“Compared to frequent developments in CPUs and accelerators, disk and storage communication technologies as well as parallel file systems are not realizing the same rate of innovation (Moore’s Law). However, this is changing as a number of new new and interesting technologies and developments such as HAMR drives, hybrid disks, intelligent flash, and new communication protocols including 12 Gb/s SAS and PCI-E direct attach are becoming available in the industry. This presentation intends to explain these technological directions and explore what these techniques mean for HPC storage over the coming years.”
Intel has selected Georgia Tech as the site of one of its newest Parallel Computing Centers. “The IPCC at Georgia Tech will develop new parallel algorithms and software for quantum chemistry and biomolecular simulation. Research will target large-scale computer systems using Intel Xeon Processors and Intel Xeon Phi coprocessors. The center will also develop new curricular materials to equip future computer scientists with the skills to fully realize the capabilities of parallel computing resources for scientific applications.”
“We have developed an active programme of industry engagement, typically consulting in niche areas and helping those partners exploit advanced computing within their organisations. This may be improving fraud detection algorithms, large-scale data management, tailored training courses or oil & gas related work. In fact it is very rarely about computer time! We also work with public sector bodies to support computing centric projects by the state and provide so-called platform technology support for research communities that need more than just raw cycles.”
In this episode of This Week in HPC, Michael Feldman and Addison Snell from Intersect360 Research discuss high frequency trading and the High Performance on Wall Street Conference. After that, they look at a Fujitsu’s Petascale upgrade at the Japan Aerospace Exploration Agency. The novel architecture for this Sparc-powered FX10 follow-on system will feature Micron’s Hybrid Memory Cube technology.
“Today, HPC has expanded beyond just national laboratories and research institutes to become a key technology for enterprises of all sizes as they seek to develop improved products or entirely new industries. Getting the maximum performance from HPC and data-intensive applications requires fast and scalable storage software. Simply put, today’s HPC workloads require storage infrastructure that scales endlessly and delivers unmatched I/O levels.”
Today at LUG 2014, Ken Claffey from Xyratex/Seagate announced that the company is donating the Lustre.org domain back the user community. “From my perspective, this move is a great indication that Seagate intends to be an active, contributing member of the Lustre community. After years of upheaval, Lustre users can now leave the politics behind and focus the world’s toughest computing challenges.”
“The emerging large-scale Data Centers for high-performance computing, clouds, and Web 2.0 infrastructures span tens and hundreds-of-thousands of nodes, all connected together via high-speed connectivity solutions. With the growing size of systems and CPU cores per server node, not only the traditional demands from the interconnect increase dramatically, but also new demand is introduced. Traditional interconnect solutions do not scale out to deliver efficient and balanced throughput and scalable latency at reasonable power and cost. This session introduces Mellanox interconnect solutions based on InfiniBand and Ethernet networks, presents multiple deployment examples, and outlines a vision for the future of interconnects and a roadmap of the company’s products.”