FNN vs GigabitEther & Myrinet

Patrick Geoffray patrick at myri.com
Wed Oct 24 03:41:59 PDT 2001

"Eray Ozkural (exa)" wrote:

> Which brings to my mind GAMMA project. Why wasn't that project backed up by
> other people so that it could be made into production use? The latencies
> reported in the papers and the website are absolutely awesome. With GAMMA/MPI
> we could easily have the courage to play with fine-grained algorithms.

You are right. The GAMMA work is excellent, and the idea to provide 
a OS-bypass protocol easily portable over the Ethernet family is a 
good one.
The difficult part here is the number of different NICs and the lack 
of support from the vendors. I had the occasion to visit Giovani and 
Guiseppe in Genoa, and they had an evident lack of human and hardware 
ressources. I would encourage developpers in search for a good project 
to participate, and vendors to loan/give NICs (or at least increasing 
the life time of the GigE NICs, nothing is more frustating to finish 
a driver when the NIC is discontinued).


|   Patrick Geoffray, Ph.D.      patrick at myri.com 
|   Myricom, Inc.                http://www.myri.com
|   Cell:  865-389-8852          685 Emory Valley Rd (B)
|   Phone: 865-425-0978          Oak Ridge, TN 37830

More information about the Beowulf mailing list