LAM/MPI General User's Mailing List Archives

From: Wa-Kun Lam (rexchaos_at_[hidden])
Date: 2003-09-26 05:06:17

• Next message: Wa-Kun Lam: "LAM: about plotting software"
• Previous message: Irshad Ahmed: "LAM: Installing LAM"
• Next in thread: Jeremy Archuleta: "Re: LAM: FFTW is not that good !?"
• Reply: Jeremy Archuleta: "Re: LAM: FFTW is not that good !?"

hi all,
  It's some problem while using FFTW in LAM/MPI. I have written a
program to test the efficiency.

for (idx=0; idx<5000; idx++)
{
  fftw_mpi(forward_plan, 4096, mydata, outdata);
  if (rank==0)
  {
    // processing outdata here
  }
  fftw_mpi(backward_plan, 4096, outdata, mydata);
}

I found that the efficiency of the above code, running in a 8-node
parallel network, is not better than that running in a single machine !!!

I wonder if anything wrong with my code or FFTW in MPI is not as good as
we expect.

• Next message: Wa-Kun Lam: "LAM: about plotting software"
• Previous message: Irshad Ahmed: "LAM: Installing LAM"
• Next in thread: Jeremy Archuleta: "Re: LAM: FFTW is not that good !?"
• Reply: Jeremy Archuleta: "Re: LAM: FFTW is not that good !?"