I am building a cluster and i was wondering what would be more important, memory with lower latency (cas 2 compared to cas 3) or more memory( 512 megs compared to 1 gig). Is memory latency a bottleneck in clustered computering or is it usually memory size that is the bottleneck. Also would it be better to have 20 smp machines or 40 single processor machines( both of which would be connected by 100base-t).If anybody could point me to some benchmarks that would be very helpful also.
thanks rob
