On Jan 26, 2009, at 4:33 PM, Nifty Tom Mitchell wrote:
I suspect the most common transport would be TCP/IP and that would
introduce
gateway and routing issues between quick fabrics and other quick
fabrics
that would be intolerable for most HPC applications (but not all).
It may be that IPoIB would be a sufficient communication layer for
Infiniband
fabrics but would not address Myrinet or GigE+ links. Gateways and
bridges would have to come to the party.
I think the prevalent attitude would be: "if you have a low latency
network, why hobble yourself with IP over <native>?"
On this point...
but I'm pretty sure that OMPI failed when used with QLogic and
Mellanox HCAs in a single MPI job. This is fairly unsurprising,
given
if OMPI was compiled to use the QLogic PSM layer then it would
interoperate best with PSM capable hardware. Since QLogic sells
multiple
HCAs including Mellanox design HCAs it is incorrect to make a blanket
statement that QLogic HCAs do not inter-operate with Mellanox.
Note that I did not say that. I specifically stated that OMPI failed
and it is due to the fact that we are customizing for the individual
hardware devices. To be clear: this is an OMPI issue. I'm asking (at
the request of the IWG) if anyone cares about fixing it.
--
Jeff Squyres
Cisco Systems
