Entries filed under “Collaborations”

Partnerships between vendors or institutions to develop, deploy, or productize HPC technology

Bull Enters €28 Million Joint Venture to Mainstream HPC

By Staff | Published May 22, 2012

Bull has announced a €28 million joint venture with a French investment company, aimed at accelerating the widespread adoption of high-performance computing (HPC).

The new joint company will focus on delivering secured HPC services, as a Cloud computing service provider. The other investor, CDC (Caisse des Dépots), is a public group serving France’s general interest and economic development. CDC will contribute nearly €10m in equity to the project.

The ‘NumInnov’ project aims to create an independent service provider specialising in HPC applications, which will operate at a European level.

I am delighted at the launch of this project, which will have a tangible impact on the industry and the digital economy in both France and in Europe,’ said Philippe Vannier, chairman and chief executive officer of Bull. “The project will be a very powerful driver to accelerate the adoption of HPC technologies, and will trigger the development of new applications and services by large enterprises as well as SMEs. As a specialist company in critical digital systems, Bull is the only European player capable of delivering expertise in on-demand HPC within the security constraints that are critical to this project.”

This story originally appeared on HPC Projects. It appears here as part of a cross-publishing agreement with Scientific Computing World.

Also posted in HPC | Leave a comment

Podcast: DDN WOS Software on OCP Storage Hardware to Enable Hyperscale Storage Clouds

By Rich Brueckner | Published May 22, 2012

In this podcast, Jeff Denworth from DDN provides details on the company’s recent announcement that their Web Object Scaler (WOS) will support Open Compute server and storage platforms in cooperation with the Open Compute Project.

Historically, there has not been an industry movement around standardizing and driving the adoption of mass-market hyperscale hardware technology,” said Jean-Luc Chatelain, Executive Vice President of Strategy and Technology, DDN. “With the new OCP storage hardware specification, DDN is able to focus its cloud storage efforts and investments on the software intelligence that drives today’s business and social connection. The Open Compute movement allows us to harness the power of crowd-sourced hardware design and a highly optimized supply chain to drive the best value for our customers.”

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

Also posted in HPC, HPC Hardware, HPC Software, Podcast, Storage | Leave a comment

Simulating the Next Generation of Fuel-Efficient Engines

By Rich Brueckner | Published May 1, 2012

Marianne Lavelle over at National Geographic News writes that supercomputers like Jaguar at ORNL are helping researchers design the next generation of fuel-efficient engines.

We don’t understand the coupling of turbulent mixing and ignition chemistry in fine enough detail to help us impact the design,” said Jacqueline Chen of Sandia National Laboratories. “You need to get the correct burn rate, or you get a very noisy engine.” In other words, either the fuel mixture needs to be adjusted, or the temperatures in different portions of the mixture need to be stratified, or layered, to control the speed at which pressure rises in the engine.”

Read the Full Story.

Also posted in Computing Research, HPC | Leave a comment

ANI Testbed a 100-Gigbit Highway for Science

By Rich Brueckner | Published May 1, 2012

Linda Vu from Lawrence Berkeley Labs writes that the Advanced Networking Initiative (ANI) has created a 100 Gbps national prototype network and a wide-area network testbed that is changing how researchers think about moving Big Data.

It took us approximately 30 minutes to move 35 terabytes of climate data over a wide-area 100 Gbps network. This is a great accomplishment,” said Mehmet Balman of Berkeley Lab’s Scientific Data Management group. “On a 10 Gbps network, it would have taken five hours to move this much data across the country.”

Read the Full Story.

 

Also posted in Computing Research, HPC, HPC Hardware, Network | Leave a comment

Common Communication Interface (CCI) Project Benefits for HPC

By Rich Brueckner | Published April 30, 2012

Scott Atchley from ORNL writes that the Common Communication Interface (CCI) is an open-source project under development that promises simplicity, portability, performance, scalability, and robustness for parallel applications.

Given the goals described in part 1, we are developing the Common Communication Interface (CCI) as an open-source project for use by any application that needs a NAL. Note that CCI does not replace MPI since it does not provide matching or collectives. But it can be used by an MPI, probably as its NAL (likewise by a parallel file system). For applications that rely on the sockets API, it can provide improved performance when run on systems with high-performance interconnects and fall back on actual sockets when not.

A Tip of the Hat goes to Jeff Squyres for pointing us to this post. Read the Full Story.

Also posted in HPC, HPC Software | Leave a comment

Dell and Clemson Increase Access to Research Computing with Cloud Services

By Rich Brueckner | Published April 24, 2012

Dell announced today that the company is working with Clemson University to provide more Internet2 institutions and organizations access to high performance research computing technology.

Clemson and Dell are establishing a groundbreaking partnership that extends Dell’s community-based management model empowering the research & education community. This partnership is a first step pulling together a broader set of partners to extend the benefits of High Performance and Data Intensive Computing to a wider set of research communities. Reaching this broader audience aids the acceleration of research and inquiry to help solve the ever-increasing and complex problems facing society. Using Internet2′s Innovation Platform concept and emerging suite of Net+ services will allow the academic community to deploy massive resources in response to the data grand challenge.”

Read the Full Story.

Also posted in Cloud HPC, HPC | Leave a comment

Video: OpenSFS Update at LUG 2012

By Rich Brueckner | Published April 23, 2012

In this video, Galen Shipman from ORNL presents: OpenSFS Update. Recorded at LUG 2012 in Austin.

Note: Most of the videos from LUG 2012 are now posted at the OpenSFS site.

Also posted in Events, HPC, HPC Software, LUG 2012, Video | Leave a comment

Video: EOFS Update at LUG 2012

By Rich Brueckner | Published April 23, 2012

In this video, Hugo Falter from European Open File System group presents an EOFS Update. Recorded at LUG 2012 in Austin.

Note: Most of the videos from LUG 2012 are now posted at the OpenSFS site.

Also posted in Events, HPC, HPC Software, LUG 2012, Video | Leave a comment

BGI Taps Tianhe-1A Super for Genomics

By Staff | Published April 23, 2012

Genomics organisation BGI has launched a joint bioinformatics and computing laboratory with National Supercomputing Center in Tianjin (NSCC-TJ). Located in Binhai New Area of Tianjin, China, the Tianhe-BGI Bioinformatics and Computing Joint Laboratory will promote interdisciplinary cooperation in the fields of supercomputing and biological science, and aid development of omics-related industries.

The new lab is in part named after Tianhe-1A, the world’s second fastest supercomputer, which is currently installed at NSCC-TJ. Utilising the system’s 2.57 petaflops computing capacity and experience of multi-omics research at BGI, researchers from the two organisations will conduct an initial project to optimise the pipeline of bioinformatics analysis and develop stronger tools and algorithms to address many scientific challenges in life science.

‘In the next step, we will establish a comprehensive bioinformatics and computing platform based on Tianhe-1A. It will focus on the research and development of the high-performance software with higher efficiency, including standard analysis software, the analytical pipeline and tools for enormous data, among others,’ said Guangming Liu, director of CSCC-TJ. ‘We hope this new laboratory could greatly promote the applications of genomic technologies in agriculture, drug discovery and human health in Binhai New Area and make more contributions to the society.’

Professor Jian Wang, president of BGI, added: ‘In the past, it took a year to conduct a project on the genomics association study of 500 human samples, but now with Tianhe, three hours is enough. We believe this will broaden the applications of Tianhe-1A in life science and greatly accelerate the development of science and technology.’

This story originally appeared on HPC Projects. It appears here as part of a cross-publishing agreement with Scientific Computing World.

Also posted in GPUs, HPC, HPC Hardware | Leave a comment

Need Supercomputer Access? PRACE Issues Call for Proposals

By Rich Brueckner | Published April 18, 2012

Clipped from: prace-ri.eu (share this clip)

 

The European PRACE Research Infrastructure has issued their fifth Regular call for Project Access, inviting applications for high-end (Tier-0) computing resources to carry out projects which have high scientific quality and impact. Allocations will be for 1 year starting November 2012.

Applications are due May 30, 2012.

Also posted in HPC | Leave a comment

HPC Wales to Collaborate with Fujitsu on New Supercomputing Research

By Rich Brueckner | Published April 16, 2012

This week Fujitsu announced it will collaborate with HPC Wales on new supercomputing research, helping to establish seven PhD studentships in computational science in Welsh universities. The studentships form part of a wider strategic collaboration between HPC Wales and Fujitsu, designed to promote the uptake of high-performance computing (HPC) in Welsh industries in areas of priority to the Welsh Government.

We are pleased to be supporting these projects, which are at the leading edge of scientific research and at the same time will contribute to the development of the Welsh economy, said David Craddock, Chief Executive Officer of HPC Wales. “The projects already involve significant collaboration between the universities and businesses and promise to strengthen and grow a number of key areas of the Welsh economy.”

Read the Full Story.

Also posted in Digital Manufacturing, HPC, Video | Leave a comment

Altair and SGI Combine Forces for Power-Efficient Exascale

By Rich Brueckner | Published April 16, 2012

Today SGI and Altair announced a collaboration to develop scheduling and systems management solutions to support energy efficient computing at exascale levels. To get things started, SGI has entered into an OEM agreement with Altair that names the company its preferred workload management supplier, making it possible for SGI to more cost-effectively integrate Altair’s PBS Professional scheduler on its HPC clusters.

The goal of the collaboration is for SGI and Altair to deliver a set of software to efficiently manage large scale systems for performance, resilience, and power optimization. With this software, capacity planning can be based on available power, scaling to meet the changing power requirements of a specific job or an entire workload. Focus areas for the project include workload and application profiling, and power rate and load scheduling. The solution will enable intelligent scheduling based on power consumption, so users can run jobs on the most energy-efficient resource for a given application, or apply policies that allow them to schedule jobs when energy rates are at their lowest.

Read the Full Story.

Also posted in Exascale, HPC | Leave a comment

Interview: EMC Speeds Lustre Integration with Whamcloud

By Rich Brueckner | Published April 13, 2012

This week Whamcloud announced that the company is extending its working relationship with EMC Corporation to provide deeper integration between the Parallel Log-structured File System (PLFS) and Lustre. To get the full story, I caught up with Percy Tzelnic from EMC’s CTO Office and the SVP Fast Data Group.

insideHPC: What is the nature of the collaboration with EMC that you announced this week?

Percy Tzelnic: The collaboration between EMC and Whamcloud is designed to help Lustre improve metadata handling and small file I/O performance, leveraging PLFS, which is open source software whose development started at Los Alamos National Lab and continues as a joint project with EMC. In the extreme HPC domain (large supercomputing clusters), PLFS also reduces checkpoint time by a large order of magnitude.

insideHPC: EMC is a big player in the enterprise storage space. Does this collaboration indicate a growing interest in Lustre on the commercial computing side of the fence?

Percy Tzelnic: EMC has been very active in the HPC domain. A large portion of commercial HPC has been very successfully addressed with EMC Isilon, as well as VNX as block storage for file systems such as StorNext and even Lustre. The current Fast Data initiative is focused on both extreme, as well as commercial HPC. EMC is definitely interested in commercial HPC, and Lustre has emerged in some of the verticals as another valuable tool, enabling VNX block to be deployed in very high bandwidth and low latency use cases.

insideHPC: The news release mentions that this extension of an existing collaboration with EMC. What have been the results so far?

Percy Tzelnic: EMC has been working with Whamcloud for over a year. This collaboration helped with the development of a Lustre appliance that includes EMC VNX technology, in a partnership with a third party. This appliance is being currently test marketed and elicited a high level of interest.

insideHPC: How will this collaboration help with the goal of getting the Lustre client included in the upstream Linux kernel?

Percy Tzelnic: EMC is interested in making Lustre readily consumable by our commercial HPC customers. EMC is collaborating with the Linux community and Whamcloud to enable the availability of Lustre client software as part of the standard Linux distribution.

insideHPC: With tighter integration with PLFS, will Lustre enable much faster checkpoint/restarts for large file systems?

Percy Tzelnic: Yes, PLFS improves checkpoint performance by several orders of magnitude in a Lustre filesystem environment. This is a specific use-case, mostly present in extreme HPC — but PLFS also addresses certain commercial HPC applications needs when deployed with Lustre.

Also posted in HPC, HPC Hardware, HPC Software, Storage | Leave a comment

Colfax Goes Cluster Ready with Sandy Bridge and Bright Computing

By Rich Brueckner | Published April 11, 2012

Colfax International is one of the first vendors out of the gate to have certified Intel Cluster Ready systems based on the new Sandy Bridge Xeon E5 processors. To get customers up and running quickly, the company announced that it will include a free trial of Bright Cluster Manager on its new Intel Xeon E5 processor-based HPC clusters.

Our partnership with Bright Computing is a key step in expanding our HPC product offerings,” said Gautam Shah, CEO of Colfax International. “This partnership provides our customers with powerful, compute-ready HPC systems. Colfax customers can get to work immediately, without the complexity and time-consuming task of setting up and testing their clusters.

Read the Full Story.

Also posted in Compute, HPC, HPC Hardware, HPC Software, System Management | Leave a comment

Jülich Orders Eurotech Super for DEEP Exascale Research

By Rich Brueckner | Published April 6, 2012

Germany’s Jülich center has ordered a 1.2 million euro Aurora supercomputer from Eurotech for use in the EU-funded project DEEP (Dynamical Exascale Entry Platform).

The DEEP consortium, led by Forschungszentrum Jülich, proposes to develop a novel, Exascale-enabling supercomputing architecture that takes the concept of compute acceleration to a new level: instead of adding accelerator cards to Cluster nodes, an accelerator Cluster, called Booster, will complement a conventional HPC system and increase its compute performance. While the Cluster is an off-the-shelf component, the Booster will be designed and built by the DEEP project partners using cutting edge technology. Together with a software stack focused on meeting Exascale requirements, comprising adapted programming models, libraries and performance tools, the DEEP architecture will enable unprecedented scalability. In the DEEP consortium Eurotech will be the responsible to assemble and design the cabinets, racks and blades of the system.

The HPC 10-10 Aurora supercomputer is based on the Sandy Bridge Intel Xeon 2600 series processors with 32 Gb per node of memory and a 3D Torus driven by Extoll software. Read the Full Story.

Also posted in Compute, Exascale, HPC, HPC Hardware, Network | Leave a comment

Advertisement


View All Videos

insideHPC.com is a production of insideHPC, LLC. © 2006-2011 Sitemap