[Beowulf] 1.2 us IB latency?

[Peter Kjellstrom]

On Tuesday 27 March 2007, Mark Hahn wrote:
> http://www.hpcwire.com/hpc/1336731.html
>
> well, if the numbers mean what they appear to mean, this is quite
> a dramatic breakthrough: 1.2 us, 25M msg/s.  since we just happend to
> be talking about "conventional" IB vs Infinipath (1.29 us, 11.3M msg/s).
>
> or is this an example of message aggregation?  heck, from the url
> above, it might even be counting intra-box messages.

Nope, this is "normal" ping-pong for the new generation cards (connectx). 
Maybe a bit optimistic though, I'd expect closer to 1.5 in a back-to-back 
config.

> also, I'm sorta amazed people keep selling (and presumably buying)
> dual-port IB cards.  doesn't that get quite expensive, switch-wise?

Not defending them but, It could possibly maybe be useful if you have a 
stand-alone IB net for, say, storage or something else not mpi. Also, it's 
not like they're that much more expensive than single port ones...

/Peter

> regards, mark hahn.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://www.scyld.com/pipermail/beowulf/attachments/20070328/399dcf2a/attachment.bin