[openfabrics-ewg] IB MTU tunable for uDAPL and/or Intel MPI?

Scott Weitzenkamp (sweitzen) sweitzen at cisco.com
Fri Jun 9 10:44:56 PDT 2006


While we're talking about MTUs, is the IB MTU tunable in uDAPL and/or
Intel MPI via env var or config file?
 
Looks like Intel MPI 2.0.1 uses 2K for IB MTU like MVAPICH does in OFED
1.0 rc4 and rc6, I'd like to try 1K with Intel MPI.
 
Scott


________________________________

	From: openib-general-bounces at openib.org
[mailto:openib-general-bounces at openib.org] On Behalf Of Scott
Weitzenkamp (sweitzen)
	Sent: Thursday, June 08, 2006 4:38 PM
	To: Tziporet Koren; openfabrics-ewg at openib.org
	Cc: openib-general
	Subject: RE: [openib-general] OFED-1.0-rc6 is available
	
	
	The MTU change undos the changes for bug 81, so I have reopened
bug 81 (http://openib.org/bugzilla/show_bug.cgi?id=81).
	 
	With rc6, PCI-X osu_bw and osu_bibw performance is bad, and
PCI-E osu_bibw performance is bad.  I've enclosed some performance data,
look at rc4 vs rc5 vs rc6 for Cougar/Cheetah/LionMini.
	 
	Are there other benchmarks driving the changes in rc6 (and rc4)?
	 
	Scott Weitzenkamp
	SQA and Release Manager
	Server Virtualization Business Unit
	Cisco Systems
	 

		 

		OSU MPI:

		*        Added mpi_alltoall fine tuning parameters

		*        Added default configuration/documentation file
$MPIHOME/etc/mvapich.conf

		*        Added shell configuration files
$MPIHOME/etc/mvapich.csh , $MPIHOME/etc/mvapich.csh

		*        Default MTU was changed back to 2K for
InfiniHost III Ex and InfiniHost III Lx HCAs. For InfiniHost card
recommended value is:
		VIADEV_DEFAULT_MTU=MTU1024

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/ewg/attachments/20060609/002e33a7/attachment.html>


More information about the ewg mailing list