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
|
// Start of atomics64.h
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP) || defined(cl_khr_int64_base_atomics) && defined(cl_khr_int64_extended_atomics)
SCALAR_FUN_ATTR int64_t atomic_xchg_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_xchg_i64_shared(volatile __local int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_cmpxchg_i64_global(volatile __global int64_t *p,
int64_t cmp, int64_t val);
SCALAR_FUN_ATTR int64_t atomic_cmpxchg_i64_shared(volatile __local int64_t *p,
int64_t cmp, int64_t val);
SCALAR_FUN_ATTR int64_t atomic_add_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_add_i64_shared(volatile __local int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_smax_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_smax_i64_shared(volatile __local int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_smin_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_smin_i64_shared(volatile __local int64_t *p, int64_t x);
SCALAR_FUN_ATTR uint64_t atomic_umax_i64_global(volatile __global uint64_t *p, uint64_t x);
SCALAR_FUN_ATTR uint64_t atomic_umax_i64_shared(volatile __local uint64_t *p, uint64_t x);
SCALAR_FUN_ATTR uint64_t atomic_umin_i64_global(volatile __global uint64_t *p, uint64_t x);
SCALAR_FUN_ATTR uint64_t atomic_umin_i64_shared(volatile __local uint64_t *p, uint64_t x);
SCALAR_FUN_ATTR int64_t atomic_and_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_and_i64_shared(volatile __local int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_or_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_or_i64_shared(volatile __local int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_xor_i64_global(volatile __global int64_t *p, int64_t x);
SCALAR_FUN_ATTR int64_t atomic_xor_i64_shared(volatile __local int64_t *p, int64_t x);
#ifdef FUTHARK_F64_ENABLED
SCALAR_FUN_ATTR double atomic_fadd_f64_global(volatile __global double *p, double x);
SCALAR_FUN_ATTR double atomic_fadd_f64_shared(volatile __local double *p, double x);
#endif
SCALAR_FUN_ATTR int64_t atomic_xchg_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicExch((unsigned long long*)p, x);
#else
return atom_xchg(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_xchg_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicExch((unsigned long long*)p, x);
#else
return atom_xchg(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_cmpxchg_i64_global(volatile __global int64_t *p,
int64_t cmp, int64_t val) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicCAS((unsigned long long*)p, cmp, val);
#else
return atom_cmpxchg(p, cmp, val);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_cmpxchg_i64_shared(volatile __local int64_t *p,
int64_t cmp, int64_t val) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicCAS((unsigned long long*)p, cmp, val);
#else
return atom_cmpxchg(p, cmp, val);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_add_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAdd((unsigned long long*)p, x);
#else
return atom_add(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_add_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAdd((unsigned long long*)p, x);
#else
return atom_add(p, x);
#endif
}
#ifdef FUTHARK_F64_ENABLED
SCALAR_FUN_ATTR double atomic_fadd_f64_global(volatile __global double *p, double x) {
#if defined(FUTHARK_CUDA) && __CUDA_ARCH__ >= 600 || defined(FUTHARK_HIP)
return atomicAdd((double*)p, x);
// On OpenCL, use technique from
// https://pipinspace.github.io/blog/atomic-float-addition-in-opencl.html
#elif defined(cl_nv_pragma_unroll)
// use hardware-supported atomic addition on Nvidia GPUs with inline
// PTX assembly
double ret;
asm volatile("atom.global.add.f64 %0,[%1],%2;":"=d"(ret):"l"(p),"d"(x):"memory");
return ret;
#elif __has_builtin(__builtin_amdgcn_global_atomic_fadd_f64)
// use hardware-supported atomic addition on some AMD GPUs
return __builtin_amdgcn_global_atomic_fadd_f64(p, x);
#else
// fallback emulation:
// https://forums.developer.nvidia.com/t/atomicadd-float-float-atomicmul-float-float/14639/5
union {int64_t i; double f;} old;
union {int64_t i; double f;} ret;
old.f = x;
while (1) {
ret.i = atomic_xchg_i64_global((volatile __global int64_t*)p, (int64_t)0);
ret.f += old.f;
old.i = atomic_xchg_i64_global((volatile __global int64_t*)p, ret.i);
if (old.i == 0) {
break;
}
}
return ret.f;
#endif
}
SCALAR_FUN_ATTR double atomic_fadd_f64_shared(volatile __local double *p, double x) {
#if defined(FUTHARK_CUDA) && __CUDA_ARCH__ >= 600 || defined(FUTHARK_HIP)
return atomicAdd((double*)p, x);
#else
union { int64_t i; double f; } old;
union { int64_t i; double f; } assumed;
old.f = *p;
do {
assumed.f = old.f;
old.f = old.f + x;
old.i = atomic_cmpxchg_i64_shared((volatile __local int64_t*)p, assumed.i, old.i);
} while (assumed.i != old.i);
return old.f;
#endif
}
#endif
SCALAR_FUN_ATTR int64_t atomic_smax_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA)
return atomicMax((long long*)p, x);
#elif defined(FUTHARK_HIP)
// Currentely missing in HIP; probably a temporary oversight.
int64_t old = *p, assumed;
do {
assumed = old;
old = smax64(old, x);
old = atomic_cmpxchg_i64_global((volatile __global int64_t*)p, assumed, old);
} while (assumed != old);
return old;
#else
return atom_max(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_smax_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA)
return atomicMax((long long*)p, x);
#elif defined(FUTHARK_HIP)
// Currentely missing in HIP; probably a temporary oversight.
int64_t old = *p, assumed;
do {
assumed = old;
old = smax64(old, x);
old = atomic_cmpxchg_i64_shared((volatile __local int64_t*)p, assumed, old);
} while (assumed != old);
return old;
#else
return atom_max(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_smin_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA)
return atomicMin((long long*)p, x);
#elif defined(FUTHARK_HIP)
// Currentely missing in HIP; probably a temporary oversight.
int64_t old = *p, assumed;
do {
assumed = old;
old = smin64(old, x);
old = atomic_cmpxchg_i64_global((volatile __global int64_t*)p, assumed, old);
} while (assumed != old);
return old;
#else
return atom_min(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_smin_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA)
return atomicMin((long long*)p, x);
#elif defined(FUTHARK_HIP)
// Currentely missing in HIP; probably a temporary oversight.
int64_t old = *p, assumed;
do {
assumed = old;
old = smin64(old, x);
old = atomic_cmpxchg_i64_shared((volatile __local int64_t*)p, assumed, old);
} while (assumed != old);
return old;
#else
return atom_min(p, x);
#endif
}
SCALAR_FUN_ATTR uint64_t atomic_umax_i64_global(volatile __global uint64_t *p, uint64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMax((unsigned long long*)p, x);
#else
return atom_max(p, x);
#endif
}
SCALAR_FUN_ATTR uint64_t atomic_umax_i64_shared(volatile __local uint64_t *p, uint64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMax((unsigned long long*)p, x);
#else
return atom_max(p, x);
#endif
}
SCALAR_FUN_ATTR uint64_t atomic_umin_i64_global(volatile __global uint64_t *p, uint64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMin((unsigned long long*)p, x);
#else
return atom_min(p, x);
#endif
}
SCALAR_FUN_ATTR uint64_t atomic_umin_i64_shared(volatile __local uint64_t *p, uint64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMin((unsigned long long*)p, x);
#else
return atom_min(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_and_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAnd((unsigned long long*)p, x);
#else
return atom_and(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_and_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAnd((unsigned long long*)p, x);
#else
return atom_and(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_or_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicOr((unsigned long long*)p, x);
#else
return atom_or(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_or_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicOr((unsigned long long*)p, x);
#else
return atom_or(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_xor_i64_global(volatile __global int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicXor((unsigned long long*)p, x);
#else
return atom_xor(p, x);
#endif
}
SCALAR_FUN_ATTR int64_t atomic_xor_i64_shared(volatile __local int64_t *p, int64_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicXor((unsigned long long*)p, x);
#else
return atom_xor(p, x);
#endif
}
#endif // defined(FUTHARK_CUDA) || defined(FUTHARK_HIP) || defined(cl_khr_int64_base_atomics) && defined(cl_khr_int64_extended_atomics)
// End of atomics64.h
|
