2 * Copyright 1993-2008 NVIDIA Corporation. All rights reserved.
6 * This source code is subject to NVIDIA ownership rights under U.S. and
7 * international Copyright laws. Users and possessors of this source code
8 * are hereby granted a nonexclusive, royalty-free license to use this code
9 * in individual and commercial software.
11 * NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE
12 * CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR
13 * IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH
14 * REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF
15 * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
16 * IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL,
17 * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
18 * OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
19 * OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
20 * OR PERFORMANCE OF THIS SOURCE CODE.
22 * U.S. Government End Users. This source code is a "commercial item" as
23 * that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting of
24 * "commercial computer software" and "commercial computer software
25 * documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995)
26 * and is provided to the U.S. Government only as a commercial end item.
27 * Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through
28 * 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the
29 * source code with only those rights set forth herein.
31 * Any use of this source code in individual and commercial software must
32 * include, in the user documentation and internal comments to the code,
33 * the above Disclaimer and U.S. Government End Users Notice.
40 // Simple utility function to check for CUDA runtime errors
41 void checkCUDAError(const char *msg);
43 ///////////////////////////////////////////////////////////////////////////////
45 ///////////////////////////////////////////////////////////////////////////////
46 int main(int argc, char **argv)
49 // pointer and dimension for host memory
53 // pointers for device memory
56 // allocate and initialize host memory
57 // Bonus: try using cudaMallocHost in place of malloc
59 h_a = (float *)malloc(dimA * sizeof(float));
60 for (n = 0; n < dimA; n++) {
63 // Part 1 of 5: allocate device memory
64 size_t memSize = dimA * sizeof(float);
65 cudaMalloc((void **)&d_a, memSize);
66 cudaMalloc((void **)&d_b, memSize);
68 // Part 2 of 5: host to device memory copy
69 cudaMemcpy(d_a, h_a, memSize, cudaMemcpyHostToDevice);
71 // Part 3 of 5: device to device memory copy
72 cudaMemcpy(d_b, d_a, memSize, cudaMemcpyDeviceToDevice);
75 for (n = 0; n < dimA; n++) {
79 // Part 4 of 5: device to host copy
80 cudaMemcpy(h_a, d_b, memSize, cudaMemcpyDeviceToHost);
82 // Check for any CUDA errors
83 checkCUDAError("cudaMemcpy calls");
85 // verify the data on the host is correct
86 for (n = 0; n < dimA; n++) {
87 assert(h_a[n] == (float)n);
89 // Part 5 of 5: free device memory pointers d_a and d_b
93 // Check for any CUDA errors
94 checkCUDAError("cudaFree");
96 // free host memory pointer h_a
97 // Bonus: be sure to use cudaFreeHost for memory allocated with cudaMallocHost
100 // If the program makes it this far, then the results are correct and
101 // there are no run-time errors. Good work!
102 printf("Correct!\n");
106 void checkCUDAError(const char *msg)
108 cudaError_t err = cudaGetLastError();
109 if (cudaSuccess != err) {
110 fprintf(stderr, "Cuda error: %s: %s.\n", msg,
111 cudaGetErrorString(err));