LFBS Home Lehrstuhl für Betriebssysteme RWTH
Disclaimer/
Haftungsausschluss
Webmaster
(admin@lfbs...)
Home > Research > MP-MPICH > Performance > NT-MPICH Performance > PMB Results  

Pallas MPI Benchmarks Results


Here are the results of the Pallas MPI Benchmarks:

Interconnections MPI implementations Number of nodes Processes per node
Fast Ethernet NT-MPICH, MPICH.NT, MPI/Pro, WMPI 8 1
Gigabit Ethernet NT-MPICH, MPICH.NT, MPI/Pro, WMPI 1) 8 1
Shared Memory NT-MPICH, MPICH.NT, WMPI 2) 1 8
Fast & Gigabit Ethernet NT-MPICH 8 1
       
SCI, Gigabit Ethernet SCI-MPICH, NT-MPICH planned



1) We had to turn off some internal optimizations in MPI/Pro for message sizes up to 256kB (using the command line argument -msti_tcp_pin_size 300000) because otherwise we noticed some very heavy performance drops in some benchmarks with message sizes between 64kB and 256kB.

2) We could not benchmark MPI/Pro because our evaluation license had unexpectedly expired.

Print Version