You can run it, but the result will be wrong, you can check this through my code below.
/*
* Copyright 1993-2010 NVIDIA Corporation. All rights reserved.
*
* NVIDIA Corporation and its licensors retain all intellectual property and
* proprietary rights in and to this software and related documentation.
* Any use, reproduction, disclosure, or distribution of this software
* and related documentation without an express license agreement from
* NVIDIA Corporation is strictly prohibited.
*
* Please refer to the applicable NVIDIA end user license agreement (EULA)
* associated with this source code for terms and conditions that govern
* your use of this NVIDIA software.
*
*/
#include <stdio.h>
static void HandleError( cudaError_t err,
const char *file,
int line ) {
if (err != cudaSuccess) {
printf( "%s in %s at line %d\n", cudaGetErrorString( err ),
file, line );
exit( EXIT_FAILURE );
}
}
#define HANDLE_ERROR( err ) (HandleError( err, __FILE__, __LINE__ ))
#define N 1024
// #define N 1025
__global__ void add( int *a, int *b, int *c ) {
int tid = threadIdx.x; // this thread handles the data at its thread id
if (tid < N)
c[tid] = a[tid] + b[tid];
}
int main( void ) {
int a[N], b[N], c[N];
int *dev_a, *dev_b, *dev_c;
// allocate the memory on the GPU
HANDLE_ERROR( cudaMalloc( (void**)&dev_a, N * sizeof(int) ) );
HANDLE_ERROR( cudaMalloc( (void**)&dev_b, N * sizeof(int) ) );
HANDLE_ERROR( cudaMalloc( (void**)&dev_c, N * sizeof(int) ) );
// fill the arrays 'a' and 'b' on the CPU
for (int i=0; i<N; i++) {
a[i] = -i;
b[i] = i * i;
}
// copy the arrays 'a' and 'b' to the GPU
HANDLE_ERROR( cudaMemcpy( dev_a, a, N * sizeof(int),
cudaMemcpyHostToDevice ) );
HANDLE_ERROR( cudaMemcpy( dev_b, b, N * sizeof(int),
cudaMemcpyHostToDevice ) );
dim3 threadsPerBlock( N, 1, 1 );
add<<<1,threadsPerBlock>>>( dev_a, dev_b, dev_c );
// copy the array 'c' back from the GPU to the CPU
HANDLE_ERROR( cudaMemcpy( c, dev_c, N * sizeof(int),
cudaMemcpyDeviceToHost ) );
// display the results
for (int i=0; i<N; i++) {
if (i==N-1)
printf( "%d + %d = %d\n", a[i], b[i], c[i] );
}
// free the memory allocated on the GPU
HANDLE_ERROR( cudaFree( dev_a ) );
HANDLE_ERROR( cudaFree( dev_b ) );
HANDLE_ERROR( cudaFree( dev_c ) );
return 0;
}
Once you change the N to 1025 (or any value bigger than 1024), you will find the computing result is wrong.