[Beowulf] Slection from processor choices; Requesting Giudence

[Geoff Jacobs]

laytonjb at charter.net wrote:
<snip>
> Sure. This is for one specific CFD code. Let's assum that MPICH 1 is the basline.
> MPICH2 was twice as fast (half the run time). LAM was 30% faster than MPICH2.
> Scali MPI Connect was 20% faster than LAM. Altogether, Scali MPI Connect
> was twice as fast as MPICH1.
> 
> Is this what you were looking for?
> 
> Jeff
> 

Yes, thanks. How well did LAM scale beyond 2^4 nodes compared to the others?

-- 
Geoffrey D. Jacobs

Go to the Chinese Restaurant,
Order the Special