From: Axel Kohlmeyer (akohlmey_at_cmm.chem.upenn.edu)
Date: Mon May 25 2009 - 10:13:13 CDT
On Mon, 2009-05-25 at 14:13 +0300, Marius Micluta wrote:
> Dear NAMD experts,
i cannot comment on many technical details, but...
> Could this be a compiler optimization issue? The MPI version compiles and runs
> fine with the -O2 optimization flag, while the SMP version compiled only with
> -O1. The documentation states that the TCP and SMP versions are not affected by
> this bug and that the +netpoll parameter could be used to circumvent the bug. I
> also tried this parameter, but with no success. An strace reveals that all the
> involved processes (charmrun and namd2) are stuck in an endless poll which
> times out. The compiler version is 10.1.011, the same used to build the
intel 10.1.011 is quite outdated i suggest to update to a more
recent patchlevel. many early intel 10.1.x patchlevels are known
to miscompile codes. the fact that you have to lower optimization
to get the code compiled, confirms that the code is straining the
> hardware manufacturer's MPI libraries.
> I would be very grateful for any help or suggestion related to the
> above-mentioned problems.
> Kind regards,
> Marius Micluta
> Institute of Biochemistry of the Romanian Academy
-- ======================================================================= 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 - 15:52:51 CST