Archives for December 2014

The Russians are Coming: RSC in TOP10 of TOP500 Vendors

This week Russian supercomputing vendor RSC Group announced that the company is now a TOP10 supercomputing vendor according to the current edition of the Top500 list. In fact, RSC is the only Russian developer and manufacturer of HPC systems in the leading group of the rating by the number of deployed supercomputers.

Video: Accelerating ORNL’s Applications to the Exascale

In this video from the Nvidia booth theater at SC14, Buddy Bland from Oak Ridge National Laboratory presents: Accelerating ORNL’s Applications to the Exascale. “The Titan computer at Oak Ridge National Laboratory is delivering exceptional results for our scientific users in the U.S. Department of Energy’s Office of Science, Applied Energy programs, academia, and industry. Mr. Bland will describe the Titan system, how this system fits within the roadmap to exascale machines, and describe successes we have had with our applications using GPU accelerators.”

RCE Podcast: A Look at the Libfabric Implementation of Open Fabrics

In this RCE Podcast, Brock Palen and Jeff Squyres host Sean Hefty from Intel for a discussion about Libfabric, a software implementation of Open Fabrics Interfaces (OFI).

Supercomputing Santa’s Intractable Task

Over at the Adaptive Computing Blog, Trev Harmon takes a computational look at the Santa mythology and how a parallel machine would go about servicing the estimated 1,333,316,210 households on Planet Earth.

Job of the Week: SGI HPC Systems Admin with Security Cleararnce

SGI is seeking a HPC Systems Administrator with Secret Clearance in our Job of the Week.

DOD HPC Mod Program Beefs Up Supercomputing Capacity

This week the Department of Defense High Performance Computing Modernization Program (HPCMP) announced a new supercomputing investment for use by its engineering and research teams.

Mellanox: Paving the Road to Exascale

In this video from SC14, Eyal Waldman from Mellanox announces that the company can now deliver end-to-end 100 Gigabit/sec InfiniBand. “The demand for more computing power, efficiency and scalability is constantly accelerating in the HPC, enterprise, cloud computing and Web 2.0 markets. To address these demands Mellanox provides complete end-to-end solutions (silicon, adapter cards, switch systems, cables and software) supporting InfiniBand and Ethernet networking technologies.”

Why Storage Matters to HPC

In this special guest feature from Scientific Computing World, Robert Roe writes that the era of data-centric HPC is upon us. He then investigates how data storage companies are rising to the challenge. In August 2014, a ‘Task Force on High Performance Computing’ reported to the US Department of Energy that data-centric computing will be […]

University of Hawaii Says Aloha to New Cray CS Supercomputer

Today Cray announced that the Unhawaiiiversity of Hawaii has installed a new Cray CS supercomputer.

Video: Heterogeneous HPC, Architectural Optimization and NVLink

In this video, Steve Oberlin from Nvidia presents: Heterogeneous HPC, Architectural Optimization and NVLink.