-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
85 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,85 @@ | ||
// from https://github.com/olcf-tutorials/vector_addition_cuda/blob/master/vector_addition.cu | ||
|
||
#include <stdio.h> | ||
|
||
// Size of array | ||
#define N 1048576 | ||
|
||
// Kernel | ||
__global__ void add_vectors(double *a, double *b, double *c) | ||
{ | ||
int id = blockDim.x * blockIdx.x + threadIdx.x; | ||
if(id < N) c[id] = a[id] + b[id]; | ||
} | ||
|
||
// Main program | ||
int main() | ||
{ | ||
// Number of bytes to allocate for N doubles | ||
size_t bytes = N*sizeof(double); | ||
|
||
// Allocate memory for arrays A, B, and C on host | ||
double *A = (double*)malloc(bytes); | ||
double *B = (double*)malloc(bytes); | ||
double *C = (double*)malloc(bytes); | ||
|
||
// Allocate memory for arrays d_A, d_B, and d_C on device | ||
double *d_A, *d_B, *d_C; | ||
cudaMalloc(&d_A, bytes); | ||
cudaMalloc(&d_B, bytes); | ||
cudaMalloc(&d_C, bytes); | ||
|
||
// Fill host arrays A and B | ||
for(int i=0; i<N; i++) | ||
{ | ||
A[i] = 1.0; | ||
B[i] = 2.0; | ||
} | ||
|
||
// Copy data from host arrays A and B to device arrays d_A and d_B | ||
cudaMemcpy(d_A, A, bytes, cudaMemcpyHostToDevice); | ||
cudaMemcpy(d_B, B, bytes, cudaMemcpyHostToDevice); | ||
|
||
// Set execution configuration parameters | ||
// thr_per_blk: number of CUDA threads per grid block | ||
// blk_in_grid: number of blocks in grid | ||
int thr_per_blk = 256; | ||
int blk_in_grid = ceil( float(N) / thr_per_blk ); | ||
|
||
// Launch kernel | ||
add_vectors<<< blk_in_grid, thr_per_blk >>>(d_A, d_B, d_C); | ||
|
||
// Copy data from device array d_C to host array C | ||
cudaMemcpy(C, d_C, bytes, cudaMemcpyDeviceToHost); | ||
|
||
// Verify results | ||
double tolerance = 1.0e-14; | ||
for(int i=0; i<N; i++) | ||
{ | ||
if( fabs(C[i] - 3.0) > tolerance) | ||
{ | ||
printf("\nError: value of C[%d] = %d instead of 3.0\n\n", i, C[i]); | ||
exit(1); | ||
} | ||
} | ||
|
||
// Free CPU memory | ||
free(A); | ||
free(B); | ||
free(C); | ||
|
||
// Free GPU memory | ||
cudaFree(d_A); | ||
cudaFree(d_B); | ||
cudaFree(d_C); | ||
|
||
printf("\n---------------------------\n"); | ||
printf("__SUCCESS__\n"); | ||
printf("---------------------------\n"); | ||
printf("N = %d\n", N); | ||
printf("Threads Per Block = %d\n", thr_per_blk); | ||
printf("Blocks In Grid = %d\n", blk_in_grid); | ||
printf("---------------------------\n\n"); | ||
|
||
return 0; | ||
} |