In this slidecast, Colin Williams from D-Wave Systems presents: Quantum Computing – A New Resource for HPC. I’ve recorded hundreds of podcasts here on insideHPC, but I have to say that this is one of the most fascinating topics I’ve ever covered.
With the industry’s emphasis on scalable systems for Big Data, a lot of companies are coming out with claims of faster I/O performance. What’s noteworthy about the Xyratex ClusterStor 9000 announcement is that it goes beyond a dramatic generational improvement in performance and scalability to discuss how that performance can be used effectively to streamline an enterprise’s existing workflow,” said Addison Snell, CEO of Intersect 360 Research.
“StrongBox is a network attached storage (NAS) appliance that is purpose-built to lower the costs of long-term storage and protection for unstructured, fixed content. By pairing a flexible, policy-driven disk cache with Linear Tape File System (LTFS) technology, StrongBox empowers you to control storage costs without sacrificing data availability.”
In this slidecast, Sumit Gupta from Nvidia discusses the latest product news on GPU computing for HPC. “With the breakthrough performance and higher memory capacity of the Tesla K40 GPU, enterprise customers can quickly crunch through massive volumes of data generated by their big data analytics applications.”
“We performed two-dimensional simulations of incompressible flow past the anatomically correct cross-section of the species Chrysopelea paradisi, showing that a significant enhancement in lift appears at an angle of attack of 35◦, above Reynolds numbers 2000. Previous experiments on physical models also obtained an increased lift, at the same angle of attack. The flow is inherently three-dimensional in physical experiments, due to fluid instabilities, and it is thus intriguing that the enhanced lift appears also in the two-dimensional simulations.”
“For this big workload, a 156,314-core CycleCloud behemoth spanning 8 AWS regions, totaling 1.21 petaFLOPS (RPeak, not RMax) of aggregate compute power, to simulate 205,000 materials, crunched 264 compute years in only 18 hours. Thanks to Cycle’s software and Amazon’s Spot Instances, a supercomputing environment worth $68M if you had bought it, ran 2.3 Million hours of material science, approximately 264 compute-years, of simulation in only 18 hours, cost only $33,000, or $0.16 per molecule.