A kernel level message passing service

Ron Brightwell rbbrigh at valeria.mp.sandia.gov
Fri Sep 1 15:17:52 PDT 2000

> Actually, we have a little project going to do that, more or less.  We're
> actually pitching IP altoghter, but staying with the existing Linux network
> protocol framework to implement a lightweight, reliable messaging service
> that continues to work with the existing sockets interface.  It requires
> very little change to user code to use it.  The question is - how much
> performance savings is due to the protocol, and how much is due to the
> interface?  I don't claim to know the answer, so we figured we'd try it out
> and see what happens.

You may want to look at
  High-Performance Local-Area Communication with Fast Sockets
  D. Culler, S. Rodriques and T. Anderson
  USENIX 1997 Annual Technical Conference
  Jan 1997

They put the sockets API on top of active messages over Myrinet and
characterized some performance limitations of the sockets API.


Ron Brightwell
Senior Member of Technical Staff                            bright at cs.sandia.gov
Sandia National Laboratories                    http://www.cs.sandia.gov/~bright
Scalable Computing Systems                                 work : (505) 844-2099
P.O. Box 5800                                            mobile : (505) 379-1913
Albuquerque, NM  87185-1110                                fax  : (505) 845-7442

More information about the Beowulf mailing list