Hello,
This is a moderately naïve question: I have been using the Portland Group
compiler package and the free MPICH (1.2.6, 1.2.7p1) implementation of MPI
for parallel compilation of AMBER 8 on Intel Xeon/Red Hat Enterprise
systems, but am considering using the Intel compiler for parallel AMBER 8 in
the future. It seems from reading my mail from the amber reflector, and the
reflector archive, that in general, the recent Intel Fortran compilers work
well with AMBER 8 and MPICH, and that the parallel performance may be better
than with the Portland Group compiler. It is my impression that it is not
necessary to use the Intel Cluster OpenMP for parallel AMBER 8 with the
Intel Fortran compiler 9.1 on Linux systems, and if I understood a recent
e-mail on the reflector correctly, the Cluster OpenMP does not provide such
good performance.
Am I correct? Or am I missing something?
Thanks in advance,
Craig
*****************************************
Craig Gough
Integrated Database Team
Japan Biological Information Research Center (JBIRC)
AIST Waterfront Bio-IT Research Building, 7th Floor
Aomi 2-42, Koto-ku, Tokyo
135-0064
Tel: 03-3599-8810
*****************************************
-----------------------------------------------------------------------
The AMBER Mail Reflector
To post, send mail to amber.scripps.edu
To unsubscribe, send "unsubscribe amber" to majordomo.scripps.edu
Received on Sun Feb 25 2007 - 06:07:30 PST
