_gpu_mtx_add.cu File Reference

#include <iostream>
#include <math.h>

Go to the source code of this file.

Functions
__global__ void	add (int n, float *x, float *y)
int	main (void)

Function Documentation

add()

__global__ void add	(	int	n,
		float *	x,
		float *	y
	)

Definition at line 4 of file _gpu_mtx_add.cu.

                                               {
    for (int i = 0; i < n; i++)
        y[i] = x[i] + y[i];
}

main()

int main

(

void

)

Definition at line 9 of file _gpu_mtx_add.cu.

               {
    int N = 1 << 20;
    float *x, *y;
 
    // Allocate Unified Memory – accessible from CPU or GPU
    cudaMallocManaged(&x, N * sizeof(float));
    cudaMallocManaged(&y, N * sizeof(float));
 
    // initialize x and y arrays on the host
    for (int i = 0; i < N; i++) {
        x[i] = 1.0f;
        y[i] = 2.0f;
    }
 
    // Run kernel on 1M elements on the GPU
    add<<<1, 1>>>(N, x, y);
 
    // Wait for GPU to finish before accessing on host
    cudaDeviceSynchronize();
 
    // Check for errors (all values should be 3.0f)
    float maxError = 0.0f;
    for (int i = 0; i < N; i++)
        maxError = fmax(maxError, fabs(y[i] - 3.0f));
    std::cout << "Max error: " << maxError << std::endl;
 
    // Free memory
    cudaFree(x);
    cudaFree(y);
 
    return 0;
}

References N.