err = clSetKernelArg(kernel, 6, sizeof(int), &colsB); gpuerr(clSetKernelArg);
//Run the program
- err = clEnqueueNDRangeKernel(cpx_mtx_command_queue, kernel, 2, NULL, (size_t[]){rowsR, colsR}, (size_t[]){64, 64}, 0, NULL, NULL);
+ err = clEnqueueNDRangeKernel(cpx_mtx_command_queue, kernel, 2, NULL, (size_t[]){rowsR, colsR}, (size_t[]){32, 32}, 0, NULL, NULL);
gpuerr(clEnqueueNDRangeKernel);
//Wait for completion