2 posts • joined 1 Apr 2008
Nothing to do with Virtual Iron, but the key is that becasue it isn't a standard NUMA architecture such as SGI Altix thelatency question is not relevant. The COMA memory chunk, caches Gigabytes of data. Predictive algorithms prefetch data blocks so that when computation is needed they are already resident in memory, hence no IB latency issue. The net issue is MPIcodesat the same speed as an IB cluster, support for large shared memory jobs, without cluster management complexity.
As far as the IB is converned the system uses standard Mellanox IB, including ConnectX if it shipping yet.
The larger, 8-32 socket system uses an internal IB switch to connect servers together.
to anonymous coward
Sensible question, but It's a hybrid NUMA/COMA architercture, so the latency is hidden.
- YARR! Pirates walk the plank: DMCA magnets sink in Google results
- Pics Whisper tracks its users. So we tracked down its LA office. This is what happened next
- Review Xperia Z3: Crikey, Sony – ANOTHER flagship phondleslab?
- Ex-US Navy fighter pilot MIT prof: Drones beat humans - I should know
- OnePlus One cut-price Android phone on sale to all... for 1 HOUR