[Beowulf] x86-64 NUMA vs SMP kernel: appl. performance?

[Mikhail Kuzminsky]

     Dear colleagues,

I have possible choice between using of SMP or NUMA-enabled x86_64 
kernels (2.4.21 from SuSE Linux 9.0 distributive). We use 2-way 
Opteron-based nodes w/2 GBytes RAM per node (symmetrical DIMMs 
occupation). 
Our applications are parallelized :-), so we have 2 "computing 
threads"
per each 2-way SMP node.

Have somebody data about relative performance of applications working 
under NUMA vs SMP kernels ? Quantum chemical packages like
Gaussian/Gamess-US/NWchem are the most interesting (their performance
is "memory-bounded"), but at least direct STREAM results are 
interesting
also.

Mikhail Kuzminsky
Zelinsky Institute of Organic Chemistry
Moscow