Today Numascale announced announced a collaboratioin with the Pittsburgh Supercomputing Center to explore how the company’s large-memory systems could benefit PSC research projects. By aggregating memory from multiple servers, Numascale technology is a cost-effective way to provide more directly addressable memory than is readily available on single, commodity, multi-socket, large memory servers.
Rapid advancement in many scientific fields of data-dependent research will be facilitated by the availability of larger memory systems at near commodity prices,” says Michael J. Levine, scientific director, PSC. “Having large amounts of data in directly-addressable memory avoids very time-consuming disk input/output and allows a much more productive programming paradigm.”
According to Einar Rustad, CTO and co-founder of Numascale, the goal is to provide users with big memory systems so they can operate in the familiar programming and runtime environment they are used to with workstations. In other words, users don’t have to rework their code to use explicit message passing.
PSC has long been an advocate of big memory systems with their Blacklight SGI UV supercomputer. That’s expensive technology, so it should come as no surprise that PSC is exploring Numascale as a lower-cost solution for big memory problems.
Read the Full Story.