[Wien] Highest performance within Opteron

[Saeid Jalali]

    Dear WIEN2k community,
      We are going to build a cluster using the following hardware:
      64 homogenous nodes of AMD-Opteron dual CPU, 2.2 GHz , 1-Gigabit  network (2 cards per node),  2GB RAM per node.
      To increase the performance of the above hardware in running  WIEN2k in parallel mode employing simultaneously both k-point and fine grained  parallelizations, we would install the best  FORTRAN, and MPI compilers, as well as  libraries.
      Since there are several versions of MPI, e.g. mpich, lanmpi,  
, we are not sure which one has the highest performance. This is the case also  for the FORTRAN compilers.
      Further comments (in particular on the version of MPI) besides  the current benchmark:
      http://www.wien2k.at/reg_user/benchmark/
      and what one could find in the FAQ, e.g. http://www.wien2k.at/reg_user/faq/OptimizingWIEN2k.htm
      can help us to reach the highest performance for running  WIEN2k.
      We are not also aware whether there exist curves of WIEN2k performances  versus the number of nodes. Any comments will indebt us to you.
    

Sincerely yours,
S. Jalali.
/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/
Saeid Jalali Asadabadi,
Department of Physics, Faculty of Science,
University of Isfahan (UI), Hezar Gerib Avenue,
81744 Isfahan, Iran.
Phones:
Dep. of Phys.      :+98-0311-793 2435
Office             :+98-0311-793 2430
Fax No.            :+98-0311-793 2409
E-mail             :s_jalali_a at yahoo.com
www                :http://www.ui.ac.ir
/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/_/
 			
---------------------------------
Do you Yahoo!?
 Everyone is raving about the  all-new Yahoo! Mail Beta.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://zeus.theochem.tuwien.ac.at/pipermail/wien/attachments/20060816/8f6ff5fa/attachment.html