OpenMP is Expanding

In this podcast, Matthijs van Waveren from OpenMP.org presents: OpenMP is Expanding. OpenMP, the de-facto standard for parallel programming on shared memory systems, continues to extend its reach beyond pure HPC to include DSPs, real time systems, and accelerators. The first release candidate of OpenMP 4.0 was made available at the SC12 conference and exhibition.

We are proud to mark the 15th anniversary of OpenMP,” said Michael Wong, OpenMP CEO, “with a major leap forward with significant enhancements to parallelism.”

OpenMP released a technical report on directives for attached accelerators recently with the intent to integrate OpenACC into the final OpenMP release candidate in the 1st quarter of 2013. The second release candidate will include the directives for attached accelerators, tasking extensions and error handling. Read the Full Story. Download the MP3 * Download the slides (PDF) * Subscribe on iTunes * If Dropbox is blocked, download audio from Google Drive.

NetApp - Big Data and HPC

In this podcast, Richard Treadway and Rich Seger from NetApp discuss the company's storage solutions for Big Data and HPC. The company's HPC solutions for Lustre support massive performance and storage density without sacrificing efficiency. Download the MP3 * Download the slides (PDF) * Subscribe on iTunes * If Dropbox is blocked, download audio from Google Drive.

ProfitBricks IaaS is HPC in the Cloud Made Real

In this podcast, ProfitBricks USA CEO Bob Rizika describes how the world has changed since the first generation of Clouds and that high performance computing today can be a viable Infrastructure as a Service.

What’s different now in Cloud computing? It's not first generation difficult-to-use, costly, slow and limiting – but second-generation Infrastructure as a Service (IaaS).  We now live in a world where instances can be connected at 80Gb/s, and instances can have 196GB of RAM and 48 cores. The real clouds are arriving.  And despite what some might think, they are priced and packaged for the masses.

Read the Full Story.

Texas Instruments Builds System on Chip for HPC

In this podcast, Arnon Friedmann from Texas Instruments describes the company's new multicore System-on-Chips (SoCs). Based on its award winning KeyStone architecture, TI's SoCs are designed as accelerate traditional x86 servers as well as enable the building purpose-built, energy efficient devices for specific applications powered by ARM processors and TI DSPs on the same package.

Targeted for applications such as networking, radar, imaging, high performance computing, gaming and media processing, TI's new KeyStone multicore processors offer developers more than twice the capacity & performance at half the power relative to existing solutions.

Read the Full Story * Download the MP3 * Subscribe on iTunes * If Dropbox is blocked, Download from Google Drive.

Parallella - Supercomputing for Everyone

In this podcast, Adateva Founder & CEO Andreas Olofsson describes the new Parallella project, an open-source development platform for low-power parallel computing. In an attempt to finance the project, the company is launching Parallella as a Kickstarter campaign so that the development platform can be offered for only $99 dollars.

Inspired by great hardware communities like Raspberry Pi and Arduino, we see a critical need for an truly open, high-performance computing platform that will close the knowledge gap in parallel programing," said Andreas Olofsson, CEO of Adapteva. "High performance parallel computing is currently only accessible to a small and select group of expert programmers. The goal of the Parallella project is to democratize access to parallel computing. The parallel programming dilemma is a grand challenge of computer science and we need all hands on deck."

OCF enCORE: HPC on Demand

In this podcast, Jerry Dixon from OCF describes the company's new enCORE HPC on Demand service.

OCF's enCORE service provides a highly scalable compute facility that can be accessed on a pay-as-you-go basis via the Internet. No concerns over data centre space, power, cooling, or in recruiting and retaining the skills to implement and maintain your own cluster. Simply register, log on and begin running jobs in your own secure area. The service provides access to a state-of-the-art IBM iDataPlex compute cluster with Infiniband interconnects, GPU nodes and high speed IBM storage, to deliver a truly scalable, high performance computing resource. Users will be allocated their own area on the system and, via the scheduler, can place jobs onto the physical compute nodes of the system. Then simply monitor progress and download the results."

Learn more at: http://www.ocf.co.uk/what-we-do/encore

Overview of Intel Parallel Studio XE 2013

In this podcast, Intel Tool Evangelist James Reinders presents an overview of the new Intel Parallel Studio XE 2013 and Intel Cluster Studio XE 2013 tool suites.