Hi,
You don't even need a hostfile.
$ lamboot -v
will make a lam universe out of your lonesome node, then
mpirun -np N application.x
will launch application.x over N MPI process.
This is a very handy way for developing MPI codes on yout laptop in the
train or plane...
You could add some printout in the code to investigate if the N MPI
processes are correctly started and which point they reach before getting
killed. Prefixing the output by the rank number may also help to track the
bug.
Best.
Pierre.
On Fri, 8 Oct 2004, ravin sachdeva wrote:
> hi ,
>
> i am working on a project that involves parallel processing so i obviously
> need to use lam...my project involves running a C source code on 4
> processors with each processor exchanging info from one another using
> MPI_send and MPI_Recv calls... i was told that i can simulate a 4 processor
> environment using lam by setting the same hostname 4 times in the hostfile ,
> then running lamboot on the processor and the code should work in parallel
> by giving the ranks 0,1,2,3 to the single processor...
> Here is where i am facing the problem.... the code only executes the rank
> 0's statements and halts when the MPI_Recv call by rank 0 is made giving the
> error:
>
> Rank(0,MPI_COMM_WORLD) : call stack for LAM
> Rank(0,MPI_COMM_WORLD) : MPI_Recv()
> Rank(0,MPI_COMM_WORLD) : main()
>
> and goes back to the shell. its not executing the other rank's(1,2,3)
> statements at all.
>
> is there anywhere that i am going wrong ?? what should i do ?? please
> help ! you are my last hope.
>
> _________________________________________________________________
> All the news that matters. All the gossip from home.
> http://www.msn.co.in/NRI/ Specially for NRIs!
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
--
Soutenez le mouvement SAUVONS LA RECHERCHE :
au national : http://recherche-en-danger.apinc.org/
sur Grenoble : http://recherchegrenoble.free.fr et http://etatsg.free.fr
_/_/_/_/ _/ _/ Dr. Pierre VALIRON
_/ _/ _/ _/ Laboratoire d'Astrophysique (UMR 5571 CNRS)
_/ _/ _/ _/ Observatoire de Grenoble / U. Joseph Fourier
_/_/_/_/ _/ _/ BP 53 F-38041 Grenoble Cedex 9 (France)
_/ _/ _/
_/ _/ _/ http://www-laog.obs.ujf-grenoble.fr
_/ _/ _/ mailto:Pierre.Valiron_at_[hidden]
_/ _/_/ Phone / Fax: +33 (0)4 76.51.47.87 / (0)4 76.44.88.21
|
