UB8(src, src_stride, src0, src1, src2, src3, src4, src5, src6, src7);
src += (8 * src_stride);
ST_UB8(src0, src1, src2, src3, src4, src5, src6, src7, dst, dst_stride);
dst += (8 * dst_stride);
LD_UB4(src, src_stride, src0, src1, src2, src3);
src += (4 * src_stride);
ST_UB4(src0, src1, src2, src3, dst, dst_stride);
dst += (4 * dst_stride);
}
} else if (0 == height % 8) {
copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 16);
} else if (0 == height % 4) {
for (cnt = (height >> 2); cnt--;) {
LD_UB4(src, src_stride, src0, src1, src2, src3);
src += (4 * src_stride);
ST_UB4(src0, src1, src2, src3, dst, dst_stride);
dst += (4 * dst_stride);
}
}
}
static void copy_width32_msa(const uint8_t *src, int32_t src_stride,
uint8_t *dst, int32_t dst_stride, int32_t height) {
int32_t cnt;
v16u8 src0, src1, src2, src3, src4, src5, src6, src7;
if (0 == height % 12) {
for (cnt = (height / 12); cnt--;) {
LD_UB4(src, src_stride, src0, src1, src2, src3);
LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
src += (4 * src_stride);
ST_UB4(src0, src1, src2, src3, dst, dst_stride);
ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
dst += (4 * dst_stride);
LD_UB4(src, src_stride, src0, src1, src2, src3);
LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
src += (4 * src_stride);
ST_UB4(src0, src1, src2, src3, dst, dst_stride);
ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
dst += (4 * dst_stride);
LD_UB4(src, src_stride, src0, src1, src2, src3);
LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
src += (4 * src_stride);
ST_UB4(src0, src1, src2, src3, dst, dst_stride);
ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
dst += (4 * dst_stride);
}
} else if (0 == height % 8) {
copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 32);
} else if (0 == height % 4) {
for (cnt = (height >> 2); cnt--;) {
LD_UB4(src, src_stride, src0, src1, src2, src3);
LD_UB4(src + 16, src_stride, src4, src5, src6, src7);
src += (4 * src_stride);
ST_UB4(src0, src1, src2, src3, dst, dst_stride);
ST_UB4(src4, src5, src6, src7, dst + 16, dst_stride);
dst += (4 * dst_stride);
}
}
}
static void copy_width64_msa(const uint8_t *src, int32_t src_stride,
uint8_t *dst, int32_t dst_stride, int32_t height) {
copy_16multx8mult_msa(src, src_stride, dst, dst_stride, height, 64);
}
void aom_convolve_copy_msa(const uint8_t *src, ptrdiff_t src_stride,
uint8_t *dst, ptrdiff_t dst_stride,
const int16_t *filter_x, int32_t filter_x_stride,
const int16_t *filter_y, int32_t filter_y_stride,
int32_t w, int32_t h) {
(void)filter_x;
(void)filter_y;
(void)filter_x_stride;
(void)filter_y_stride;
switch (w) {
case 4: {
uint32_t cnt, tmp;
/* 1 word storage */
for (cnt = h; cnt--;) {
tmp = LW(src);
SW(tmp, dst);
src += src_stride;
dst += dst_stride;
}
break;
}
case 8: {
copy_width8_msa(src, src_stride, dst, dst_stride, h);
break;
}
case 16: {
copy_width16_msa(src, src_stride, dst, dst_stride, h);
break;
}
case 32: {
copy_width32_msa(src, src_stride, dst, dst_stride, h);
break;
}
case 64: {
copy_width64_msa(src, src_stride, dst, dst_stride, h);
break;
}
default: {
uint32_t cnt;
for (cnt = h; cnt--;) {
memcpy(dst, src, w);
src += src_stride;
dst += dst_stride;
}
break;
}
}
}
|
