The problem with the performance of 'pdgetrf': very poor

I want to check the performance of LU factorization on the cluster. So the first, I called pdgetrf routine on the MKL library and execute it in my computer (Intel® Xeon Phi™ Processor 7250). 

Performance of pdgetrf with the size matrix = 20000 is 170Gfops for implement on 4 processes.

Please help me check my code, Does my program have an error? How to improve to performance of pdgetrf on KNL - 7250?  How much is the maximum performance of pdgetrf ?

Thanks a lot.

• This is compiler:

mpiicc pdgetrf.c -O3 -qopenmp -lmemkind -mkl  -xMIC-AVX512 -restrict  \
      -o pdgetrf -I./  -I/opt/intel/compilers_and_libraries_2018.5.274/linux/mkl/include/  -lmkl_scalapack_lp64  -lmkl_core -lmkl_blacs_intelmpi_lp64  -lpthread -liomp5 

• This is for execute:          mpirun -np 4 ./pdgetrf

#include <stdio.h>
#include <time.h>
#include <string.h>
#include <stdlib.h>
#include "mpi.h"



int main(int argc, char **argv) {
   int i, j, k;
/************  MPI ***************************/
   int myrank_mpi, nprocs_mpi;
   MPI_Init( &argc, &argv);
   MPI_Comm_rank(MPI_COMM_WORLD, &myrank_mpi);
   MPI_Comm_size(MPI_COMM_WORLD, &nprocs_mpi);
/************  BLACS ***************************/
   int ictxt, nprow, npcol, myrow, mycol,nb;
   int info,itemp;
   int ZERO=0,ONE=1;
	 nprow = 2; npcol = 2; nb =500;
	 int M=nprow*10000;
	 int K=npcol*10000;

   Cblacs_pinfo( &myrank_mpi, &nprocs_mpi ) ;
   Cblacs_get( -1, 0, &ictxt );
   Cblacs_gridinit( &ictxt, "Row", nprow, npcol );
   Cblacs_gridinfo( ictxt, &nprow, &npcol, &myrow, &mycol );


   int rA = numroc_( &M, &nb, &myrow, &ZERO, &nprow );
   int cA = numroc_( &K, &nb, &mycol, &ZERO, &npcol );

   double *A = (double*) malloc(rA*cA*sizeof(double));

   int descA[9];
   int *IPIV;
	 IPIV = (int *)calloc(rA + nb, sizeof(int));
	 descinit_(descA, &M,   &K,   &nb,  &nb,  &ZERO, &ZERO, &ictxt, &rA,  &info);
   
     double alpha = 1.0; double beta = 1.0;	
     double start, end, flops;
	 srand(time(NULL)*myrow + mycol);
	 #pragma simd
	 for (j=0; j<rA*cA; j++)
	 {
		 A[j]=((double)rand()-(double)(RAND_MAX)*0.5)/(double)(RAND_MAX);
	 }
     
	 MPI_Barrier(MPI_COMM_WORLD);
     start=MPI_Wtime();

	 pdgetrf(&M, &K, A, &ONE, &ONE, descA, IPIV, &info);

	 MPI_Barrier(MPI_COMM_WORLD);
     end=MPI_Wtime();
	 
	double duration = (double)(end - start); 
	 if (myrow==0 && mycol==0)
	 {
      if (M > K)
	  {
	     printf("%f Gigaflops\n", ((double)K * (double)K * (double)M - (double)K * (double)K * (double)K / (double)3) * 1.0e-9 / duration);
	  }
	  else if (K < M)
	  {
	    printf("%f Gigaflops\n", ((double)M * (double)M * (double)K - (double)M * (double)M * (double)M / (double)3) * 1.0e-9 / duration);
      }
	  else
	  {
	    printf("%f Gigaflops\n", ((double)2*(double)K *(double)K * (double)K  / (double)3) * 1.0e-9 / duration);
		
      }
	 // printf("%f Gflops\n", flops);
	 }
   Cblacs_gridexit( 0 );
   MPI_Finalize();
   return 0;
}