-
Notifications
You must be signed in to change notification settings - Fork 456
Expand file tree
/
Copy pathcublas_asum_example.cu
More file actions
84 lines (60 loc) · 2.16 KB
/
cublas_asum_example.cu
File metadata and controls
84 lines (60 loc) · 2.16 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
/*
* SPDX-FileCopyrightText: Copyright (c) 2020 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.
*/
#include <cstdio>
#include <cstdlib>
#include <vector>
#include <cublas_v2.h>
#include <cuda_runtime.h>
#include "cublas_utils.h"
using data_type = double;
int main(int argc, char *argv[]) {
cublasHandle_t cublasH = NULL;
cudaStream_t stream = NULL;
/*
* A = | 1.0 2.0 3.0 4.0 |
*/
const std::vector<data_type> A = {1.0, 2.0, 3.0, 4.0};
const int incx = 1;
data_type result = 0.0;
data_type *d_A = nullptr;
printf("A\n");
print_vector(A.size(), A.data());
printf("=====\n");
/* step 1: create cublas handle, bind a stream */
CUBLAS_CHECK(cublasCreate(&cublasH));
CUDA_CHECK(cudaStreamCreateWithFlags(&stream, cudaStreamNonBlocking));
CUBLAS_CHECK(cublasSetStream(cublasH, stream));
/* step 2: copy data to device */
CUDA_CHECK(cudaMalloc(reinterpret_cast<void **>(&d_A), sizeof(data_type) * A.size()));
CUDA_CHECK(cudaMemcpyAsync(d_A, A.data(), sizeof(data_type) * A.size(), cudaMemcpyHostToDevice,
stream));
/* step 3: compute */
CUBLAS_CHECK(cublasDasum(cublasH, A.size(), d_A, incx, &result));
CUDA_CHECK(cudaStreamSynchronize(stream));
/*
* result = 10.00
*/
printf("result\n");
std::printf("%0.2f\n", result);
printf("=====\n");
/* free resources */
CUDA_CHECK(cudaFree(d_A));
CUBLAS_CHECK(cublasDestroy(cublasH));
CUDA_CHECK(cudaStreamDestroy(stream));
CUDA_CHECK(cudaDeviceReset());
return EXIT_SUCCESS;
}