mpi dot product using point to point operations fails when data is large -

i have below code 2 dot product of 2 vectors of size vectorsize. code works fine until vectorsize 10000 gives unrelated results. when tried debug program have seen processor 0 (root) finishes job before processors send local results. got same situation when utilized mpi_reduce() (code part 2). if use mpi_scatter() before mpi_reduce() ok.

#include <stdio.h> #include <stdlib.h> #include "mpi.h"  #define vectorsize 10000000 #define root 0   //[[## operation constructvectorpart() void constructvector(double * vector, int size, short vectorenu) {   int = 0;     if(vectorenu == 1) // i.e vector 1     {         for(i = 0; < size; i++)         {             vector[i] = 0.1 + (i%20)*0.1;         }     }     else if(vectorenu == 2) // i.e. vector 2     {         for(i = 0 ; < size; i++)         {             vector[i] = 2-(i%20)*0.1;         }     } }  //[[## operation dotproduct() double dotproduct(double* a, double* b, int length)  {   double result = 0;     int = 0;    (i = 0; i<length; i++)         result +=  a[i] * b[i];    return result; }  int main( argc, argv ) int  argc; char **argv; {   int processorid, numofprocessors;     int partialvectorsize ;     double t1, t2, localdotproduct, result;    mpi_init( &argc, &argv );   mpi_comm_size( mpi_comm_world, &numofprocessors );   mpi_comm_rank( mpi_comm_world, &processorid );      if(processorid == 0)         t1 = mpi_wtime();      // processors constitute own vector parts ,      // calculates corresponding partial dot products     partialvectorsize = vectorsize/ numofprocessors;       double *v1, *v2;     v1 = (double*)(malloc((partialvectorsize) * sizeof(double)));     v2 = (double*)(malloc((partialvectorsize) * sizeof(double)));      constructvectorpart(v1,0,partialvectorsize,1);     constructvectorpart(v2,0,partialvectorsize,2);      localdotproduct = dotproduct(v1,v2, partialvectorsize);      printf(" processor %d \n",processorid);  //----------------- code part 1 ---------------------------------------------        if( processorid != 0 ) // if not master     { // send partial result master         mpi_send( &localdotproduct, 1, mpi_double, 0,0, mpi_comm_world );     }     else // master     {  // collect results       result = localdotproduct; // own result         int j;         for( j=1; j<numofprocessors; ++j )         {             mpi_recv( &localdotproduct, 1, mpi_double, j, 0, mpi_comm_world,mpi_status_ignore);             result += localdotproduct;         }         t2 = mpi_wtime();         printf(" result = %f  timeconsumed = %f \n",result, t2-t1);     }  //----------------------------------------------------------------------------       /*    //--------------------- code part 2 ----------------   mpi_reduce(&localdotproduct, &result, 1, mpi_double, mpi_sum, 0,mpi_comm_world);      if(processorid == 0)     {             t2 = mpi_wtime();             printf(" result = %f  timeconsumed = %f \n",result, t2-t1);     }     //---------------------------------------------------     */      mpi_finalize();          free(v1);         free(v2);      return 0; }