[Beowulf] torus versus (fat) tree topologies
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Chris Sideroff cnsidero at syr.eduSun Nov 7 19:04:07 PST 2004
- Previous message: [Beowulf] beowulf@beowulf.org Urgent. Newsletter of the Intern. Assoc. of Mechanical Engineers. Free participation for Successful Session Organizers
- Next message: [Beowulf] torus versus (fat) tree topologies
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
I looking for some general comments about the pros/cons of torus (2D/3D) and (fat) tree network topologies, for HPC of course. My investigation thus far has led me to believe that one reason a torus topology might be better is because it eliminates the need for a switch. On the other hand fat tree interconnects seem to dominate the larger(est) clusters out there, why? I'm looking more for comments about implementation and maintenance experiences with either topology (or both). It seems that most of the available high-performance network products give _roughly_ the same overall performance so I don't want to start a long debate about the competing products - just looking for topology differences, not company A vs company B. Thanks for any comments Chris Sideroff
- Previous message: [Beowulf] beowulf@beowulf.org Urgent. Newsletter of the Intern. Assoc. of Mechanical Engineers. Free participation for Successful Session Organizers
- Next message: [Beowulf] torus versus (fat) tree topologies
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
