The financial news out of Silicon Graphics last week - the company's profits falling even as revenues expand, and the contemplation of a reorganization in unprofitable European operations while looking for a new CEO – apparently has some customers looking for alternative shared-memory systems. Shai Fultheim, founder and CEO at …
Cost effective cluster
"...With vSMP Foundation 4.0, the vSMP hypervisor can link together as many as 128 physical server nodes and address up to 64TB of main memory across those nodes. With the 16-core Opteron 6200s used in four-socket servers, that brings 8,192 cores to bear on a single memory space, while with the current 10-core Xeon E7 processors used on eight-socket servers, that gives you 10,240 cores across a single memory space...."
This is really cost effective, just collect lot of compute nodes on a fast network, and glue them together with software, the vSMP hypervisor, which tricks this cluster to look like one single image. This makes it excellent for HPC and other number crunching cluster work load. 10,240 cpus in a cluster gives quite a performance.
The opposite is SMP servers, which is one big fat server with up to as many as 64 cpus!!! It is not a cluster, but true single image server. 64 cpus is less than 10,240 cpus, but one is a HPC cluster of compute nodes, the other is one big SMP server.