Yes, it was MPICH, not LAM/MPI. I'm sorry for this confusion.
----- Original Message -----
From: "Jeff Squyres" <jsquyres_at_[hidden]>
To: "General LAM/MPI mailing list" <lam_at_[hidden]>
Sent: Sunday, February 06, 2005 8:58 PM
Subject: Re: LAM: problem with MPI_Isend
> Are you sure that you're using LAM/MPI? That error message does not
> appear in our source code anywhere.
>
> I *do* see this error message in the ROMIO source code (in parts that
> are not used by LAM/MPI), which leads me to believe that you are using
> MPICH. If this is the case, you'll need to contact the MPICH
> developers for support.
>
> Thanks.
>
>
> On Feb 5, 2005, at 7:15 AM, Angel Tsankov wrote:
>
>> MPI_Request Req = MPI_REQUEST_NULL;
>> double a;
>> MPI_Isend(&a,1,MPI_DOUBLE,MPI_PROC_NULL,1,MPI_COMM_WORLD,&Req);
>> MPI_Status StatusSend;
>> MPI_Wait( &Req, &StatusSend );
>>
>> This code sets StatusSend.MPI_ERROR to -858993460 and MPI_Error_string
>> (called with this error code) returns "m * nprocs is < array_size and
>> is not valid for a block(m) distribution".
>>
>> What's wrong?
>
> --
> {+} Jeff Squyres
> {+} jsquyres_at_[hidden]
> {+} http://www.lam-mpi.org/
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
|
