Re: Problems compiling NAMD

From: Jesper Soerensen (jes_at_chem.au.dk)
Date: Tue Oct 07 2008 - 03:50:50 CDT

Hi Alexander,

I'm assuming that if I don't specify a compiler it defaults to gcc?
Then yes I have made a version of gcc without MPI, but once I add MPI it
fails. It seems to be that our MPI has been compiled with either intel
or pgi compilers and so gcc fails because MPI calls some intel keywords.

for example while running Make pgm:
 
>/com/mpich-1.2.7p1/lib/libmpich.a(dmpipk.o)(.text+0x249): In function
>`MPIR_UnPack_Hvector':
>: undefined reference to `_intel_fast_memcpy'

I can ask our sysadmin to make a gcc version of MPI and see if that
helps. Would that be a good idea?

Kind regards,
Jesper

On Mon, 2008-10-06 at 21:00 +0500, Alexander A. Vakhrushev wrote:
> Hi Jesper!
>
> Did you try just gcc version?
>
> 2008/10/6 Jesper Soerensen <jes_at_chem.au.dk>:
> > Hi Alexander,
> >
> > I'm running CentOS 4.3. I've tried using both OpenMPI and MPICH but both
> > fail. I've tried:
> > OpenMPI version 1.2.6
> > MPICH version 1.2.7
> > Using Intel compilers (icc & ifort) version 10.1.017
> >
> > I ran the megatest set from charm++ and I get a failure in test14:
> >
> >> ./mpirun ./pgm
> >> ...
> >> test 14: initiated [tempotest (fang)]
> >> p0_29927: p4_error: interrupt SIGSEGV: 11
> >
> >
> >> mpirun -np 4 -all-local ./pgm
> >> Megatest is running on 4 processors.
> >> ...
> >> test 14: initiated [tempotest (fang)]
> >> p2_30323: p4_error: interrupt SIGSEGV: 11
> >> p3_30346: p4_error: Found a dead connection while looking for
> > messages: 0
> >> [jesper_at_fe1 megatest]$ p1_30297: p4_error: interrupt SIGx: 13
> >> rm_l_2_30324: (10.011719) net_send: could not write to fd=5, errno =
> > 32
> >> rm_l_3_30347: (7.667969) net_send: could not write to fd=5, errno = 32
> >> p2_30323: (12.027344) net_send: could not write to fd=5, errno = 32
> >> p3_30346: (13.675781) net_send: could not write to fd=5, errno = 32
> >> p1_30297: (18.843750) net_send: could not write to fd=5, errno = 32
> >
> > Does anybody recognize this?
> >
> > Kind regards,
> >
> > Jesper
> >
> >
> >
> >
> > On Fri, 2008-10-03 at 22:44 +0500, Alexander A. Vakhrushev wrote:
> >> Hi Jesper!
> >>
> >> What is platform of your cluster?
> >>
> >> 2008/10/3 Jesper Soerensen <jes_at_chem.au.dk>:
> >> > Hi,
> >> >
> >> > I've just compiled NAMD on our cluster and this runs through fine, but
> >> > when I start a job I get the following error in the log file:
> >> >>Info: Entering startup phase 8 with 134856 kB of memory in use.
> >> >>Info: Finished startup with 143120 kB of memory in use.
> >> >>1 additional process aborted (not shown)
> >> >
> >> > And the cluster job-error log says:
> >> >>mpirun noticed that job rank 0 with PID 25232 on node s07n06 exited on
> >> >>signal 11 (Segmentation fault).
> >> >
> >> > I am running a Linux-amd64-MPI-icc-ifort version if this helps. Also, let
> >> > me know if there is more information I can give to help solve the
> >> > problem. I'm just wondering if anybody has seen this type of error
> >> > before.
> >> >
> >> > Kind regards,
> >> >
> >> > Jesper Soerensen
> >> >
> >> >
> >> > --
> >> > Jesper Sørensen, M.Sc.
> >> > Ph.D.-student
> >> > Biomodelling Group, inSPIN and iNANO centers
> >> > Department of Chemistry
> >> > University of Aarhus
> >> > Langelandsgade 140
> >> > 8000 Aarhus C
> >> > Office: 1510-419
> >> > Tlf. 89423385
> >> > email: jes_at_chem.au.dk
> >> > www: www.chem.au.dk/~biomodelling
> >> >
> >> >
> >>
> >>
> >>
> >
> >
>
>
>

This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:49:56 CST