An OpenCL kernel for computing the dot product of two matrices.

matdot.cl

__kernel void matdot(__global double * outputC, int widthA, int heightA, int widthB, int heightB, __global double* inputA, __global double* inputB) {
  int column = get_global_id(0);
  int row = get_global_id(1);

  double sum = 0.0;
  for (int i = 0; i < widthA; i++) {
    sum += inputA[row * widthA + i] * inputB[i * widthB + column];
  }
  outputC[row * widthB + column] = sum;
}