Inevitably, though, massively parallel interconnects (all boxes connected to all other boxes) won't scale.
On 1/23/12 9:32 PM, "Mark Hahn" <h...@mcmaster.ca> wrote: >>>> but it would take a bit of charisma. QPI-over-IB anyone? >>> >>> That's what I'm thinking! >> >> Numascale does this already with SCI > >it's easy to source and build pretty big IB systems; >how much so with SCI? > >I actually like the idea of high-fanout-distributed-router systems, >but they seem prepetually exotic. where are the hypercubes, FNNs? >afaikt, commodification of IB has snuffed topology as a design issue, >except for cray/BG/k machine-level projects. >_______________________________________________ >Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing >To change your subscription (digest mode or unsubscribe) visit >http://www.beowulf.org/mailman/listinfo/beowulf _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
