No worries - when by mid februari all components from ebay arrived and i've setup a small cluster here i hope to write some MPI benchmarks that do all sorts of latency tests which i'll attach GPL header to, and which should measure from latency to bandwidth using RDMA reads mostly,
with all cores of every node busy. Will be interesting then to compare it all. Maybe several over here want to benchmark. When i first designed the latency benchmark, later on Paul Hsieh managed to make the ideas implementation a bit more efficient. I jumped with a random generator through the memory, Paul Hsieh had optimized it to just jumping random. Dieter Buerssner then wrote the test for single cpu to compare whether it was similar to output i got - which appeared to be the case. Setting up random pattern took very long though - then i optimized to setup the random pattern to O ( n log n ). The advantage of all this is that one really sees the impact with all cores at the same time, whereas most tests use a total idle cluster and test 1 microtiny thing. Vincent _______________________________________________ Beowulf mailing list, [email protected] sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
