insideHPC

New Cray Cluster Connect Puts the Super in Big Data

Rich Brueckner — Wed, 19 Jun 2013 07:15:27 +0000

This week at ISC’13, we learned about the new Cray Cluster Connect. Described as a complete Lustre storage solution for x86 Linux clusters, Cray Cluster Connect is an “hardware agnostic” solution for customers who need flexibility in their storage configurations. In other words, you no longer need to buy a Cray supercomputer in order to get access to Cray’s Big Data and fast I/O expertise.

Cray has a long, rich history in the HPC storage space, and we have built some of the largest and fastest Lustre file systems in the world,” said Barry Bolding, Cray’s vice president of storage and data management. “With Cray Cluster Connect, we are applying our Lustre expertise and innovation, and taking all that we have learned, developed and invested in parallel storage solutions to an expanded customer base. We can now deliver end-to-end, Lustre storage solutions for customers’ existing x86 Linux environments. With the launch of Cray Cluster Connect, our storage and data management solutions are no longer limited to Cray supercomputer customers.”

Available now, Cray Cluster Connect offers a wide range of storage options including block storage components from Cray Sonexion (Xyratex), DataDirect Networks, or NetApp plus a full set of management and storage connectivity tools for data movement, archiving and management. Read the Full Story.

The post New Cray Cluster Connect Puts the Super in Big Data appeared first on insideHPC.

Job of the Week: HPC Middleware Engineer at Shell in the Netherlands

Staff — Wed, 19 Jun 2013 07:10:25 +0000

Shell in the Netherlands is seeking an HPC Middleware Engineer in our Job of the Week.

The HPC department in Shell provides HPC infrastructure services globally to Shell, with the bulk of our staff being based in Houston, USA and Rijswijk, Netherlands. We are part of a wider IT group that focuses on Technical and Competitive IT solutions and services within Shell. The team sits within the IT Services & Operations (ITSO) function under the Technical Landscape Services (TLS) department. We bring business value with reliable and secure operations and services. TLS puts capabilities into the hands of end-users who are generating significant business value. The HPC Services team deploys and supports large Linux-based compute clusters providing highly available, reliable capacity aimed at users of HPC-enabled applications in Shell’s Geoscience and Engineering communities. You will be a member of the HPCS Middleware team of approximately 15 staff in the US and Europe working with colleagues on other HPCS teams and for customers. We are seeking two Middleware Engineers who will be primarily focused on job scheduling solution design, development, deployment and support.

Are you paying too much for your job ads? Not only do we offer ads for a fraction of what the other guys charge, our insideHPC Job Board is powered by SimplyHIred, the world’s largest job search engine.

As a reminder, we are offering FREE job listings for .EDU and .GOV domains, so email us at: info @ insideHPC.com for a special discount code.

The post Job of the Week: HPC Middleware Engineer at Shell in the Netherlands appeared first on insideHPC.

NRENs Seeking Proposals for Enlighten Your Research Global Competition

Ralph — Wed, 19 Jun 2013 03:43:21 +0000

Five leading national research and education networks (NRENs) — ESnet, Funet, Internet2, Janet and SURFnet – have launched a competition called the Enlighten Your Research Global. The program aims to encourage and support research collaborations by taking advantage of leading-edge, global network resources to accelerate national research.

Networks have become a critical piece of the research enterprise. Almost all scientific disciplines rely on networks to support research activities, well above and beyond the ubiquitous use of email, web, and other commodity-like services. Experimental collaborations such as the Large Hadron Collider demonstrate years of experience in working with networks as part of the science workflow. With the exponential growth in data output, similar paradigms are now rapidly emerging across many scientific disciplines from genomics to climate research and to new materials discovery. The EYR-Global program builds on SURFnet’s successful effort in the Netherlands, and represents an important step forward in helping researchers in all research fields to incorporate advanced global research networks to significantly improve discoveries and collaboration processes.

Researchers from any discipline and with any level of technical expertise are invited to submit a proposal by Monday, July1, 2013.

The post NRENs Seeking Proposals for Enlighten Your Research Global Competition appeared first on insideHPC.

Video: Driving Industrial Innovation on the Road to Exascale

Rich Brueckner — Tue, 18 Jun 2013 13:21:32 +0000

In this video from ISC’13, Raj Hazra from Intel presents: Driving Industrial Innovation on the Road to Exascale.

Join Intel for a look at the state of the HPC industry from two perspectives. First, we’ll look at how innovations in HPC are driving innovation in manufacturing industries with energy and automotive industry leaders providing examples. Next, we’ll give our perspective on the race to Exascale and discuss how Intel is collaborating with the HPC industry to address the challenges.”

During the presentation, Hazra announced five new Intel Xeon Phi products tailor-made for HPC. Download the slides (PDF).

The post Video: Driving Industrial Innovation on the Road to Exascale appeared first on insideHPC.

Researchers Deploy GPUs To Build World’s Largest Artificial Neural Network

Ralph — Tue, 18 Jun 2013 07:27:19 +0000

Today at ISC’13, Nvidia announced a collaboration with Stanford University to create the world’s largest artificial neural network built to model how the human brain learns. At 6.5 times bigger than the previous record-setting network developed by Google in 2012, the neural net will be capable of “learning” how to model the behavior of the brain — including recognizing objects, characters, voices and audio in the same way that humans do.

Creating large-scale neural networks is extremely computationally expensive. For example, Google used approximately 1,000 CPU-based servers, or 16,000 CPU cores, to develop its neural network, which taught itself to recognize cats in a series of YouTube videos. The network included 1.7 billion parameters, the virtual representation of connections between neurons. In contrast, the Stanford team, led by Andrew Ng, director of the university’s Artificial Intelligence Lab, created an equally large network with only three servers using Nvidia GPUs to accelerate the processing of the big data generated by the network. With 16 NVIDIA GPU-accelerated servers, the team then created an 11.2 billion-parameter neural network.

Delivering significantly higher levels of computational performance than CPUs, GPU accelerators bring large-scale neural network modeling to the masses,” said Sumit Gupta, general manager of the Tesla Accelerated Computing Business Unit at NVIDIA. “Any researcher or company can now use machine learning to solve all kinds of real-life problems with just a few GPU-accelerated servers.”

Read the Full Story.

The post Researchers Deploy GPUs To Build World’s Largest Artificial Neural Network appeared first on insideHPC.

Do We Underestimate the Real Challenge of Exascale?

Rich Brueckner — Tue, 18 Jun 2013 07:06:22 +0000

Over at the ISC Blog, Mark Parsons from the EPCC supercomputing centre writes that scalable software is the real Grand Challenge of Exascale.

I believe that the problems that we’ve seen at the Petascale with regard to the scaling of many codes are insurmountable if we take the incremental change approach at the Exascale. Looking at the CRESTA codes, it is highly unlikely any of them will scale to the Exascale, even allowing for weak scaling (through increased resolution of the model under study) using incremental improvements. This means we need to think about disruptive changes to codes in order to meet the challenge.

Parsons leads the CRESTA FP7 project, which is focussing its work on a small set of six HPC applications that are widely used today and represent the sort of codes that will have to run on Exascale systems. He says that over the past 20 years, the community has managed to cope with each new generation of hardware through incrementally improving our codes. But today, simply changing a solver or some other disruptive change to an existing code will not be enough.

We simply do not understand how to compute using one billion parallel threads (except perhaps in trivial cases). It requires us to completely rethink how we simulate our physical world using this much parallelism. The problem goes to the foundations of modern modelling and simulation – we need to think beyond the tools we have today and invent new methods to express the mathematical descriptions of the physical world around us, on these and even larger systems in the future. Only by doing this will we move modelling and simulation forward for the next 20 years. This is the real challenge we face at the Exascale.

Read the Full Story.

The post Do We Underestimate the Real Challenge of Exascale? appeared first on insideHPC.

Video: Lustre Update and Roadmap from ISC’13

Rich Brueckner — Tue, 18 Jun 2013 07:05:30 +0000

In this video from the HPC Advisory Council European Conference 2013, Brent Gorda from Intel (Whamcloud) presents: Lustre Update and Roadmap.

Gorda also discusses the new Intel Enterprise Edition for Lustre software, a supported distribution of Lustre featuring management tools as well as a new adaptor for the Intel Distribution for Apache Hadoop.

Download the slides (PDF).

The post Video: Lustre Update and Roadmap from ISC’13 appeared first on insideHPC.

Altair Chosen for JAIST Research Center in Japan

Ralph — Tue, 18 Jun 2013 07:05:01 +0000

Altair’s workload management product, PBS Professional, has been selected to manage workload for the Cray XC30 supercomputer recently put into production by the Japan Advanced Institute for Science and Technology (JAIST).

One of Japan’s premier academic research centres, JAIST is using the new Cray XC30 supercomputer for research into massively parallel programming and a variety of scientific pursuits.

The two-cabinet Cray XC30 supercomputer at JAIST has a peak performance of more than 118 teraflops with 5760 CPU cores and is the institute’s main system for its high-performance computing facility.

At JAIST, it is imperative to provide our world-class scientists with the best available technology resources to support their computational research,’ said Mineo Kaneko, director of the JAIST Research Center for Advanced Computing Infrastructure. “The pioneering Cray XC30 supercomputer with PBS Professional will allow our users to expand the scope of their research efforts with a proven, well-integrated solution they can rely on.”

This story appears here as part of a cross-publishing agreement with Scientific Computing World.

The post Altair Chosen for JAIST Research Center in Japan appeared first on insideHPC.

Adaptive Computing to Manage HPC Workloads at Baden-Württemberg

Ralph — Tue, 18 Jun 2013 07:03:42 +0000

This week at ISC’13, Adaptive Computing announced that the Baden-Württemberg High Performance Computing Competence Centers (bwHPC) will use the company’s Moab software to manage supercomputing workloads in its distributed supercomputing system. The system will have an estimated 6,500 processors socket in five clusters upon completion.

Moab will help this undertaking realize its full potential,” said Achim Streit, Ph.D., professor and director at the Steinbuch Centre for Computing at Karlsruhe Institute of Technology (KIT), where at first the bwUniCluster will be installed. “In addition to helping us achieve maximum resource efficiency, Moab also enables us to ensure a uniform interface for the user base of the five clusters and tailor these individual systems to the needs of our specific communities.”

Adaptive Computing will be demonstrating its Moab HPC Suite during ISC’13 booth #500. Read the Full Story.

The post Adaptive Computing to Manage HPC Workloads at Baden-Württemberg appeared first on insideHPC.

Podcast: Radio Free HPC Interviews Jack Dongarra on the New TOP500

Rich Brueckner — Mon, 17 Jun 2013 18:21:59 +0000

In this podcast, the Radio Free HPC team discusses the June 2013 TOP500 list with Jack Dongarra from the University of Tennessee. How did the Chinese manage to trump the world once again with the #1 supercomputer on the planet? Listen in to find out.

Download the MP3 * Subscribe on iTunes * RSS Feed

The post Podcast: Radio Free HPC Interviews Jack Dongarra on the New TOP500 appeared first on insideHPC.

Excitement at ISC13: Getting to the MilkyWay 2

johnH — Mon, 17 Jun 2013 08:40:51 +0000

In this special guest feature, Intel’s John Hengeveld describes the effort that went into building the fastest supercomputer on Earth.

Milky Way 2 is amazing.. and whats more amazing is… you can build a similar system for your needs.

So by now you have all heard about the MilkyWay 2 system in China that has surprised the world and achieved the #1 spot on the TOP500 list. The Intel team has been working on many fronts in the past year. The upcoming Intel Xeon Processors E5-2600 V2, a major expansion to the Intel Xeon Phi products family, expanding our industry leading software development toolkits. We’re in like 98% of the new systems on the TOP500 list.. so seriously.. we need a rest.

All of these things are coming together at ISC13. The outgrowth of much of this work is shows up in the MilkyWay 2 system, but what’s more important is that this technology is very soon available from a broad range of suppliers to be turned on a wide range of industrial and scientific technical computing applications.

The Processor and Coprocessor components Intel proposed and shipped in production for MilkyWay2 are being announced and demonstrated by Intel for the first time at ISC today. The first demonstration of the as yet unlaunched Intel Xeon Processor E5-2600 V2 product family will be shown in the Intel Booth in a live 52 node cluster showing high fidelity visualizations of an Audi RS5 vehicle design.

During ISC’13, Raj Hazra announced the general availability of 5 new Intel Xeon Phi Coprocessor products including the 3100 family that is featured in the MilkyWay 2 system. You can watch the video right here on insideHPC.

I want to tell a short story about the MilkyWay 2 system that you probably haven’t heard, and show why being at Intel is the coolest thing ever.

About a year ago, the NUDT folks, led by Professor Liao, had a really good idea of how he wanted to build the worlds biggest super computer, using the next step in their proprietary fabric and trying to use intel’s latest processors to achieve its objectives in power efficiency and performance.

They gave Intel and others programmability, node power and node performance goals with very tight constraints. Then they dropped the heavy challenge… “and it all has to work and be #1 in the world by June 2013”. Intel proposed a solution that not only met all their time and performance requirements but also their programmability requirements.

What they wanted they later described as a “Neo-Heterogeneous Architecture”. This type of system has two tiers of hardware heterogeneity, but driven off a consistent programming model and parallelism abstraction. This allows very much faster development of applications that scale to a very high level.

What the use of Intel Xeon Phi Coprocessors offered is hardware with the performance and energy efficiency required, but removed the need for an alternate programming model for the second tier thus enabling their neo-heterogeneous architectural vision.

The plan to build out the system as audacious as well. The customer developed the system based on Intel Xeon Processor E5-2600 based products and built test cluster that would itself be on the top500 list. After debugging that system and the code that ran on it, NUDT planned to get the next generation product (the future Intel Xeon Processor E5-2600 V2 family) and basically drop it in. This enabled them to go from first delivery of a blade to a completed system in about 4 weeks. The Linpack run came about a week later. By the time Jack Dongarra and others saw it at the end of May, it was running real applications.

For Intel’s part, what Intel’s factory and engineering teams did was validate two new products and put them into high volume production on schedule to within a week of our schedule predicted a year before.

I have been getting asked why Intel got chosen for this amazing system. The short answer is.. because we deliver. We delivered.

The post Excitement at ISC13: Getting to the MilkyWay 2 appeared first on insideHPC.

It’s Official: China Once Again Leads the TOP500

Rich Brueckner — Mon, 17 Jun 2013 08:39:18 +0000

The June 2013 TOP500 was released today at ISC’13 with an all-new Chinese supercomputer leading the list with 33.86 Petaflops on the Linpack benchmark.

Tianhe-2, or Milky Way-2, will be deployed at the National Supercomputer Center in Guangzho, China, by the end of the year. The surprise appearance of Tianhe-2, two years ahead of the expected deployment, marks China’s first return to the No. 1 position since November 2010, when Tianhe-1A was the top system. Tianhe-2 has 16,000 nodes, each with two Intel Xeon IvyBridge processors and three Xeon Phi processors for a combined total of 3,120,000 computing cores.

Formerly number one on the list, the Titan Cray XK7 at Oak Ridge is now ranked No. 2 with 17.59 Petaflops and Sequoia, an IBM BlueGene/Q system installed at LLNL falls to number 3 on the list with 17.17 petaflops.

Other highlights from the June 2013 TOP500 list include:

There are 26 systems with performance greater than a Petaflop, up from 23 six months ago.
The new No. 1 system, Tianhe-2, and the No. 6 system, Stampede, are using Intel Xeon Phi processors to speed up their computational rate. The No. 2 system, Titan, and the No. 10 system, Tianhe-1A, are using NVIDIA GPUs to accelerate computation.
A total of 54 systems on the list are using accelerator/co-processor technology, down from 62 in November 2012. Thirty-nine of these use NVIDIA chips, three use ATI Radeon, and eleven systems use Intel MIC technology (Xeon Phi).
The number of systems installed in China has now stabilized at 66, with 72 and 68 on the last two lists. As a nation, China now holds the No. 2 position as a user of HPC, ahead of Japan, UK, France, and Germany. Due to Tianhe-2, China has also taken the No. 2 position in the performance share, ahead of Japan.
Intel continues to provide the processors for the largest share (80.4 percent) of TOP500 systems.

Read the Full Story.

The post It’s Official: China Once Again Leads the TOP500 appeared first on insideHPC.

nCore HPC Rolls Out BrownDwarf ARM DSP Supercomputer

Rich Brueckner — Mon, 17 Jun 2013 08:07:28 +0000

We don’t get the chance to announce new players in the HPC space very often, especially from our hometown of Portland. Today newcomers nCore HPC announced the BrownDwarf Y-class supercomputer, a heterogeneous ARM- and DSP-based system designed for green high performance computing.

With its unique parallel computing architecture and a high performance, low latency interconnect, the BrownDwarf is “Y-Class supercomputer” with extremely low power consumption. In a 144 node configuration, BrownDwarf delivers 70 Teraflops of performance at 10kw inside a 42U high rack.

The BrownDwarf Y-Class system is an incredibly important milestone in HPC system development,” said Ian Lintault, managing director of nCore HPC. “Working in close collaboration with TI, IDT and our hardware partner Prodrive, we have successfully established a new class of energy efficient supercomputers designed to fulfill the demands of a wide range of scientific, technical and commercial applications.”

The BrownDwarf Y-Class node leverages multiple Keystone-II and Keystone-I SoC components from Texas Instruments Incorporated (TI). Each node integrates four ARM Cortex-A15 MPCore processors, 24 TMS320C66x digital signal processor (DSP) cores and 26GB of ECC memory.

Read the Full Story.

The post nCore HPC Rolls Out BrownDwarf ARM DSP Supercomputer appeared first on insideHPC.

C-DAC Initiatives in HPC for Scientific & Engineering Research

Rich Brueckner — Sun, 16 Jun 2013 15:11:13 +0000

In this video from the HPC Advisory Council European Conference 2013, Abishek Das from C-DAC presents: C-DAC Initiatives in HPC for Scientific & Engineering Research.

Exploitation of parallel processing technologies for Scientific & Engineering Research will accelerate research of applications in various engineering disciplines that employ HPC techniques and facilitates research about HPC technologies contributing to capacity-building of the country.”

Download the slides (PDF).

The post C-DAC Initiatives in HPC for Scientific & Engineering Research appeared first on insideHPC.

Gordon Supercomputer Fosters New Fields of Research for HPC

Ralph — Sun, 16 Jun 2013 15:04:20 +0000

With over 300 TB of high performance Intel flash memory SSD, the Gordon supercomputer at SDSC is opening the door to new areas of research for HPC such as political science, mathematical anthropology, finance, and even the cinematic arts.

Gordon’s extraordinary speed makes it possible for researchers to tackle questions they couldn’t address before, simply because they didn’t have a system that was uniquely tailored to handle the challenges of data intensive computing,” said SDSC Michael Norman just prior to Gordon’s launch. “I view Gordon as a new kind of vessel, a ship that will take us on new voyages to makes new discoveries in new areas of science.”

Read the Full Story.

The post Gordon Supercomputer Fosters New Fields of Research for HPC appeared first on insideHPC.

Video: Xyratex Update – ClusterStor

Rich Brueckner — Sun, 16 Jun 2013 14:11:32 +0000

In this video from the HPC Advisory Council European Conference 2013, Torben Kling-Petersen from Xyrtex presents: Xyratex Update – ClusterStor.

Download the slides (PDF).

The post Video: Xyratex Update – ClusterStor appeared first on insideHPC.

Hungarian Datacenter Inaugurated

Staff — Sun, 16 Jun 2013 13:47:42 +0000

CERN and the Wigner Research Centre for Physics have inaugurated the Hungarian data centre in Budapest, marking the completion of the facility hosting the extension for CERN computing resources.

About 500 servers, 20,000 computing cores, and 5.5 Petabytes of storage are already operational at the site. The dedicated and redundant 100 Gbit/s circuits connecting the two sites are functional since February 2013 and are among the first transnational links at this distance. The capacity at Wigner will be remotely managed from CERN, substantially extending the capabilities of the Worldwide LHC Computing Grid (WLCG) Tier-0 activities and bolstering CERN’s infrastructure business continuity.

WLCG’s mission is to provide global computing resources to store, distribute and analyse more than 25 Petabytes of data annually generated by the Large Hadron Collider (LHC). It is a global system organised in tiers, with the central hub being the Tier-0 at CERN.

The experiments” computing resources needs will increase significantly when the LHC restarts in 2015. Hosting computing equipment at the Wigner Centre to extend CERN’s data centre Tier-0 capabilities is essential for dealing with this expected increase, and to the success of our physics programme. The remote capacity will also contribute to business continuity for the critical systems in case of a major issue on CERN’s site,’ said CERN director-general Rolf Heuer. “A number of sciences currently face exponential data growth. This innovative approach with Wigner could point the way for research centres to run their services in the future.”

This story appears here as part of a cross-publishing agreement with Scientific Computing World.

The post Hungarian Datacenter Inaugurated appeared first on insideHPC.

Video: High Performance Computing Trends for 2013

Rich Brueckner — Sun, 16 Jun 2013 13:36:56 +0000

In this video from the HPC Advisory Council European Conference 2013, Addison Snell from Intersect360 Research presents: High Performance Computing Trends for 2013.

This presentation is an overview of the current important trends in HPC, based on the latest end-user research studies and market forecasts. Topics include accelerator adoption, the role of HPC in Big Data, and the ratio of spending between hardware, software, staffing, and facilities.”

Download the slides (PDF).

The post Video: High Performance Computing Trends for 2013 appeared first on insideHPC.

Livermore to Share 5 Petaflops with Industry

Ralph — Sun, 16 Jun 2013 12:16:13 +0000

Over at FCW Magazine, Mark Rockwell writes that Lawrence Livermore National Labs has five petaflops of computing power it wants to share. To help fuel technological innovation to spur U.S. economic competitiveness, the research facility has officially opened up access to its massive Vulcan supercomputer to industry and academia for collaborative developmental projects.

High performance computing is a key to accelerating the technological innovation that underpins U.S. economic vitality and global competitiveness,” said Fred Streitz, HPC Innovation Center director, in a June 11 statement. “Vulcan offers a level of computing that is transformational, enabling the design and execution of studies that were previously impossible, opening opportunities for new scientific discoveries and breakthrough results for American industries.”

During its initial shakeout period, LLNL said Vulcan was combined with the larger Sequoia system to produce set a world speed record of 504 billion events per second for a discrete event simulation in collaboration with the Rensselaer Polytechnic Institute. That achievement, said the lab, opens the way for the scientific exploration of complex, planetary-sized systems.

Read the Full Story.

The post Livermore to Share 5 Petaflops with Industry appeared first on insideHPC.

Video: Efficient and Cost-Effective HPC Interconnection Networks

Rich Brueckner — Sun, 16 Jun 2013 10:48:58 +0000

In this video from the HPC Advisory Council European Conference 2013, Jesús Escudero, from the Universidad de Castilla-La Mancha presents: Efficient and Cost-Effective HPC Interconnection Networks.

This keynote address analyzes the most prominent challenges for designing and cost-effective interconnection networks for Exascale systems, such as topology scalability, power consumption, fault tolerance, and/or congestion control. Besides, some solutions are proposed and their implementation complexity in commercial products are estimated.”

The post Video: Efficient and Cost-Effective HPC Interconnection Networks appeared first on insideHPC.