Archives for January 2014

Windows Azure Adds New High Performance Capabilities

Over at the Windows HPC Team Blog, Alex Sutton writes that Azure now offers new compute intensive VM sizes for Cloud Services.

Online Tutorial: Hybrid MPI and OpenMP Parallel Programming

OpenMP.org has posted the slides and audio from a day-long tutorial on Hybrid MPI and OpenMP Parallel Programming from SC13.

New UberCloud Marketplace is a One-Stop-Shop for HPC as a Service

Advocates of Cloud Computing for HPC Workloads got a huge potential boost for their cause this week with the announcement that opening of the new UberCloud Marketplace. As a One-Stop-Shop for HPC as a Service, the Marketplace is a place where engineers and scientists can discover, try and buy the computing power and expertise on demand they need for their computational and data-intensive tasks.

Podcast: This Week in HPC Looks at IBM’s High Performance Plans and AMD’s ARM Debut

In this episode of This Week in HPC, Addison Snell and Michael Feldman look at IBM’s plans for high performance computing now that the company has exited the x86 server business. It was also a milestone week for AMD, who rolled out their first ARM chip.

NERSC Fires Up Edison Supercomputer

Edison can execute nearly 2.4 quadrillion floating-point operations per second (petaflop/s) at peak theoretical speeds. While theoretical speeds are impressive, “NERSC’s longstanding approach is to evaluate proposed systems by how well they meet the needs of our diverse community of researchers, so we focus on sustained performance on real applications,” said NERSC Division Deputy for Operations Jeff Broughton.

Large Datasets Continue to Challenge Aerospace Engineers

“In aerospace, users prefer to have the option to visualize the entire system. But that doesn’t necessarily mean it’s something routinely done. By definition, system-level visuals involve too much data. If an engineer is trying to troubleshoot something in an analysis program, he or she will most likely analyze only the subcomponents that contribute to the problem. For example, electrical wiring information can safely be omitted when doing an airflow study of the outer surface.”

My Other Supercomputer is a Lenovo

Over at The Register, Dan Olds writes that, with the acquisition of the x86 servers business from IBM, Lenovo is buying a spot on the Top500 list and a sizeable place in the HPC market. Using the November 2013 list, Lenovo would hold onto second place in terms of systems – 25 per cent of the total (127 boxes). This puts it ahead of everyone except HP. IBM without x86 boxes would place fourth on the system count list, behind HP, Lenovo and Cray.

Allinea MAP Boosts Research at University of Luxembourg

The University of Luxembourg is harnessing the power of Allinea MAP in its quest to speed up research and to be among the world’s top universities.

Slidecast: MPI Requirements of the Network Layer

Jeff Squyres from Cisco describes the proposed successor to the Linux verbs API that is designed to better serve the needs of MPI. “It’s not libibverbs 2.0 — it’s a new API that aims to both expand the scope of what libibverbs did, and also to address many of its much-criticized shortcomings.”

ISC Posts a Tribute to Hans Meuer

ISC has posted a tribute to Hans Meuer, who passed away last week at the age of 77. Meuer was the founder of TOP500 and the ISC General Chair.