Inside HPC & AI News | High-Performance Computing & Artificial Intelligence

"As HPC resource requirements continue to increase, the need for finding economical solutions to handle the rising requirements increases as well. There are numerous ways to approach this challenge. For example, leveraging existing equipment, adding new or used equipment, and handling uncommon peak usage dynamically through cloud solutions managed by a central job management system can prove to be highly available and resource rich, while remaining economical. In this presentation we will discuss how Wayne State University implemented a combination of these approaches to dramatically increase our compute resources for the equivalent cost of only a few new servers."The post Maximizing HPC Compute Resources with Minimal Cost appeared first on insideHPC.

XSEDE is now accepting 2016 Research Allocation Requests for the Bridges supercomputer. Available starting in January, 2016 at the Pittsburgh Supercomputing Center, Bridges represents a new concept in high performance computing: a system designed to support familiar, convenient software and environments for both traditional and non-traditional HPC users.The post Submit Your 2016 Research Allocation Requests for the Bridges Supercomputer appeared first on insideHPC.

What can we do to help ocean coral survive Global Warming? In this TACC podcast, Jorge Salazar looks at how researchers are using the Stampede supercomputer to investigate how Corals can genetically adapt to warmer waters.The post Podcast: Supercomputing Powers Efforts to Save Ocean Coral appeared first on insideHPC.

"This webinar replay discusses the use of high performance computing (HPC) in the design of aircraft jet engines and gas turbines used to generate electrical power. HPC is the critical enabler in this process, but applying HPC effectively in an industrial design setting requires an integrated hardware/software solution and a clear understanding of how the value outweighs the costs. This webinar will share GE’s perspective on the successful deployment and utilization of HPC, offer examples of HPC’s impact on GE products, and discuss future trends."The post Video: HPC in the Design of Aircraft Engines appeared first on insideHPC.

Today HP and SanDisk announced a long-term partnership to collaborate on a new technology within the Storage Class Memory (SCM) category. The partnership will center around HP’s Memristor technology and expertise and SanDisk’s non-volatile ReRAM memory technology and manufacturing and design expertise to create new enterprise-wide solutions for Memory-driven Computing. The two companies also will partner in enhancing data center solutions with SSDs.The post HP and SanDisk to Team on Memory-Driven Computing appeared first on insideHPC.

Today IBM announced launched a new LC series of servers that infuse technologies from members of the OpenPOWER Foundation and are part of IBM's Power Systems portfolio of servers. According to IBM, the new LC systems perform data analytics workloads faster and cheaper than comparable x86-based servers.The post IBM Launches LC OpenPower Servers appeared first on insideHPC.

"The Robinhood Policy Engine is a versatile tool to manage contents of large file systems. It maintains a replicate of filesystem medatada in a database that can be queried at will. It makes it possible to schedule mass action on filesystem entries by defining attribute-based policies."The post Lustre Video: Robinhood v3 Policy Engine and Beyond appeared first on insideHPC.

The Morton order is a mapping of multidimensional data to one dimension that preserves locality of the data. This is also known as Z-order. "By using Morton ordering as an alternative to row-major or column-major data storage, significant speedups can be achieved on the Intel Xeon Phi coprocessor or Intel Xeon CPU when performing matrix multiplies or matrix transposes."The post Morton Ordering on the Intel Xeon Phi appeared first on insideHPC.

We'd like to invite our readers to participate in our new HPC & Large Enterprise Purchase Sentiment Survey. "It's designed to get a feel for the technology purchasing plans of HPC and large enterprise data centers. We'll also ask some questions about how your data center is approaching new technologies, usage models, and the like. Additionally, we'd like to know how you regard major vendors in the data center space."The post Requesting Your Input on the HPC & Large Enterprise Purchase Sentiment Survey appeared first on insideHPC.

“Although the use of GPUs has generalized nowadays, including GPUs in current HPC clusters presents several drawbacks mainly related with increased costs. In this talk we present how the use of remote GPU virtualization may overcome these drawbacks while noticeably increasing the overall cluster throughput. The talk presents real throughput measurements by making use of the rCUDA remote GPU virtualization middleware.”The post Video: Is Remote GPU Virtualization Useful? appeared first on insideHPC.

Sometimes the inbox for HPC news fills up faster than we can handle. In an effort to keep up, we've compiled noteworthy news into a Jeopardy type of Speed Round that phrases topics in the form a question.The post HPC News Bytes for Oct. 7, 2015 appeared first on insideHPC.

Joseph Lombardo from UNLV presented this talk at the PBS Works User Group. "Lombardo will highlight results from an Alzheimer’s research project that benefited from using PBS Professional. He will then describe the NSCEE’s new system at the Supernap and how this system can be used to advance research for HPC users in both academia/R&D and commercial industry. Lombardo will also highlight two emerging projects; the New School of Medicine and new Technology park."The post Leveraging HPC for Alzheimer’s Research and Beyond appeared first on insideHPC.

A new private Cloud HPC system will soon benefit bioinformatics researchers in their work on bacterial pathogens. The Cloud Infrastructure for Microbial Bioinformatics (CLIMB) project, a collaboration between the University of Birmingham, the University of Warwick, Cardiff University, and Swansea University, will create a free-to-use, world leading cyber infrastructure specifically designed for microbial bioinformatics research.The post Building the CLIMB Project – World’s Largest Single System for Microbial Bioinformatics appeared first on insideHPC.

In this video from the Disruptive Technologies Session at the 2015 HPC User Forum, Intel's Ralph Biesemeyer presents: Intel 3D XPoint Technology."For decades, the industry has searched for ways to reduce the lag time between the processor and data to allow much faster analysis,” said Rob Crooke, senior vice president and general manager of Intel’s Non-Volatile Memory Solutions Group. “This new class of non-volatile memory achieves this goal and brings game-changing performance to memory and storage solutions.”The post Video: Intel 3D XPoint Technology appeared first on insideHPC.

In this video from the LAD'15 Conference, Daniel Kobras from science+computing presents: Operational Characteristics of a ZFS-backed Lustre Filesystem.The post Operational Characteristics of a ZFS-backed Lustre Filesystem appeared first on insideHPC.

Today Seagate Technology announced it has completed its previously announced acquisition of Dot Hill Systems, makers of innovative software and hardware storage systems.The post Seagate Acquires Dot Hill Systems appeared first on insideHPC.

XSEDE's new Jetstream shared cloud resource is coming online early next year, but you can now apply for Jetstream research allocations.The post Apply Now for XSEDE’s Jetstream Shared Cloud Research Allocations appeared first on insideHPC.

Steve Conway from IDC describes high performance computing and how it really does impact our daily lives. "When you put HPC together with some of the most creative, scientific, engineering & business minds on the planet, magical things happen."The post IDC’s Steve Conway on Why HPC Matters appeared first on insideHPC.

With the explosion of data over the past few years, data storage has become a hot topic among corporate decision makers. It is no longer sufficient to have adequate space for the massive quantities of data that must be stored; it is just as critical that stored data be accessible without any bottlenecks that impede the ability to process and analyze data in real time.The post RDMA Enabling Storage Technology Revolution appeared first on insideHPC.

Hussein Harake from CSCS presented this talk at the HPC Advisory Council Spain Conference. “IME unleashes a new I/O provisioning paradigm. This breakthrough, software defined storage application introduces a whole new new tier of transparent, extendable, non-volatile memory (NVM), that provides game-changing latency reduction and greater bandwidth and IOPS performance for the next generation of performance hungry scientific, analytic and big data applications – all while offering significantly greater economic and operational efficiency than today’s traditional disk-based and all flash array storage approaches that are currently used to scale performance.”The post Video: Infinite Memory Engine (IME) Burst Buffer Experience at CSCS appeared first on insideHPC.

NERSC has selected a number of HPC research projects to participate in the center’s new Burst Buffer Early User Program, where they will be able to test and run their codes using the new Burst Buffer feature on the center’s newest supercomputer, Cori.The post Users to Test DataWarp Burst Buffer on Cori Supercomputer appeared first on insideHPC.

"We are excited that the H2020 SAGE Project gives us the opportunity to research and move HPC storage into the Exascale age,” said Ken Claffey, vice president and general manager, Seagate HPC systems business. “Seagate will contribute its unique skills and device technology to address the convergence of Exascale and Big Data, with an excellent selection of participants each bringing their own capabilities together to build the future of storage on an unprecedented scale.”The post Seagate to Lead Sage Storage Project for Exascale Horizon 2020 appeared first on insideHPC.

"For High Performance Computing users who leverage open-source Lustre software, a good file system for big data is now getting even better. Building on its substantial contributions to the Lustre community, Intel is rolling out new features that will make the file system more scalable, easier to use, and more accessible to enterprise customers."The post Video: Intel Commitment to Lustre appeared first on insideHPC.

Can 3D-stacking technology topple the long-standing "memory wall" that's been holding back HPC application performance? A new paper from the Barcelona Supercomputing Center written in collaboration with experts from Chalmers University and Lawrence Livermore National Laboratory concludes that it will take more than just the simple replacement of conventional DIMMs with 3D-stacked devices.The post New Paper: Can 3D-Stacking Topple the Memory Wall? appeared first on insideHPC.

In this podcast, the Radio Free HPC team looks at the new round of Grand Challenges targeted by the National Strategic Computing Initiative (NSCI). The conversation was sparked by an Scientific Computing editorial by IBM’s Dave Turek.The post Radio Free HPC Looks at the Grand Challenges of NSCI appeared first on insideHPC.

ESnet has released open source code for building online Interactive Network Portals. "Now that the libraries are made available, the team hopes that other organizations will take the code, use it, add to it and work with ESnet to make the improvements available to the community."The post ESnet Releases Code for Building Online Interactive Network Portals appeared first on insideHPC.

Tom Wilkie from Scientific Computing World reports on how China’s HPC vendors are seeking export markets with the support of their Government. With exhibits and various talks at ISC 2015, Inspur and Sugon were busy showcasing their technologies for the European market.The post Chinese HPC Vendors Look to Expand Overseas appeared first on insideHPC.

"DMF has been protecting data in some of the industries largest virtualized environments all over the world, enabling them to maintain uninterrupted online access to data for more than 20 years. Some customers have installations with over 100PB online data capacity, and billions of files, which they are able to manage at a fraction of the cost of conventional online architectures."The post Video: DMF and Tiering Update appeared first on insideHPC.

SC15 has stepped up with a series of blog posts previewing the conference this year, an effort that seems much more engaging than the random press releases we've seen in the past.The post SC15 Blog Puts the Spotlight on Invited Talks appeared first on insideHPC.

"ThroughPuter PaaS is purpose-built for secure, dynamic cloud computing of parallel processing era. ThroughPuter offers unique, realtime application load and type adaptive parallel processing: Get the speed-up from parallel execution cost-efficiently where and when any given program/task benefits most from the parallel processing resources. Addressing the parallel processing challenge takes a full programming-to-execution platform approach."The post Executing Multiple Dynamically Parallelized Programs on Dynamically Shared Cloud Processors appeared first on insideHPC.

The good folks from the StartupHPC-15 Conference have posted the Agenda for their meeting at SC15. The day-long conference takes place Monday, Nov 16 in Austin at the Capital Factory in Downtown Austin, Texas. "Does your Startup have ties to High Performance Computing? Please come, meet like minded people, listen to industry notables, and help StartupHPC continue its efforts to build a support community."The post StartupHPC-15 Conference Posts Agenda for Austin Event appeared first on insideHPC.

"Andreas presents an overview on the features currently under development for the upcoming Lustre 2.8 and 2.9 releases. This includes Layout Enhancement, Progressive File Layouts, Data-on-MDT, and improved single-client metadata and IO performance. In addition, several Lustre-specific ZFS improvements are also under development that will be available in this timeframe.”The post Video: Lustre 2.9 and Beyond appeared first on insideHPC.

"The HP Apollo 8000 supercomputing platform approaches HPC from an entirely new perspective as the system is cooled directly with warm water. This is done through a “dry-disconnect” cooling concept that has been implemented with the simple but efficient use of heat pipes. Unlike cooling fans, which are designed for maximum load, the heat pipes can be optimized by administrators. The approach allows significantly greater performance density, cutting energy consumption in half and creating synergies with other building energy systems, relative to a strictly air-cooled system."The post Video: HP R&D and HPC appeared first on insideHPC.

"By adopting an MDX philosophy, engineers are able to test designs automatically from the early concept stages and against all of the physical factors that might influence a system’s performance. It assesses which set of design parameters will break a system, and which will improve it. This pushes back the simulation process to force engineers to question every assumption they have made within a design, and optimise it appropriately by assessing a simulation with multiple operating scenarios."The post Is MDX the Future of Engineering Simulation? appeared first on insideHPC.

“NOAA will acquire software engineering support and associated tools to re-architect NOAA’s applications to run efficiently on next generation fine-grain HPC architectures. From a recent procurement document: “Finegrain architecture (FGA) is defined as: a processing unit that supports more than 60 concurrent threads in hardware (e.g. GPU or a large core-count device).”The post Video: NOAA Software Engineering for Novel Architectures (SENA) Project appeared first on insideHPC.

Today the Barcelona Supercomputing Center (BSC) announced the opening of their Performance Optimization and Productivity (POP) Center of Excellence. With the POP, developers of applications that require the use of High Performance Computing can count now with the free advice of European experts to analyze the performance of its codes.The post BSC Opens Productivity Center of Excellence for HPC Apps appeared first on insideHPC.

Climaveneta of Italy announced that the company has won a contract to provide liquid-cooling equipment for a 100 Petaflop supercomputer coming to the Jiangnan Institute of Computer Technology in Wuxi, China, near Shanghai.The post Climaveneta to Provide Liquid Cooling for 100 Petaflop Supercomputer Coming to China appeared first on insideHPC.

“Exascale levels of computing pose many system- and application-level computational challenges. Mellanox as a provider of end-to-end communication services is progressing the foundation of the InfiniBand architecture to meet the exascale challenges. This presentation will focus on recent technology improvements which significantly improve InfiniBand’s scalability, performance, and ease of use.”The post Video: The Road to Exascale appeared first on insideHPC.

"A parallel implementation of SpMV can be implemented, using OpenMP directives. However, by allocating memory for each core, data races can be eliminated and data locality can be exploited, leading to higher performance. Besides running on the main CPU, vectorization can be implemented on the Intel Xeon Phi coprocessor. By blocking the data in various chunks, various implementations on the Intel Xeon Phi coprocessor can be run and evaluated."The post Sparse Matrix Multiplication appeared first on insideHPC.

Today the San Diego Supercomputer Center (SDSC) announced that it has made significant upgrades to its cloud-based storage system to include a new range of computing services designed to support science-based researchers, especially those with large data requirements that preclude commercial cloud use, or who require collaboration with cloud engineers for building cloud-based services.The post SDSC Steps up with Upgraded Cloud and Storage Services appeared first on insideHPC.

Chris Morrone from OpenSFS/LLNL gave this talk at LAD'15. "The first thing I want to talk about is that Lustre.org is now managed collectively by OpenSFS and EOFS. So the Lustre.org site is now managed by the community. One of the major benefits of this is that the major mailing lists (lustre-announce, lustre-discuss, and lustre-devel) are now under our control, so we want everyone to come back to those mailing lists and start using them again."The post Lustre Development Update from LAD’15 appeared first on insideHPC.

The Cal Poly San Luis Obispo Computer Science Department is hiring a tenure-track faculty position in our HPC Job of the Week.The post Job of the Week: Tenure-track Faculty Position in HPC at Cal Poly appeared first on insideHPC.

In this podcast, the Radio Free HPC team goes over a Trip Report from Rich Brueckner from insideHPC, who's been on the road at a series of HPC conferences. We captured more that 50 talks in the past month, and we have them all right here with the very latest in High Performance Computing.The post Radio Free HPC Looks at Highlights from Fall 2015 HPC Conferences appeared first on insideHPC.

Today the PRACE Partnership for Advanced Computing in Europe issued their 12th Call for Proposals. By providing access to some of the fastest supercomputer in Europe, the Call for Proposals targets large-scale, computationally intensive projects that would not be possible or productive without access to PRACE resources.The post PRACE Opens 12th Call for Proposals appeared first on insideHPC.

"NVLink enables fast data exchange between CPU and GPU, thereby improving data throughput through the computing system and overcoming a key bottleneck for accelerated computing today. NVLink makes it easier for developers to modify high-performance and data analytics applications to take advantage of accelerated CPU-GPU systems. We think this technology represents another significant contribution to our OpenPOWER ecosystem.”The post Video: NVLink Interconnect for GPUs appeared first on insideHPC.

Today Mellanox announced a definitive agreement to acquire EZchip, a leader in high-performance processing solutions for carrier and data center networks. You may recognize EZchip from their recent Tilera acquisition, makers of Tile-Gx multicore network processors.The post Mellanox to Acquire EZchip AKA Tilera appeared first on insideHPC.

For some applications, cloud based clusters may be limited due to communication and/or storage latency and speeds. With GPUs, however, these issue are not present because application running on cloud GPUs perform exactly the same as those in your local cluster -- unless the application span multiple nodes and are sensitive to MPI speeds. For those GPU applications that can work well in the cloud environment, a remote cloud may be an attractive option for both production and feasibility studies.The post Developing a Plan for Cloud Based GPU Processing appeared first on insideHPC.

Today Cray announced the Company has been awarded a contract to provide a Cray XC40 supercomputer to the Yukawa Institute for Theoretical Physics (YITP) at Kyoto University in Japan. The two-cabinet Cray XC40 system will provide the YITP user community with a supercomputer that occupies one-fourth of the physical footprint of the Institute's previous system and a 4x improvement in overall compute performance. The liquid-cooled system will power a wide range of theoretical physics research at YITP, such as astrophysics, nuclear physics and particle physics, and will also serve as a shared supercomputing resource supporting theoretical physicists all across Japan.The post Kyoto University to Install Cray XC40 Supercomputer appeared first on insideHPC.

DK Panda from Ohio State University presented this talk at the HPC Advisory Council Spain Conference. “Dr. Panda and his research group members have been doing extensive research on modern networking technologies including InfiniBand and 10-40GE/iWARP. His research group is currently collaborating with National Laboratories and leading InfiniBand and 10-40GE/iWARP companies on designing various subsystems of next generation high-end systems."The post Communication Frameworks for HPC and Big Data appeared first on insideHPC.