[Beowulf] More cores/More processors/More nodes?
prw at ceiriog.eclipse.co.uk
Thu Sep 28 11:06:14 PDT 2006
Please enlighten a baffled newbie:
Now there are motherboards with 8 sockets; quad-core processors; and
with as many nodes as you can shake a stick at.
It seems there are at least 3 dimensions for expansion. What (in your
opinion) is the right tradeoff between more cores, more processors and
individual compute nodes?
In particular, I am thinking of in-house parallel finite difference /
finite element codes,
parallel BLAS, and maybe some commercial Monte-Carlo codes (the last
embarrassingly parallel problem).
I have been set the task of building our first cluster for these
Our existing in-house codes run on an SGI machine with a parallelizing
They would need to be ported to use MPI on a cluster. However, I do not
what happens when you have multi-processor/multi-core nodes in a
cluster. Do you
just use MPI (with each thread using its own non-shared memory) or is
way to do "mixed-mode" programming which takes advantage of shared
memory within a
node (like, an MPI/OpenMP hybrid?).
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 189 bytes
Desc: This is a digitally signed message part
More information about the Beowulf