Question

I am currently working on a project where I need to implement a parallel fft algorithm using openmpi. I have a compiling piece of code, but when I run it over the cluster I get segmentation faults.

I have my hunches about where things are going wrong, but I don’t think I have enough of an understanding about pointers and references to be able to make a efficient fix.

The first chunk that could be going wrong is in the passing of the arrays to the helper functions. I believe that either my looping is inconsistent, or I am not understanding how the to pass these pointers and get back the things I need.

The second possible spot would be within the actual mpi_Send/Recv commands. I am sending a type that is not supported by the openmpi c datatypes, so I am using the mpi_byte type to send the raw data instead. Is this a viable option? Or should I be looking into an alternative to this method.

/* function declarations */
double complex get_block(double complex c[], int start, int stop);

double complex put_block(double complex from[], double complex to[], 
            int start, int stop);

void main(int argc, char **argv)
{
  /* Initialize MPI */
  MPI_Init(&argc, &argv);

  double complex c[N/p];
  int myid;
  MPI_Comm_rank(MPI_COMM_WORLD, &myid);
  //printf("My id is %d\n",myid);

  MPI_Status status;

  int i;
  for(i=0;i<N/p;i++){
    c[i] = 1.0 + 1.0*I;
  }

  int j = log(p)/log(2) + 1;
  double q;
  double complex z;
  double complex w = exp(-2*PI*I/N);
  double complex block[N/(2*p)]; // half the size of chunk c
  int e,l,t,k,m,rank,plus,minus;
  int temp = (log(N)-log(p))/log(2);
  //printf("temp = %d", temp);

  for(e = 0; e < (log(p)/log(2)); e++){
    /* loop constants */
    t = pow(2,e); l = pow(2,e+temp);
    q = n/2*l; z = cpow(w,(complex)q); 
    j = j-1; int v = pow(2,j);

    if(e != 0){
      plus = (myid + p/v)%p;
      minus = (myid - p/v)%p;
    } else {
      plus = myid + p/v;
      minus = myid - p/v;
    }

    if(myid%t == myid%(2*t)){
      MPI_Recv((char*)&c, 
           sizeof(c),
           MPI_BYTE,
           plus,
           MPI_ANY_TAG,
           MPI_COMM_WORLD,
           &status);

      /* transform */
      for(k = 0; k < N/p; k++){
    m = (myid * N/p + k)%l;
    c[k] = c[k] + c[k+N/v] * cpow(z,m);
    c[k+N/v] = c[k] - c[k + N/v] * cpow(z,m); 
    printf("(k,k+N/v) = (%d,%d)\n",k,k+N/v);
    }*/
      printf("\n\n");
      /* end transform */

      *block = get_block(c, N/v, N/v + N/p + 1);
      MPI_Send((char*)&block,
           sizeof(block),
           MPI_BYTE, 
           plus,
           1, 
           MPI_COMM_WORLD);
    } else {
      // send data of this PE to the (i- p/v)th PE
      MPI_Send((char*)&c,
           sizeof(c),
           MPI_BYTE,
           minus,
           1, 
           MPI_COMM_WORLD);
      // after the transformation, receive data from (i-p/v)th PE
      //      and store them in c:
      MPI_Recv((char*)&block,
           sizeof(block),
           MPI_BYTE,
           minus, 
           MPI_ANY_TAG, 
           MPI_COMM_WORLD,
              &status);

      *c = put_block(block, c, N/v, N/v + N/p - 1);
      //printf("Process %d send/receive %d\n",myid, plus);
    }
  }
  /* shut down MPI */
  MPI_Finalize();
}

/* helper functions */
double complex get_block(double complex *c, int start, int stop)
{
  double complex block[stop - start + 1];
  //printf("%d = %d\n",sizeof(block)/sizeof(double complex), sizeof(&c)/sizeof(double  complex));
  int j = 0;
  int i;
  for(i = start; i < stop+1; i++){
    block[j] = c[i];
    j = j+1;
  }
  return *block;
}


double complex put_block(double complex from[], double complex to[], int start, int stop)
{  
  int j = 0;
  int i;
  for(i = start; i<stop+1; i++){
    to[i] = from[j];
    j = j+1;
  }
  return *to;
}

I really appreciate the feedback!

Answer 1

You are using arrays / pointers to arrays in the wrong way. For example you declare an array as double complex block[N], which is fine (although uncommon, in most cases it is better to use malloc) and then you receive into it via MPI_Recv(&block). However “block” is already a pointer to that array, so by writing “&block” you are passing the pointer of the pointer to MPI_Recv. That’s not what it expects. If you want to use the “&” notation you have to write &block[0], which would give you the pointer to the first element of the block-array.