A High-Performance Parallel FDTD Method Enhanced by Using SSE Instruction Set

Algorithm 2

//allocate the 1D memory

array_name_tmp = (float*)_aligned_malloc(

 sizeof (float) * x_size * y_size * z_size, 16);

array_name = (float ***)_aligned_malloc (

 sizeof (float**) * x_size, 16);

 for(i = 0; i < x_size; i++) {

  array_name [i] = (float **)_aligned_malloc

   (sizeof (float*) * y_size, 16);

  for(j = 0; j < y_size; j++) {

   //map the 1D memory address to 3D array

   map_address = i * y_size * z_size + j * z_size;

   array_name [i][j] = &array_name_tmp [map_address];

}}