[并行] 并行效率低，求解答

program test1
   implicit none
   integer,parameter::nscanpts = 8
   integer:: n=150000,m=1000000
   integer i,j,k
   real time1,time2,timescan(nscanpts),time3,time4
   integer rel(nscanpts)
   
   rel = 0
   call cputime(time3)
   !$OMP PARALLEL SHARED(n,rel,timescan,m), PRIVATE(i,time1,time2)
   !$OMP DO
   do i = 1, nscanpts
      write(*,*) "iscan=",i
      call cputime(time1)
      do j = 1,n
         do k = 1,m
            rel(i) = rel(i) + k * j
         end do
      end do
      call cputime(time2)
      timescan(i) = time2-time1
   end do
   !$OMP END DO
   !$OMP END PARALLEL
   call writeTime(nscanpts,timescan)
   call writeResult(nscanpts,rel)
   call cputime(time4)
   
   write(*,*) "Time=",time4-time3
 end program
 subroutine cputime(t)
       implicit none
       real, intent(out) :: t
       integer  date_time(8)
       character (len=10)    big_ben(3)
       call date_and_time(big_ben(1),big_ben(2),big_ben(3),date_time)
       t = date_time(5)*3600 + date_time(6)*60 + date_time(7)+ &
           date_time(8)*1.0d-3   
           
       return
 end subroutine cputime  
 !****************************************************************
 !
 subroutine writeTime(n,time)
       implicit none
       integer, intent(in)  :: n
       real, intent(in)  :: time(n)
       integer:: fid=40, i
       open (fid, file = 'timescan.dat', status = 'unknown')
       write(fid,'(e16.8)') (time(i), i=1,n)
       close(fid)
       return
 end subroutine writeTime
 subroutine writeResult(n,r)
       implicit none
       integer, intent(in)  :: n
       integer, intent(in)  :: r(n)
       integer:: fid=41, i
       open (fid, file = 'results.dat', status = 'unknown')
       write(fid,'(i16)') (r(i), i=1,n)
       close(fid)
       return
 end subroutine writeResult

!$OMP PARALLEL DO reduction(+:rel)
   do i = 1, nscanpts
      write(*,*) "iscan=",i
      call cputime(time1)
      do j = 1,n
         do k = 1,m
            rel(i) = rel(i) + k * j
         end do
      end do
      call cputime(time2)
      timescan(i) = time2-time1
   end do

   call writeTime(nscanpts,timescan)
   call writeResult(nscanpts,rel)
   call cputime(time4)

   write(*,*) "Time=",time4-time3
    end program

  nThreads = nscanpts  
  Write(*,*) 'This Program will use',nThreads,' threads'  
  call omp_set_num_threads( nThreads )