Re: Problems compiling NAMD

From: Axel Kohlmeyer (akohlmey_at_cmm.chem.upenn.edu)
Date: Tue Oct 07 2008 - 11:54:21 CDT

On Tue, 7 Oct 2008, Jesper Soerensen wrote:

JS> Hi Alexander,
JS>
JS> I'm assuming that if I don't specify a compiler it defaults to gcc?
JS> Then yes I have made a version of gcc without MPI, but once I add MPI it
JS> fails. It seems to be that our MPI has been compiled with either intel
JS> or pgi compilers and so gcc fails because MPI calls some intel keywords.
JS>
JS> for example while running Make pgm:
JS>
JS> >/com/mpich-1.2.7p1/lib/libmpich.a(dmpipk.o)(.text+0x249): In function
JS> >`MPIR_UnPack_Hvector':
JS> >: undefined reference to `_intel_fast_memcpy'
JS>
JS> I can ask our sysadmin to make a gcc version of MPI and see if that
JS> helps. Would that be a good idea?

yes. one - easier to achieve - alternative, would be to reduce
the optimization level in the respective "arch" files. compilers
become increasingly unreliable with higher optimization levels.
with intel compilers, i found that a combination of flags like

-O2 -unroll -march=pentiumpro -mtune=pentiumpro -pc64

produces fast and reliably working executables on AMD cpus.

i would also, in case you are still getting segmentation
faults, remove the -ip flag.

cheers,
   axel.

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

-- 
=======================================================================
Axel Kohlmeyer   akohlmey_at_cmm.chem.upenn.edu   http://www.cmm.upenn.edu
   Center for Molecular Modeling   --   University of Pennsylvania
Department of Chemistry, 231 S.34th Street, Philadelphia, PA 19104-6323
tel: 1-215-898-1582,  fax: 1-215-573-6233,  office-tel: 1-215-898-5425
=======================================================================
If you make something idiot-proof, the universe creates a better idiot.

This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:48:24 CST