using System;

public class GlobalFFT {
 movable FFT( double[] zRe, double[] zIm, int processorNumber,
                    Channel( double[], double[], int ) channelZ ) {
  int np = CommWorld.Size;
  if ( np > 1 ) np -= 1; // When the program runs in distributed mode then cluster's frontend is included in CommWorld.Size
  int partLength = zRe.Length / np;
  int shift = processorNumber * partLength;
  double[] partOfZRe = new double [partLength];
  double[] partOfZIm = new double [partLength];
  double multiplier = 2 * Math.PI / (double) zRe.Length;
  for ( int k = 0; k < partLength; k++ ) {
   for ( int j = 0; j < zRe.Length; j++ ) {
    double arg = multiplier * (j + 1) * (k + shift + 1);
    double cos = Math.Cos( arg );
    double sin = Math.Sin( arg );
    partOfZRe [k] += zRe [j] * cos + zIm [j] * sin;
    partOfZIm [k] += zIm [j] * cos - zRe [j] * sin;
   }
  }
  channelZ.Send( partOfZRe, partOfZIm, processorNumber );
 }

 void Get( ref double[] ZRe, ref double[] ZIm ) &
   Channel CZ( double[] partOfZRe, double[] partOfZIm, int processorNumber ) {
  int shift = processorNumber * partOfZRe.Length;
  for ( int i = 0; i < partOfZRe.Length; i++ ) {
   ZRe [i + shift] = partOfZRe [i];
   ZIm [i + shift] = partOfZIm [i];
  }
 }

 public static void Main( string[] args ) {
  GlobalFFT fft = new GlobalFFT();
  int m = Int32.Parse( args [0] );
  Random r = new Random();
  double[] zRe = new double [m];
  double[] zIm = new double [m];
  for ( int i = 0; i < m; i++ ) { zRe [i] = r.NextDouble(); zIm [i] = r.NextDouble(); }
  int np = CommWorld.Size;
  if ( np > 1 ) np -= 1;
  for ( int k = 0; k < np; k++ ) fft.Calculate( zRe, zIm, k, fft.CZ );
  for ( int k = 0; k < np; k++ ) fft.Get( ref zRe, ref zIm );
 }
}