“Moab Task Manager is very valuable to customers who want drastically improved throughput on production clusters that have many small, short-lived, similar jobs,” said David Jackson, Adaptive Computing’s CTO and co-founder. “When pushing a high number of jobs through the system, Moab Task Manager works in unison with Moab to facilitate parallel job scheduling with larger, longer-running jobs.”
“FDR InfiniBand delivers today the highest performance for high-performance computing, cloud, Web 2.0, database and storage applications. Our interconnect solutions connect nearly half of the world’s Petaflop systems, demonstrating the high system efficiency and scalability that our interconnect provides. We continue with our development efforts to bring the next generation of 100Gb/s interconnect solutions, which are expected to be released in 2014/2015 time frame.”
In this video from SC13, Einer Rustad from Numascale describes how the company’s innovative products enable you to build scalable shared memory systems from standard servers. The company recently announced the successful validation of the large shared memory NumaConnect cluster at University of Oslo in Norway, which was installed under a prototype PRACE study assessing emerging new technologies for European HPC.