Il giorno 12/ott/07, alle ore 11:29, David van der Spoel ha scritto:
Ivano Eberini wrote:Dear all,we have just installed GROMACS-3.3.2 on a BlueGene (BG/L) cluster, compiling it without FORTRAN. Do you deem it could be better to recompile it adding "--enable- fortran"?the proof of the pudding is in the eating. please try it.
Dear David,here are the results for two runs (full.mdp in speptide folder of GROMACS tutorial) with 16 chips / 32 tasks on BG/L,
without FORTRAN:
NODE (s) Real (s) (%)
Time: 161.000 161.000 100.0
2:41
(Mnbf/s) (GFlops) (ns/day) (hour/ns)
Performance: 12.529 3.034 5.366 4.472
with FORTRAN:
NODE (s) Real (s) (%)
Time: 155.000 155.000 100.0
2:35
(Mnbf/s) (GFlops) (ns/day) (hour/ns)
Performance: 13.021 3.143 5.574 4.306
Best regards,
Ivano
--
Ivano Eberini
Gruppo di Studio per la Proteomica e la Struttura delle Proteine
Dipartimento di Scienze Farmacologiche
Università degli Studi di Milano
Via Giuseppe Balzaretti, 9
20133 - Milano
tel.: +39-02-50318395, fax: +39-02-50318284
"Quelli che scavano il sole, cercando un'ombra migliore"
smime.p7s
Description: S/MIME cryptographic signature
_______________________________________________ gmx-users mailing list [email protected] http://www.gromacs.org/mailman/listinfo/gmx-users Please search the archive at http://www.gromacs.org/search before posting! Please don't post (un)subscribe requests to the list. Use the www interface or send it to [EMAIL PROTECTED] Can't post? Read http://www.gromacs.org/mailing_lists/users.php
