-
Notifications
You must be signed in to change notification settings - Fork 456
Expand file tree
/
Copy pathcurand_mrg32k3a_uniform_example.cpp
More file actions
139 lines (102 loc) · 4 KB
/
curand_mrg32k3a_uniform_example.cpp
File metadata and controls
139 lines (102 loc) · 4 KB
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
/*
* SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*
* This program uses the host CURAND API to generate 100
* pseudorandom floats.
*/
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <stdexcept>
#include <vector>
#include <cuda_runtime.h>
#include <curand.h>
#include "curand_utils.h"
using data_type = float;
void run_on_device(const int &n, const unsigned long long &offset,
const unsigned long long &seed,
const curandOrdering_t &order, const curandRngType_t &rng,
const cudaStream_t &stream, curandGenerator_t &gen,
std::vector<data_type> &h_data) {
data_type *d_data = nullptr;
/* C data to device */
CUDA_CHECK(cudaMalloc(reinterpret_cast<void **>(&d_data),
sizeof(data_type) * h_data.size()));
/* Create pseudo-random number generator */
CURAND_CHECK(curandCreateGenerator(&gen, CURAND_RNG_PSEUDO_MRG32K3A));
/* Set cuRAND to stream */
CURAND_CHECK(curandSetStream(gen, stream));
/* Set offset */
CURAND_CHECK(curandSetGeneratorOffset(gen, offset));
/* Set ordering */
CURAND_CHECK(curandSetGeneratorOrdering(gen, order));
/* Set seed */
CURAND_CHECK(curandSetPseudoRandomGeneratorSeed(gen, seed));
/* Generate n floats on device */
CURAND_CHECK(curandGenerateUniform(gen, d_data, h_data.size()));
/* Copy data to host */
CUDA_CHECK(cudaMemcpyAsync(h_data.data(), d_data,
sizeof(data_type) * h_data.size(),
cudaMemcpyDeviceToHost, stream));
/* Sync stream */
CUDA_CHECK(cudaStreamSynchronize(stream));
/* Cleanup */
CUDA_CHECK(cudaFree(d_data));
}
void run_on_host(const int &n, const unsigned long long &offset,
const unsigned long long &seed, const curandOrdering_t &order,
const curandRngType_t &rng, const cudaStream_t &stream,
curandGenerator_t &gen, std::vector<data_type> &h_data) {
/* Create pseudo-random number generator */
CURAND_CHECK(curandCreateGeneratorHost(&gen, CURAND_RNG_PSEUDO_MRG32K3A));
/* Set cuRAND to stream */
CURAND_CHECK(curandSetStream(gen, stream));
/* Set offset */
CURAND_CHECK(curandSetGeneratorOffset(gen, offset));
/* Set ordering */
CURAND_CHECK(curandSetGeneratorOrdering(gen, order));
/* Set seed */
CURAND_CHECK(curandSetPseudoRandomGeneratorSeed(gen, seed));
/* Generate n floats on host */
CURAND_CHECK(curandGenerateUniform(gen, h_data.data(), h_data.size()));
}
int main(int argc, char *argv[]) {
cudaStream_t stream = NULL;
curandGenerator_t gen = NULL;
curandRngType_t rng = CURAND_RNG_PSEUDO_MRG32K3A;
curandOrdering_t order = CURAND_ORDERING_PSEUDO_BEST;
const int n = 10;
const unsigned long long offset = 0ULL;
const unsigned long long seed = 1234ULL;
/* Create stream */
CUDA_CHECK(cudaStreamCreateWithFlags(&stream, cudaStreamNonBlocking));
/* Allocate n floats on host */
std::vector<data_type> h_data(n, 0);
run_on_host(n, offset, seed, order, rng, stream, gen, h_data);
printf("Host\n");
print_vector(h_data);
printf("=====\n");
run_on_device(n, offset, seed, order, rng, stream, gen, h_data);
printf("Device\n");
print_vector(h_data);
printf("=====\n");
/* Cleanup */
CURAND_CHECK(curandDestroyGenerator(gen));
CUDA_CHECK(cudaStreamDestroy(stream));
CUDA_CHECK(cudaDeviceReset());
return EXIT_SUCCESS;
}