#pragma OPENCL EXTENSION cl_khr_byte_addressable_store : enable

__kernel void matrix_mult(__global float* C, __global float* A, __global float* B, int widthA, int widthB) {
   int x = get_global_id(0);
   int y = get_global_id(1);

   float value = 0;
   for(int k = 0; k < widthA; k++) {
      float elemA = A[y * widthA + k];
      float elemB = B[k * widthB + x];
      value += (elemA * elemB);
   }

   C[y * widthA + x] = value;
}