Now that the deployment of the 1 Terabyte/sec file system at Blue Waters has been completed, what comes next? In this video from the Xyratex Blog, John Fragalla, principal solutions architect at Xyratex, discusses the value that ClusterStor brings to the HPC market and what the company has learned from designing and deploying ClusterStor solutions.
Video: Lessons Learned from the Blue Waters 1 Terabyte/sec File System
Video: HPCS I/O Scenarios Update
In this video from the Lustre User Group 2013, John Carrier from Cray presents: HPCS I/O Scenarios Update.
Download the slides (PDF) or check out our LUG 2013 Video Gallery.
Air-Cooling Cascade with the New Cray XC30-AC Supercomputer
Today Cray introduced the Cray XC30-AC supercomputer as an air-cooled addition to its series of Cray XC30 (Cascade) systems. Shipping now, the new Cray XC30-AC supercomputer includes all of the advanced HPC technologies offered in the Cray XC30 system, and features aggressive price points intended to attract a new a class of HPC users – the technical enterprise.
Innovation is not limited to Fortune 100 companies. There are many Fortune 1000 companies, and even departments within Fortune 100 companies, with a growing need for a supercomputing system that provides a critical tool for taking advantage of performing complex simulations,” said Peg Williams, Cray’s senior vice president of high performance computing systems. “With all of the features and functionality of our high-end Cray XC30 systems, our new Cray XC30- AC supercomputer is perfectly suited for technical enterprise customers, giving them the ability to leverage all of the world-class computational resources of a Cray supercomputer at much lower starting price points.”
In case you’re wondering, the Cray XC30-AC does not incorporate Appro technology. Cray acquired Appro late last year, and that company was known for its innovative system cooling.
With prices starting at $500,000, the Cray XC30-AC does feature the same key traits of the Cray XC30 system – the Aries system interconnect and the Cray Linux Environment. The system has ability to handle a wide variety of processor types, including Intel Xeon processors, Intel Xeon Phi coprocessors, and NVIDIA Tesla GPU accelerators.
Read the Full Story or check out the related post by Jay Gould over at the Cray Blog.
Video: High Availability in Lustre
In this video from the Lustre User Group 2013, John Fragalla from Xyratex presents: High Availability in Lustre.
Download the slides (PDF) or check out our LUG 2013 Video Gallery.
Video: Massive I/O Requirements for the SKA Telescope
In this video from the 2013 Open Fabrics Developer Workshop, Bill Boas from Cray presents: Massive I/O Requirements for the SKA Telescope.
Processing the vast quantities of data produced by the SKA will require very high performance central supercomputers capable of 100 petaflops per second processing power. This is about 50 times more powerful than the most powerful supercomputer in 2010 and equivalent to the processing power of about one hundred million PCs.
Download the slides (PDF) or check out more OFA videos in our Open Fabrics Worshop Video Gallery.
Upgrading the Grid for the LHC
Over at International Science Grid This Week, Katie Kahlie writes that the current maintenance hiatus for the Large Hadron Collider provides a window to upgrade one of the most ambitious data grids on the planet.
The challenges for the Grid were three-fold. The main one was to understand how best to manage the LHC data and use the Grid’s heterogeneous environment in a way that physicists could concern themselves with analysis without needing to know where their data were. A distributed system is more complex and demanding to master than the usual batch-processing farms, so the physicists required continuous education on how to use the system. The Grid needs to be fully operational at all times (24/7, 365 days/year) and should “never sleep”, meaning that important upgrades of the Grid middleware in all data centres must be done on a regular basis. For the latter, the success can be attributed in part to the excellent quality of the middleware itself (supplied by various common projects, such as WLCG/EGEE/EMI in Europe and OSG in the US, see box) and to the administrators of the computing centres (coordinated by EGI in Europe and OSG in North America), who keep the computing fabric running continuously.
Read the Full Story.
Video: EIOW Exascale I/O Working Group
In this video from the Lustre User Group 2013, Meghan McClelland from Xyratex presents: EIOW – Exascale I/O Working Group.
There is a fierce competition on the storage market to offer the best performing devices, with great management at a low price. The EIOW group, from the outset, decided that it would not attempt to offer an end-to-end solution, which would necessarily involve competing instead of working with storage providers. The focus of EIOW is on middleware to provide, for example, schemas describing data structure and layout, novel access methods to data for applications, a uniform data management infrastructure and a framework for the implementation of layered I/O software, similar in spirit to HDF5 as a specialized use of a parallel file system. We decided EIOW should be open, and have interfaces to layer on lower level storage infrastructure such as object stores, databases and file systems as provided by storage providers, to allow their expertise and leadership in this area to continue to benefit the HPC community.
Download the EIOW whitepaper and slides, or check out our LUG 2013 Video Gallery.
RDMA and Storage at a Distance
Over at Forbes, Tom Coughlin writes that RDMA extends the capability of fast direct access to memory between computers in a cluster to greater distances, within a Metropolitan Area Network (MAN ) or even in a Wide Area Network (WAN) that can span continents.
RDMA over a WAN allows some very useful capabilities that can increase the overall power of a clustered computer system. It can provide remote collaboration with a remote file system allowing access as though it were local, enabling apparent real-time collaboration. RDMA also allows very efficient file transfer over a WAN. This direct data placement is accomplished with little impact on the processors on either end of the file transport. These features are very useful for working with large data files such as those common in many HPC applications. Storage at a Distance will not directly impact conventional client computing since these devices typically don’t have access to dedicated high-speed Internet connections. However with the growth of on-line (cloud) services the use of RDMA could accelerate many background processes within a given data center and between data centers. This could improve overall cloud performance and provide services such as fast backups and replications of data to provide data recovery. Thus Storage at a Distance could have a great impact on the overall performance and capabilities available over the Cloud.
Read the Full Story or see Coughlin’s recent Open Fabrics presentation over at inside-Cloud.
Video: Infinetics – Innovative Topologies
In this video from the 2013 Open Fabrics Developer Workshop, Harry Quackenboss and Ratko Tomic from Infinetics present: Innovative Topologies.
We have invented a unique approach to building a fabric across a large number of Ethernet switches, and built a comprehensive technology platform based on this Flexible Radix Switching (FRS) technique. This innovation enables transparent integration with existing data center solutions and big improvements to networks supporting cloud, virtualization, and big data applications. These data center network solutions are superior in terms of cost, performance, robustness and ease of use.
Download the slides (PDF). You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.
Intel MPI Library for Intel Xeon Phi-based Clusters & MVAPICH2 for Intel MIC
In this video from the 2013 Open Fabrics Developer Workshop, Bill Magro from Intel presents: Intel MPI Library: Implementation for Intel Xeon Phi Based Clusters. Download the slides (PDF).
In this follow-up session, DK Panda from Ohio State University presents: MVAPICH2 for Intel MIC.
You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.
Video: Network Direct v2 and WinOFED
In this video from the 2013 Open Fabrics Developer Workshop, Fab Tillier from Microsoft presents: Network Direct v2 and WinOFED.
You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.
Penguin Computing Unveils Large-Scale Storage Platform
Penguin Computing has revealed its new Cloud CS Storage Platform that will utilize Scality’s RING Organic Storage software.
Performance, availability and scalability requirements of large scale cloud businesses cannot be met with traditional IT approaches to storage, that typically excel in one of these areas and fall short in another,” said Charles Wuischpard, CEO Penguin Computing. “To meet the demands of our customers that require storage solutions at the petabyte scale we based our large scale storage appliance Icebreaker CS on software from Scality. With its distributed no-shared architecture and its sophisticated Advanced Resilience Configuration, Scality RING offers excellent storage scalability and great availability without compromising performance.”
Read the Full Story.
SGI to Provide Massive Data Storage Capability for the Australian Square Kilometre Array Pathfinder
This week SGI announced that iVEC and the Commonwealth Scientific and Industrial Research Organisation (CSIRO) have selected SGI to provide the massive data management infrastructure at the Pawsey Supercomputing Centre. The centre is part of the Australian Government Super Science Initiative to support the Australian Square Kilometre Array Pathfinder (ASKAP) and the Murchison Widefield Array (MWA) radio astronomy facility.
For decades, SGI has been solving Big Data challenges for researchers across science and industry in an effort to find answers to the world’s toughest challenges,” said Jorge Titinger, president and CEO, SGI. “We are very pleased to support the data management needs of the Pawsey Supercomputing Centre. They are conducting impressive research, and with our InfiniteStorage and UV 2000 technology, will be able to reach results and interactions more quickly. We look forward to continuing this partnership and seeing the Pawsey Centre’s revolutionary solutions to challenges in science.”
Read the Full Story.
Evolving OFS – Teaching Sharks to Swim, from the Top Down
In this video from the 2013 Open Fabrics Developer Workshop, Paul Grun from OFA presents: Evolving OFS – Teaching Sharks to Swim, from the Top Down.
This talk is a follow-on to Grun’s OFA workshop opening presentation. You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.
Interview: Open Fabrics Alliance Looks Ahead
In this video, Jim Ryan and Paul Grun from OFA discuss where Open Fabrics is headed in the future.
Open Fabrics began as a way of providing a memory-to-memory messaging service from application to application. So, fundamentally, that’s what sets Open Fabrics apart from any other network. Typically networks are about delivering packets from one platform to another. But Open Fabrics takes a perspective that its about the way the applications communicate, it’s truly about memory to memory.
You can check out more OFA videos at our Open Fabrics Workshop Video Gallery.
