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
|
/*
* ARM generic helpers for various arithmetical operations.
*
* This code is licensed under the GNU GPL v2 or later.
*
* SPDX-License-Identifier: GPL-2.0-or-later
*/
#include "qemu/osdep.h"
#include "qemu/crc32c.h"
#include <zlib.h> /* for crc32 */
#define HELPER_H "tcg/helper.h"
#include "exec/helper-proto.h.inc"
/*
* Note that signed overflow is undefined in C. The following routines are
* careful to use unsigned types where modulo arithmetic is required.
* Failure to do so _will_ break on newer gcc.
*/
/* Signed saturating arithmetic. */
/* Perform 16-bit signed saturating addition. */
static inline uint16_t add16_sat(uint16_t a, uint16_t b)
{
uint16_t res;
res = a + b;
if (((res ^ a) & 0x8000) && !((a ^ b) & 0x8000)) {
if (a & 0x8000) {
res = 0x8000;
} else {
res = 0x7fff;
}
}
return res;
}
/* Perform 8-bit signed saturating addition. */
static inline uint8_t add8_sat(uint8_t a, uint8_t b)
{
uint8_t res;
res = a + b;
if (((res ^ a) & 0x80) && !((a ^ b) & 0x80)) {
if (a & 0x80) {
res = 0x80;
} else {
res = 0x7f;
}
}
return res;
}
/* Perform 16-bit signed saturating subtraction. */
static inline uint16_t sub16_sat(uint16_t a, uint16_t b)
{
uint16_t res;
res = a - b;
if (((res ^ a) & 0x8000) && ((a ^ b) & 0x8000)) {
if (a & 0x8000) {
res = 0x8000;
} else {
res = 0x7fff;
}
}
return res;
}
/* Perform 8-bit signed saturating subtraction. */
static inline uint8_t sub8_sat(uint8_t a, uint8_t b)
{
uint8_t res;
res = a - b;
if (((res ^ a) & 0x80) && ((a ^ b) & 0x80)) {
if (a & 0x80) {
res = 0x80;
} else {
res = 0x7f;
}
}
return res;
}
#define ADD16(a, b, n) RESULT(add16_sat(a, b), n, 16);
#define SUB16(a, b, n) RESULT(sub16_sat(a, b), n, 16);
#define ADD8(a, b, n) RESULT(add8_sat(a, b), n, 8);
#define SUB8(a, b, n) RESULT(sub8_sat(a, b), n, 8);
#define PFX q
#include "op_addsub.c.inc"
/* Unsigned saturating arithmetic. */
static inline uint16_t add16_usat(uint16_t a, uint16_t b)
{
uint16_t res;
res = a + b;
if (res < a) {
res = 0xffff;
}
return res;
}
static inline uint16_t sub16_usat(uint16_t a, uint16_t b)
{
if (a > b) {
return a - b;
} else {
return 0;
}
}
static inline uint8_t add8_usat(uint8_t a, uint8_t b)
{
uint8_t res;
res = a + b;
if (res < a) {
res = 0xff;
}
return res;
}
static inline uint8_t sub8_usat(uint8_t a, uint8_t b)
{
if (a > b) {
return a - b;
} else {
return 0;
}
}
#define ADD16(a, b, n) RESULT(add16_usat(a, b), n, 16);
#define SUB16(a, b, n) RESULT(sub16_usat(a, b), n, 16);
#define ADD8(a, b, n) RESULT(add8_usat(a, b), n, 8);
#define SUB8(a, b, n) RESULT(sub8_usat(a, b), n, 8);
#define PFX uq
#include "op_addsub.c.inc"
/* Signed modulo arithmetic. */
#define SARITH16(a, b, n, op) do { \
int32_t sum; \
sum = (int32_t)(int16_t)(a) op (int32_t)(int16_t)(b); \
RESULT(sum, n, 16); \
if (sum >= 0) \
ge |= 3 << (n * 2); \
} while (0)
#define SARITH8(a, b, n, op) do { \
int32_t sum; \
sum = (int32_t)(int8_t)(a) op (int32_t)(int8_t)(b); \
RESULT(sum, n, 8); \
if (sum >= 0) \
ge |= 1 << n; \
} while (0)
#define ADD16(a, b, n) SARITH16(a, b, n, +)
#define SUB16(a, b, n) SARITH16(a, b, n, -)
#define ADD8(a, b, n) SARITH8(a, b, n, +)
#define SUB8(a, b, n) SARITH8(a, b, n, -)
#define PFX s
#define ARITH_GE
#include "op_addsub.c.inc"
/* Unsigned modulo arithmetic. */
#define ADD16(a, b, n) do { \
uint32_t sum; \
sum = (uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b); \
RESULT(sum, n, 16); \
if ((sum >> 16) == 1) \
ge |= 3 << (n * 2); \
} while (0)
#define ADD8(a, b, n) do { \
uint32_t sum; \
sum = (uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b); \
RESULT(sum, n, 8); \
if ((sum >> 8) == 1) \
ge |= 1 << n; \
} while (0)
#define SUB16(a, b, n) do { \
uint32_t sum; \
sum = (uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b); \
RESULT(sum, n, 16); \
if ((sum >> 16) == 0) \
ge |= 3 << (n * 2); \
} while (0)
#define SUB8(a, b, n) do { \
uint32_t sum; \
sum = (uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b); \
RESULT(sum, n, 8); \
if ((sum >> 8) == 0) \
ge |= 1 << n; \
} while (0)
#define PFX u
#define ARITH_GE
#include "op_addsub.c.inc"
/* Halved signed arithmetic. */
#define ADD16(a, b, n) \
RESULT(((int32_t)(int16_t)(a) + (int32_t)(int16_t)(b)) >> 1, n, 16)
#define SUB16(a, b, n) \
RESULT(((int32_t)(int16_t)(a) - (int32_t)(int16_t)(b)) >> 1, n, 16)
#define ADD8(a, b, n) \
RESULT(((int32_t)(int8_t)(a) + (int32_t)(int8_t)(b)) >> 1, n, 8)
#define SUB8(a, b, n) \
RESULT(((int32_t)(int8_t)(a) - (int32_t)(int8_t)(b)) >> 1, n, 8)
#define PFX sh
#include "op_addsub.c.inc"
/* Halved unsigned arithmetic. */
#define ADD16(a, b, n) \
RESULT(((uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b)) >> 1, n, 16)
#define SUB16(a, b, n) \
RESULT(((uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b)) >> 1, n, 16)
#define ADD8(a, b, n) \
RESULT(((uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b)) >> 1, n, 8)
#define SUB8(a, b, n) \
RESULT(((uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b)) >> 1, n, 8)
#define PFX uh
#include "op_addsub.c.inc"
static inline uint8_t do_usad(uint8_t a, uint8_t b)
{
if (a > b) {
return a - b;
} else {
return b - a;
}
}
/* Unsigned sum of absolute byte differences. */
uint32_t HELPER(usad8)(uint32_t a, uint32_t b)
{
uint32_t sum;
sum = do_usad(a, b);
sum += do_usad(a >> 8, b >> 8);
sum += do_usad(a >> 16, b >> 16);
sum += do_usad(a >> 24, b >> 24);
return sum;
}
/* For ARMv6 SEL instruction. */
uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b)
{
uint32_t mask;
mask = 0;
if (flags & 1) {
mask |= 0xff;
}
if (flags & 2) {
mask |= 0xff00;
}
if (flags & 4) {
mask |= 0xff0000;
}
if (flags & 8) {
mask |= 0xff000000;
}
return (a & mask) | (b & ~mask);
}
/*
* CRC helpers.
* The upper bytes of val (above the number specified by 'bytes') must have
* been zeroed out by the caller.
*/
uint32_t HELPER(crc32)(uint32_t acc, uint32_t val, uint32_t bytes)
{
uint8_t buf[4];
stl_le_p(buf, val);
/* zlib crc32 converts the accumulator and output to one's complement. */
return crc32(acc ^ 0xffffffff, buf, bytes) ^ 0xffffffff;
}
uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes)
{
uint8_t buf[4];
stl_le_p(buf, val);
/* Linux crc32c converts the output to one's complement. */
return crc32c(acc, buf, bytes) ^ 0xffffffff;
}
|
