Simplest Possible Example to Show GPU Outperform CPU Using CUDA

Question

I am looking for the most concise amount of code possible that can be coded both for a CPU (using g++) and a GPU (using nvcc) for which the GPU consistently outperforms the

Answer 1

For reference, I made a similar example with time measurements. With GTX 660, the GPU speedup was 24X where its operation includes data transfers in addition to actual computation.

#include "cuda_runtime.h"
#include "device_launch_parameters.h"

#include 
#include 

#define N (1024*1024)
#define M (10000)
#define THREADS_PER_BLOCK 1024

void serial_add(double *a, double *b, double *c, int n, int m)
{
    for(int index=0;index>>( d_a, d_b, d_c );

    cudaMemcpy( c, d_c, size, cudaMemcpyDeviceToHost );


    printf( "c[0] = %d\n",0,c[0] );
    printf( "c[%d] = %d\n",N-1, c[N-1] );


    free(a);
    free(b);
    free(c);
    cudaFree( d_a );
    cudaFree( d_b );
    cudaFree( d_c );

    end = clock();
    float time2 = ((float)(end-start))/CLOCKS_PER_SEC;
    printf("CUDA: %f seconds, Speedup: %f\n",time2, time1/time2);

    return 0;
}