Data initialize task on scalapack with C file

Hello,

i want to use some scalapacks' functions. but i confuse to set initial data form in scalapack, so i asked it here.

i have understood the data layout like figure below, and made code, too.

test code what i coded (pdgeqrf) like below :

#include <stdio.h>
#include <stdlib.h>
#include <malloc.h>
#include <time.h>
#include <mpi.h>
#include <mkl_blacs.h>
#include <mkl_scalapack.h>
#include <mkl_lapacke.h>
#include <mkl_cblas.h>
#include <errno.h>



int main(int    argc,
         char **argv)
{
  int i,j;
  // test parameters (default)
  int m      = 4000;
  int n      = 4000;
  int mb     = 8;
 int nb     = 8;
  int nprows = 8;
 int npcols = 8; // temp values

 // parameter value change (optional)
  if(argc >=5){
    m=atoi(argv[1]);
    n=atoi(argv[2]);
    nprows=atoi(argv[3]);
    npcols=atoi(argv[4]);
  
  }

  // time and validity
  double startTime;
  double endTime;
  double gap;
  double flops;

 //QR
 double * A;
 double * tau;
 double * work;

  int mpirank, mpisize;
  MPI_Init(&argc, &argv);
  MPI_Comm_rank(MPI_COMM_WORLD, &mpirank);
  MPI_Comm_size(MPI_COMM_WORLD, &mpisize);

  int myid, numproc, ctxt, myrow, mycol;
  MKL_INT descA[9];
  MKL_INT zero = 0;
 MKL_INT one = 1;
 MKL_INT info = 0;

  Cblacs_pinfo(&myid, &numproc);
  if(numproc > 1 && myid != 0){
    Cblacs_setup(&myid, &numproc);
  }
  Cblacs_get(-1, 0, &ctxt);
  Cblacs_gridinit(&ctxt, "R", nprows, npcols);
  blacs_gridinfo_(&ctxt, &nprows, &npcols, &myrow, &mycol);

  if(myrow == -1){
    return 0;
  }

 /*
  * temp value for fortran
  */
 char aform = 'N';
 char diag = 'N';
 MKL_INT lda = m;
 MKL_INT iarow = 0;
 MKL_INT iacol = 0;
 MKL_INT iseed = 10;
 MKL_INT iroff = 0;
 MKL_INT irnum = numroc_(&m, &mb, &myrow, &zero, &nprows);
 MKL_INT icoff = 0;
 MKL_INT icnum = numroc_(&n, &nb, &mycol, &zero, &npcols);
 MKL_INT lwork = -1;

 //descinit(desc,  m,  n,  mb,  nb, irsrc, icsrc, ictxt, LLD, info)
  descinit_(descA, &m, &n, &mb, &nb, &zero, &zero, &ctxt, &icnum, &info);
 A = (double*)malloc(sizeof(double)*irnum*icnum);
 tau = (double*)malloc(sizeof(double)*(m*n/2)); //array size should >= LOCc(ja+min(m,n)-1)
 work = (double*)malloc(sizeof(double)*m*n);

 //pdmatgen_(&ctxt, &aform, &diag, &m, &n, &mb, &nb, A, &m, &iarow, &iacol, &iseed, &iroff, &irnum, &icoff, &icnum, &myrow, &mycol, &nprows, &npcols);


 /*
  *  generate matrix (by column major)
  *
  * matrix      : A
  * size        : irnum * icnum
  * seed        : 10
  */
  for(j = 0; j < irnum; ++j)
  {
    for(i = 0; i < icnum; ++i)
    {
      A[i*irnum+j] = rand()%10;
    }
  }

  printf("QR valid test (MPI)\n");

 
 // pdgeqrf routine
 MPI_Barrier(MPI_COMM_WORLD);
  startTime = MPI_Wtime();
 pdgeqrf_(&m,&n,A,&one,&one,descA,tau,work,&lwork,&info);
  //info = dgeqrf(LAPACK_COL_MAJOR, m, n, A, m, tau, descA, mpirank);
 MPI_Barrier(MPI_COMM_WORLD);
  endTime = MPI_Wtime();

  // flops
  gap = (double)( endTime - startTime );
  flops = (2.0 * (double)n * (double)n * (double)(m-n/3) ) * 1.0e-9 / gap;
  printf("info\t%d, dgemm time (sec)\t%f, Gflops\t%f \n", info, gap, flops);
 
  Cblacs_gridexit(ctxt);
  Cblacs_exit(&zero);
  MPI_Finalize();
   
  free(A);
  free(tau);
 free(work);
  return 0;
}

i have compiled my code like this :

 mpiicc scalapack_test2.c -lmkl_scalapack_lp64 -lmkl_blacs_intelmpi_lp64 -mkl

i've comfirmed the result value 0 correctly, but there is some weird things especially speed things.

in addition, i couldn't check this result is right or not. i'm not sure of  initializing data set value exactly.

this is result texts what i confirmed.

//  form : ./a.out m n nprow npcol

[@localhost src]$ mpirun -n 4 ./a.out 6400 6400 2 2
QR valid test (MPI)
QR valid test (MPI)
QR valid test (MPI)
QR valid test (MPI)
info    0, dgemm time (sec)     0.001011, Gflops        345703.851960
info    0, dgemm time (sec)     0.001003, Gflops        348580.607742
info    0, dgemm time (sec)     0.001141, Gflops        306337.241154
info    0, dgemm time (sec)     0.001143, Gflops        305826.040084

[@localhost src]$ mpirun -n 1 ./a.out 6400 6400 1 1
QR valid test (MPI)
info    0, dgemm time (sec)     0.000237, Gflops        1474979.915656

could you give me some advise what i miss understand or miss used? if you give me good example of this, i'm really thank for you.