[Beowulf] building Infiniband 4x cluster questions

Greg Lindahl lindahl at pbm.com
Sun Nov 13 21:23:33 PST 2011


> Is that for an MPI message ?  I'd heard that FDR might
> have higher latencies due to the coding changes that
> were happening - is this not the case ?

When you're asking about MPI latency, are you interested in a 2-node
cluster, or a big one? The usual MPI latency benchmark only uses 1
core each on 2 nodes, and on some interconnects, that's a very
different latency than what you'll see on 16 nodes or 100s of nodes.

-- greg




More information about the Beowulf mailing list