DWarez

#include <stdio.h>

// Macro for checking CUDA errors
#define CUDA_CHECK_ERROR(err) \
    if (err != cudaSuccess) { \
        printf("CUDA err: %s at line %d\n", cudaGetErrorString(err), __LINE__); \
        exit(EXIT_FAILURE); \
    }

// Kernel definition

DWarez

#include <stdio.h>

#define TILE_WIDTH 7
__global__ void matMulKernel(float* A, float* B, float* C, int Width) {
    __shared__ float Ads[TILE_WIDTH][TILE_WIDTH];
    __shared__ float Bds[TILE_WIDTH][TILE_WIDTH];

    int bx = blockIdx.x;
    int by = blockIdx.y;
    int tx = threadIdx.x;