[maz]

Hi,

Here is an OpenMP implementation of a Laplace solver (a parallel Fortran code). I can get a good speedup on up to 4 processors, but it does not improve when I use more processors.
Could you please let me know how I can get a better speedup by using more processors?

program lpomp
integer imax,jmax,im1,im2,jm1,jm2,it,itmax
parameter (imax=4001,jmax=4001)
parameter (im1=imax-1,im2=imax-2,jm1=jmax-1,jm2=jmax-2)
parameter (itmax=200)
real*8 u(imax,jmax),du(imax,jmax),umax,dumax,tol
parameter (umax=10.0,tol=1.0e-6)
call omp_set_num_threads(2)
!$OMP PARALLEL DEFAULT(SHARED) PRIVATE(i,j)
!$OMP DO
do j=1,jmax
do i=1,imax-1
u(i,j)=0.0
du(i,j)=0.0
enddo
u(imax,j)=umax
enddo
!$OMP END DO
!$OMP END PARALLEL
it=1
dumax=1.0
!$OMP PARALLEL DEFAULT(SHARED) PRIVATE(i,j)
! Main computation loop
do it=1,itmax
dumax=0.0
!$OMP DO REDUCTION (max:dumax)
do j=2,jm1
do i=2,im1
du(i,j)=0.25*(u(i-1,j)+u(i+1,j)+u(i,j-1)+u(i,j+1))-u(i,j)
dumax=max(dumax,abs(du(i,j)))
enddo
enddo
!$OMP END DO
!$OMP DO
do j=2,jm1
do i=2,im1
u(i,j)=u(i,j)+du(i,j)
enddo
enddo
!$OMP END DO
enddo
!$OMP END PARALLEL
stop
end

Compile: ifort -openmp -parallel Laplace.for

Thanks!