[MPICH] Program crashes when multiple threads make MPI Calls

[Rajeev Thakur]

Yes, you need to configure with --enable-threads=multiple.

Rajeev 

> -----Original Message-----
> From: Ashok Babu Amara [mailto:ashok.amara at gmail.com] 
> Sent: Thursday, February 09, 2006 3:22 PM
> To: Rajeev Thakur
> Cc: mpich-discuss at mcs.anl.gov
> Subject: Re: [MPICH] Program crashes when multiple threads 
> make MPI Calls
> 
> I have built MPICH2 1.0.3, but the thread support still seems to be
> MPI_THREAD_FUNNELED, even though I request for MPI_THREAD_MULITPLE in
> MPI_Init_thread.
> 
> Is there any specific parameters that I need to give to ./configure in
> order to support MPI_THREAD_MULITPLE ?
> 
> Thanks,
> - Ashok
> 
> On 2/9/06, Rajeev Thakur <thakur at mcs.anl.gov> wrote:
> > If MPI_Init_thread returns provided=MPI_THREAD_FUNNELED, 
> you can't make MPI
> > calls from multiple threads. MPICH-1 supports only 
> MPI_THREAD_FUNNELED. If
> > you need MPI_THREAD_MULITPLE, you need to use MPICH2.
> >
> > Rajeev
> >
> >
> > > -----Original Message-----
> > > From: owner-mpich-discuss at mcs.anl.gov
> > > [mailto:owner-mpich-discuss at mcs.anl.gov] On Behalf Of 
> Ashok Babu Amara
> > > Sent: Thursday, February 09, 2006 12:44 PM
> > > To: mpich-discuss at mcs.anl.gov
> > > Subject: [MPICH] Program crashes when multiple threads 
> make MPI Calls
> > >
> > > Hi All,
> > >
> > > I am making MPI calls from two threads and it doesn't seem to be
> > > working. I have one thread constantly doing MPI_Send's 
> and MPI_Recv's
> > > and another thread which is constantly doing MPI_Allreduce.
> > >
> > > When I run the program it either hangs or prints this message :
> > > [0] Abort: header->id != c->next_packet_expected at line 
> 730 in file
> > > mpid/vapi/viacheck.c
> > >
> > > The version of MPICH being used is 1.2.6 and the thread 
> level support
> > > is  MPI_THREAD_FUNNELED.
> > >
> > > Can someone advise what is possibly wrong ?
> > >
> > > I have attached the code that is being tested.
> > >
> > > Thanks,
> > > - Ashok
> > >
> >
> >
> 
>