__kernel void mat_mul( __global int* out, int widthA, int heightA, int widthB, int heightB, __global int * inputA, __global int * inputB) { int row = get_global_id(1); int col = get_global_id(0); int sum = 0; for (int i = 0; i < widthA; i++) { sum += inputA[row * widthA + i] * inputB[i * widthB + col]; } out[row * widthB + col] = sum; }