back to article The Reg chats to HPE's HPC man about NASA's supercomputers, lunar ambitions and Columbia

Not content with stashing an Apollo-based supercomputer aboard the ISS, HPE will also be slinging the petaFLOPS for NASA's Ames Research Center. The Reg had a chat with supercomputing veteran Bill Mannel, vice president and general manager of HPC and AI at HPE, who told us the company is looking beyond Earth orbit. Based on …

  1. Peter Gathercole Silver badge

    Public cloud supercomputing

    The thing that many people forget is that supercomputing is as much about the interconnect speed and latency as it is about the basic CPU grunt.

    Public cloud can stand up vast amounts of CPU resource, but if you can't shunt the data between the nodes fast enough, significant computing problems that rely on stepped iteration between many parallel compute engines will stall every communication phase of each iteration.

    This is the reason why Cray have the Aries Interconnect, and IBM developed their HFI, each running elegant and complicated node-to-node topologies like Dragonfly.

    Many people think that fat tree Infiniband is the bees knees when it comes to interconnects, but these people just don't understand the total combined bandwidth of these more esoteric interconnects.

  2. Anonymous Coward
    Anonymous Coward

    The SGI 8600 (formerly SGI ICE) uses an enhanced hypercube topology. It may very well be the bees knees. Just a shame we can't run jobs of any significant size for more than a couple of days without bits of it failing...

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Biting the hand that feeds IT © 1998–2019