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
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
|
/*
* VIS op helpers
*
* Copyright (c) 2003-2005 Fabrice Bellard
*
* This library 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.
*
* This library 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 this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "cpu.h"
#include "exec/helper-proto.h"
/* This function uses non-native bit order */
#define GET_FIELD(X, FROM, TO) \
((X) >> (63 - (TO)) & ((1ULL << ((TO) - (FROM) + 1)) - 1))
/* This function uses the order in the manuals, i.e. bit 0 is 2^0 */
#define GET_FIELD_SP(X, FROM, TO) \
GET_FIELD(X, 63 - (TO), 63 - (FROM))
target_ulong helper_array8(target_ulong pixel_addr, target_ulong cubesize)
{
return (GET_FIELD_SP(pixel_addr, 60, 63) << (17 + 2 * cubesize)) |
(GET_FIELD_SP(pixel_addr, 39, 39 + cubesize - 1) << (17 + cubesize)) |
(GET_FIELD_SP(pixel_addr, 17 + cubesize - 1, 17) << 17) |
(GET_FIELD_SP(pixel_addr, 56, 59) << 13) |
(GET_FIELD_SP(pixel_addr, 35, 38) << 9) |
(GET_FIELD_SP(pixel_addr, 13, 16) << 5) |
(((pixel_addr >> 55) & 1) << 4) |
(GET_FIELD_SP(pixel_addr, 33, 34) << 2) |
GET_FIELD_SP(pixel_addr, 11, 12);
}
#if HOST_BIG_ENDIAN
#define VIS_B64(n) b[7 - (n)]
#define VIS_W64(n) w[3 - (n)]
#define VIS_SW64(n) sw[3 - (n)]
#define VIS_L64(n) l[1 - (n)]
#define VIS_B32(n) b[3 - (n)]
#define VIS_W32(n) w[1 - (n)]
#else
#define VIS_B64(n) b[n]
#define VIS_W64(n) w[n]
#define VIS_SW64(n) sw[n]
#define VIS_L64(n) l[n]
#define VIS_B32(n) b[n]
#define VIS_W32(n) w[n]
#endif
typedef union {
uint8_t b[8];
uint16_t w[4];
int16_t sw[4];
uint32_t l[2];
uint64_t ll;
float64 d;
} VIS64;
typedef union {
uint8_t b[4];
uint16_t w[2];
uint32_t l;
float32 f;
} VIS32;
uint64_t helper_fpmerge(uint32_t src1, uint32_t src2)
{
VIS32 s1, s2;
VIS64 d;
s1.l = src1;
s2.l = src2;
d.ll = 0;
d.VIS_B64(7) = s1.VIS_B32(3);
d.VIS_B64(6) = s2.VIS_B32(3);
d.VIS_B64(5) = s1.VIS_B32(2);
d.VIS_B64(4) = s2.VIS_B32(2);
d.VIS_B64(3) = s1.VIS_B32(1);
d.VIS_B64(2) = s2.VIS_B32(1);
d.VIS_B64(1) = s1.VIS_B32(0);
d.VIS_B64(0) = s2.VIS_B32(0);
return d.ll;
}
uint64_t helper_fmul8x16(uint32_t src1, uint64_t src2)
{
VIS64 d;
VIS32 s;
uint32_t tmp;
s.l = src1;
d.ll = src2;
#define PMUL(r) \
tmp = (int32_t)d.VIS_SW64(r) * (int32_t)s.VIS_B32(r); \
if ((tmp & 0xff) > 0x7f) { \
tmp += 0x100; \
} \
d.VIS_W64(r) = tmp >> 8;
PMUL(0);
PMUL(1);
PMUL(2);
PMUL(3);
#undef PMUL
return d.ll;
}
uint64_t helper_fmul8x16a(uint32_t src1, int32_t src2)
{
VIS32 s;
VIS64 d;
uint32_t tmp;
s.l = src1;
d.ll = 0;
#define PMUL(r) \
do { \
tmp = src2 * (int32_t)s.VIS_B32(r); \
if ((tmp & 0xff) > 0x7f) { \
tmp += 0x100; \
} \
d.VIS_W64(r) = tmp >> 8; \
} while (0)
PMUL(0);
PMUL(1);
PMUL(2);
PMUL(3);
#undef PMUL
return d.ll;
}
uint64_t helper_fmul8sux16(uint64_t src1, uint64_t src2)
{
VIS64 s, d;
uint32_t tmp;
s.ll = src1;
d.ll = src2;
#define PMUL(r) \
tmp = (int32_t)d.VIS_SW64(r) * ((int32_t)s.VIS_SW64(r) >> 8); \
if ((tmp & 0xff) > 0x7f) { \
tmp += 0x100; \
} \
d.VIS_W64(r) = tmp >> 8;
PMUL(0);
PMUL(1);
PMUL(2);
PMUL(3);
#undef PMUL
return d.ll;
}
uint64_t helper_fmul8ulx16(uint64_t src1, uint64_t src2)
{
VIS64 s, d;
uint32_t tmp;
s.ll = src1;
d.ll = src2;
#define PMUL(r) \
tmp = (int32_t)d.VIS_SW64(r) * ((uint32_t)s.VIS_B64(r * 2)); \
if ((tmp & 0xff) > 0x7f) { \
tmp += 0x100; \
} \
d.VIS_W64(r) = tmp >> 8;
PMUL(0);
PMUL(1);
PMUL(2);
PMUL(3);
#undef PMUL
return d.ll;
}
uint64_t helper_fexpand(uint32_t src2)
{
VIS32 s;
VIS64 d;
s.l = src2;
d.ll = 0;
d.VIS_W64(0) = s.VIS_B32(0) << 4;
d.VIS_W64(1) = s.VIS_B32(1) << 4;
d.VIS_W64(2) = s.VIS_B32(2) << 4;
d.VIS_W64(3) = s.VIS_B32(3) << 4;
return d.ll;
}
#define VIS_CMPHELPER(name, F) \
uint64_t name##16(uint64_t src1, uint64_t src2) \
{ \
VIS64 s, d; \
\
s.ll = src1; \
d.ll = src2; \
\
d.VIS_W64(0) = F(s.VIS_W64(0), d.VIS_W64(0)) ? 1 : 0; \
d.VIS_W64(0) |= F(s.VIS_W64(1), d.VIS_W64(1)) ? 2 : 0; \
d.VIS_W64(0) |= F(s.VIS_W64(2), d.VIS_W64(2)) ? 4 : 0; \
d.VIS_W64(0) |= F(s.VIS_W64(3), d.VIS_W64(3)) ? 8 : 0; \
d.VIS_W64(1) = d.VIS_W64(2) = d.VIS_W64(3) = 0; \
\
return d.ll; \
} \
\
uint64_t name##32(uint64_t src1, uint64_t src2) \
{ \
VIS64 s, d; \
\
s.ll = src1; \
d.ll = src2; \
\
d.VIS_L64(0) = F(s.VIS_L64(0), d.VIS_L64(0)) ? 1 : 0; \
d.VIS_L64(0) |= F(s.VIS_L64(1), d.VIS_L64(1)) ? 2 : 0; \
d.VIS_L64(1) = 0; \
\
return d.ll; \
}
#define FCMPGT(a, b) ((a) > (b))
#define FCMPEQ(a, b) ((a) == (b))
#define FCMPLE(a, b) ((a) <= (b))
#define FCMPNE(a, b) ((a) != (b))
VIS_CMPHELPER(helper_fcmpgt, FCMPGT)
VIS_CMPHELPER(helper_fcmpeq, FCMPEQ)
VIS_CMPHELPER(helper_fcmple, FCMPLE)
VIS_CMPHELPER(helper_fcmpne, FCMPNE)
uint64_t helper_pdist(uint64_t sum, uint64_t src1, uint64_t src2)
{
int i;
for (i = 0; i < 8; i++) {
int s1, s2;
s1 = (src1 >> (56 - (i * 8))) & 0xff;
s2 = (src2 >> (56 - (i * 8))) & 0xff;
/* Absolute value of difference. */
s1 -= s2;
if (s1 < 0) {
s1 = -s1;
}
sum += s1;
}
return sum;
}
uint32_t helper_fpack16(uint64_t gsr, uint64_t rs2)
{
int scale = (gsr >> 3) & 0xf;
uint32_t ret = 0;
int byte;
for (byte = 0; byte < 4; byte++) {
uint32_t val;
int16_t src = rs2 >> (byte * 16);
int32_t scaled = src << scale;
int32_t from_fixed = scaled >> 7;
val = (from_fixed < 0 ? 0 :
from_fixed > 255 ? 255 : from_fixed);
ret |= val << (8 * byte);
}
return ret;
}
uint64_t helper_fpack32(uint64_t gsr, uint64_t rs1, uint64_t rs2)
{
int scale = (gsr >> 3) & 0x1f;
uint64_t ret = 0;
int word;
ret = (rs1 << 8) & ~(0x000000ff000000ffULL);
for (word = 0; word < 2; word++) {
uint64_t val;
int32_t src = rs2 >> (word * 32);
int64_t scaled = (int64_t)src << scale;
int64_t from_fixed = scaled >> 23;
val = (from_fixed < 0 ? 0 :
(from_fixed > 255) ? 255 : from_fixed);
ret |= val << (32 * word);
}
return ret;
}
uint32_t helper_fpackfix(uint64_t gsr, uint64_t rs2)
{
int scale = (gsr >> 3) & 0x1f;
uint32_t ret = 0;
int word;
for (word = 0; word < 2; word++) {
uint32_t val;
int32_t src = rs2 >> (word * 32);
int64_t scaled = (int64_t)src << scale;
int64_t from_fixed = scaled >> 16;
val = (from_fixed < -32768 ? -32768 :
from_fixed > 32767 ? 32767 : from_fixed);
ret |= (val & 0xffff) << (word * 16);
}
return ret;
}
uint64_t helper_bshuffle(uint64_t gsr, uint64_t src1, uint64_t src2)
{
union {
uint64_t ll[2];
uint8_t b[16];
} s;
VIS64 r;
uint32_t i, mask, host;
/* Set up S such that we can index across all of the bytes. */
#if HOST_BIG_ENDIAN
s.ll[0] = src1;
s.ll[1] = src2;
host = 0;
#else
s.ll[1] = src1;
s.ll[0] = src2;
host = 15;
#endif
mask = gsr >> 32;
for (i = 0; i < 8; ++i) {
unsigned e = (mask >> (28 - i*4)) & 0xf;
r.VIS_B64(i) = s.b[e ^ host];
}
return r.ll;
}
|
