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
|
// Start of atomics.h
SCALAR_FUN_ATTR int32_t atomic_xchg_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_xchg_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_cmpxchg_i32_global(volatile __global int32_t *p,
int32_t cmp, int32_t val);
SCALAR_FUN_ATTR int32_t atomic_cmpxchg_i32_shared(volatile __local int32_t *p,
int32_t cmp, int32_t val);
SCALAR_FUN_ATTR int32_t atomic_add_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_add_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR float atomic_fadd_f32_global(volatile __global float *p, float x);
SCALAR_FUN_ATTR float atomic_fadd_f32_shared(volatile __local float *p, float x);
SCALAR_FUN_ATTR int32_t atomic_smax_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_smax_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_smin_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_smin_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR uint32_t atomic_umax_i32_global(volatile __global uint32_t *p, uint32_t x);
SCALAR_FUN_ATTR uint32_t atomic_umax_i32_shared(volatile __local uint32_t *p, uint32_t x);
SCALAR_FUN_ATTR uint32_t atomic_umin_i32_global(volatile __global uint32_t *p, uint32_t x);
SCALAR_FUN_ATTR uint32_t atomic_umin_i32_shared(volatile __local uint32_t *p, uint32_t x);
SCALAR_FUN_ATTR int32_t atomic_and_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_and_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_or_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_or_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_xor_i32_global(volatile __global int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_xor_i32_shared(volatile __local int32_t *p, int32_t x);
SCALAR_FUN_ATTR int32_t atomic_xchg_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicExch((int32_t*)p, x);
#else
return atomic_xor(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_xchg_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicExch((int32_t*)p, x);
#else
return atomic_xor(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_cmpxchg_i32_global(volatile __global int32_t *p,
int32_t cmp, int32_t val) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicCAS((int32_t*)p, cmp, val);
#else
return atomic_cmpxchg(p, cmp, val);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_cmpxchg_i32_shared(volatile __local int32_t *p,
int32_t cmp, int32_t val) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicCAS((int32_t*)p, cmp, val);
#else
return atomic_cmpxchg(p, cmp, val);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_add_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAdd((int32_t*)p, x);
#else
return atomic_add(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_add_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAdd((int32_t*)p, x);
#else
return atomic_add(p, x);
#endif
}
SCALAR_FUN_ATTR float atomic_fadd_f32_global(volatile __global float *p, float x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAdd((float*)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
float ret;
asm volatile("atom.global.add.f32 %0,[%1],%2;":"=f"(ret):"l"(p),"f"(x):"memory");
return ret;
#elif defined(__opencl_c_ext_fp32_global_atomic_add)
// use hardware-supported atomic addition on some Intel GPUs
return atomic_fetch_add_explicit((volatile __global atomic_float*)p,
x,
memory_order_relaxed);
#elif __has_builtin(__builtin_amdgcn_global_atomic_fadd_f32)
// use hardware-supported atomic addition on some AMD GPUs
return __builtin_amdgcn_global_atomic_fadd_f32(p, x);
#else
// fallback emulation:
// https://forums.developer.nvidia.com/t/atomicadd-float-float-atomicmul-float-float/14639/5
float old = x;
float ret;
while ((old=atomic_xchg(p, ret=atomic_xchg(p, 0.0f)+old))!=0.0f);
return ret;
#endif
}
SCALAR_FUN_ATTR float atomic_fadd_f32_shared(volatile __local float *p, float x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAdd((float*)p, x);
#else
union { int32_t i; float f; } old;
union { int32_t i; float f; } assumed;
old.f = *p;
do {
assumed.f = old.f;
old.f = old.f + x;
old.i = atomic_cmpxchg_i32_shared((volatile __local int32_t*)p, assumed.i, old.i);
} while (assumed.i != old.i);
return old.f;
#endif
}
SCALAR_FUN_ATTR int32_t atomic_smax_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMax((int32_t*)p, x);
#else
return atomic_max(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_smax_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMax((int32_t*)p, x);
#else
return atomic_max(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_smin_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMin((int32_t*)p, x);
#else
return atomic_min(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_smin_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMin((int32_t*)p, x);
#else
return atomic_min(p, x);
#endif
}
SCALAR_FUN_ATTR uint32_t atomic_umax_i32_global(volatile __global uint32_t *p, uint32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMax((uint32_t*)p, x);
#else
return atomic_max(p, x);
#endif
}
SCALAR_FUN_ATTR uint32_t atomic_umax_i32_shared(volatile __local uint32_t *p, uint32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMax((uint32_t*)p, x);
#else
return atomic_max(p, x);
#endif
}
SCALAR_FUN_ATTR uint32_t atomic_umin_i32_global(volatile __global uint32_t *p, uint32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMin((uint32_t*)p, x);
#else
return atomic_min(p, x);
#endif
}
SCALAR_FUN_ATTR uint32_t atomic_umin_i32_shared(volatile __local uint32_t *p, uint32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicMin((uint32_t*)p, x);
#else
return atomic_min(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_and_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAnd((int32_t*)p, x);
#else
return atomic_and(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_and_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicAnd((int32_t*)p, x);
#else
return atomic_and(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_or_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicOr((int32_t*)p, x);
#else
return atomic_or(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_or_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicOr((int32_t*)p, x);
#else
return atomic_or(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_xor_i32_global(volatile __global int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicXor((int32_t*)p, x);
#else
return atomic_xor(p, x);
#endif
}
SCALAR_FUN_ATTR int32_t atomic_xor_i32_shared(volatile __local int32_t *p, int32_t x) {
#if defined(FUTHARK_CUDA) || defined(FUTHARK_HIP)
return atomicXor((int32_t*)p, x);
#else
return atomic_xor(p, x);
#endif
}
// End of atomics.h
|
