MartixSubstractMatrix.cu

__global__ void kMartixSubstractMatrix(const float *m1, const float *m2, float *output) {
    /*  Computes the (elementwise) difference between two arrays
     Inputs:
     m1: array
     m2: array
     output: array,the results of the computation are to be stored here
     */

    const int id = blockIdx.x * blockDim.x + threadIdx.x;

    output[id] = m1[id] - m2[id];
}

__device__ float* dMartixSubstractMatrix(const float *m1, const float *m2, float *output, const int width, const int height){

	kMartixSubstractMatrix <<< width, height >>> ( m1, m2, output );
    cudaDeviceSynchronize();
    return output;
}