High-Performance Computing News Analysis | insideHPC

The Lustre Administrators & Developers group has issued their Call for Presentations. Registration is now open for the LAD'18 event, which takes place Sept. 24-25 in Paris. "We invite community members to send proposals for presentation. Those talks could cover, by example, tools, administration experiences, configuration setup, developments, tunings, tweaking, … No proceeding is required, just an abstract for a 30-min technical presentation."The post Call for Lustre Presentations: LAD’18 in Paris appeared first on insideHPC.

In this video from ISC 2018, Perry Hayes and Martin Galle from Supermicro describe the company's latest innovations for HPC and AI workloads. "Supermicro delivers the industry's fastest, most powerful selection of HPC solutions offering even higher density compute clusters to deliver maximum parallel computing performance for any science and engineering, simulation, modeling, or analytics applications," said Charles Liang, president and CEO of Supermicro.The post Supermicro Steps up to HPC & AI Workloads at ISC 2018 appeared first on insideHPC.

The MVAPICH User Group Meeting (MUG 2018) has published its Speaker Agenda. The event will take place from August 6-8 in Columbus, Ohio. "MUG aims to bring together MVAPICH2 users, researchers, developers, and system administrators to share their experience and knowledge and learn from each other. The event includes Keynote Talks, Invited Tutorials, Invited Talks, Contributed Presentations, Open MIC session, hands-on sessions MVAPICH developers, etc."The post Agenda Posted: MVAPICH User Group (MUG) Meeting in Ohio appeared first on insideHPC.

In this video, Gary Tyreman from Univa describes how the company is helping HPC users move their workloads to the Cloud with their Navops products. "Univa is the leading innovator in workload management and orchestration solutions. With Navops suite of products, Univa is bringing its expertise to containers. Univa Navops is a suite of products that enable enterprises to easily migrate to the cloud or hybrid cloud, increase efficiencies and run containers at scale."The post Univa Brings Navops to HPC at ISC 2018 appeared first on insideHPC.

In today’s world where science and engineering depend on the simulation of new materials and their behavior is of critical importance. New materials are constantly being designed and brought into product design in order to create products that can withstand many environmental conditions and still perform for their intended use. HPC is critical for the simulation of these materials and applications which perform at the fastest speed available on a given hardware platform can lead to earlier introduction of products that contain these materials.The post Materials Science Modeling with VASP appeared first on insideHPC.

Today Spectra Logic announced a set of updates to its enterprise tape libraries. The enhancements benefit customers in government, scientific research, high performance computing, media and entertainment, and public cloud environments who must preserve massive amounts of data long term. "In today’s world, organizations that extract more value from their data gain a competitive edge,” said Nathan Thompson, CEO of Spectra Logic. “Advancements in tape library functionality benefit organizations with large-scale computing platforms, enabling them to use, retain and, in some cases, retrieve enormous amounts of data quickly, securely and affordably for the long term.”The post Spectra Logic Enhances Tape Library Offerings appeared first on insideHPC.

In this video from ISC 2018, Laura Shepard and Jason Coari from Quantum Corporation describe how the company's high speed storage solutions power AI & HPC applications. "At ISC, Quantum highlighted end-to-end storage capabilities for large-scale HPC environments. Quantum offerings featured at their exhibit included high-performance Xcellis scale-out storage appliances to support data-intensive processing workflows, and StorNext HSM for automated migration of extremely large data sets to cost-effective storage tiers such as tape, object storage and the cloud."The post Quantum Corporation Optimizes Data Intensive Workloads at ISC 2018 appeared first on insideHPC.

In this video from ISC 2018, Jeff Reser from SUSE describes how the company's software enables High Performance Computing with HPC Modules, lower costs, and support for ARM. "SUSE Linux Enterprise for High Performance Computing provides a parallel computing platform for high performance data analytics workloads such as artificial intelligence and machine learning. Fueled by the need for more compute power and scale, businesses around the world today are recognizing that a high performance computing infrastructure is vital to supporting the analytics applications of tomorrow."The post SUSE offers Optimized HPC Modules at ISC 2018 appeared first on insideHPC.

A theoretical plasma physicist and a computational biologist are co-winners of the 2018 Frederick A. Howes Scholar in Computational Science Award. "The honorees are Seth Davidovits, now a Department of Energy (DOE) Fusion Energy Postdoctoral Fellow at the Princeton Plasma Physics Laboratory, and Sarah Middleton, now with pharmaceutical maker GlaxoSmithKline."The post Davidovits and Middleton Share 2018 Howes Scholar in Computational Science Award appeared first on insideHPC.

In this video, Jack Wells from the Oak Ridge Leadership Computing Facility and Duncan Poole from NVIDIA describe how OpenACC enabled them to port their codes to the new Summit supercomputer. "In preparation for next-generation supercomputer Summit, the Oak Ridge Leadership Computing Facility (OLCF) selected 13 partnership projects into its Center for Accelerated Application Readiness (CAAR) program. A collaborative effort of application development teams and staff from the OLCF Scientific Computing group, CAAR is focused on redesigning, porting, and optimizing application codes for Summit’s hybrid CPU–GPU architecture."The post OpenACC Helps Scientists Port their code at the Center for Application Readiness (CARR) appeared first on insideHPC.

In this NERSC News Podcast, Debbie Bard from NERSC describes how Deep Learning can help scientists accelerate their research. "Deep learning is enjoying unprecedented success in a variety of commercial applications, but it is also beginning to find its footing in science. Just a decade ago, few practitioners could have predicted that deep learning-powered systems would surpass human-level performance in computer vision and speech recognition tasks."The post Podcast: Deep Learning for Scientific Data Analysis appeared first on insideHPC.

Thorsten Kurth from LBNL gave this talk at the PASC18 conference. "We present various studies on very large scale distributed deep learning on HPC systems including the ~10k node Intel Xeon-Phi-based Cori system at NERSC. We explore CNN classification architectures and generative adversarial networks for HEP problems using large images corresponding to full LHC detectors and high-resolution cosmology convergence maps."The post Extreme Scale Deep Learning at NERSC appeared first on insideHPC.

The Computer History Museum in Silicon Valley recently added a piece of TACC's history into their permanent historical collection — sealing its place as a milestone in computing.We're always searching around the world for new, interesting, and important computing objects," said Dag Spicer, senior curator at the Computer History Museum. "TACC's Sun Microsystems 2007 Magnum switch was a critical part of high-performance computing at that time in history. The TACC switch was the largest of its class and is an example of InfiniBand technology, which has long been a key enabling technology for high performance computing."The post Legendary Magnum InfiniBand Switch comes to Computer History Museum appeared first on insideHPC.

DE Shaw Research in New York is seeking a System Administrator in our Job of the Week. Ideal candidates should have strong fundamental knowledge of Linux concepts such as file systems, networking, and processes in addition to practical experience administering Linux systems.The post Job of the Week: System Administrator at DE Shaw Research appeared first on insideHPC.

Today Adaptive Computing Enterprises announced that it has changed the name of its flagship software product “Moab” to “Moab Cloud for the HPC Suite.” The new name more accurately reflects the product’s additional cloud-bursting capabilities. "Moab Cloud for the HPC Suite adds a new level of benefits for HPC ecosystems by combining the time-tested elements of Moab with advanced cloud-bursting capabilities. The new solution can “burst” additional workloads to an external cloud on-demand. It is easy to use, manage, and configure and integrates with on-premise resources. It offers full stack provisioning, is automated, and is very cost-effective for customers."The post Moab Cloud for the HPC Suite Adds New Capabilities appeared first on insideHPC.

Today D-Wave Systems announced the publication of a significant scientific result in the peer-reviewed journal Science. The article, titled “Phase transitions in a programmable spin glass simulator,” details how a D-Wave 2000Q quantum computer was used to predict phase transitions within a particular quantum mechanical system known as the transverse field Ising model. "This work represents an important milestone for quantum computing, because it is the first time physics of this kind has been simulated in a scalable architecture at such a large scale,” said Vern Brownell, CEO of D-Wave. “It also provides unprecedented validation for annealing quantum computing, which is the basis of D-Wave’s quantum technology.”The post D-Wave Demonstrates Large-Scale Programmable Quantum Simulation appeared first on insideHPC.

In this video, Satinder Nijjar from NVIDIA describes the new DGX-2 GPU supercomputer. "Experience new levels of AI speed and scale with NVIDIA DGX-2, the first 2 petaFLOPS system that combines 16 fully interconnected GPUs for 10X the deep learning performance. It’s powered by NVIDIA DGX software and a scalable architecture built on NVIDIA NVSwitch, so you can take on the world’s most complex AI challenges."The post ISC 2018: NVIDIA DGX-2 — The World’s Most Powerful AI System on Display appeared first on insideHPC.

Today Supermicro introduced first-to-market workstation optimized for the new Intel Xeon E-2100 processors. "From professionals to content creators, our customers will benefit from the performance and reliability that these new workstation solutions offer. Furthermore, our new compact IoT system will surely be deployed in a wide range of applications from medical and surveillance appliances to robotic and industrial environments."The post Supermicro Workstation Optimized for Intel’s New Xeon E-2100 Processors appeared first on insideHPC.

In this video from ISC 2018, James Coomer from DDN describes the company's latest high performance storage technologies for AI and HPC workloads. "Attendees at ISC 2018 learned how organizations around the world are leveraging DDN’s people, technology, performance and innovation to achieve their greatest visions and make revolutionary insights and discoveries! Designed, optimized and right-sized for Commercial HPC, Higher Education and Exascale Computing, our full range of DDN products and solutions are changing the landscape of HPC and delivering the most value with the greatest operational efficiency."The post DDN Steps Up to HPC & AI Workloads at ISC 2018 appeared first on insideHPC.

In this video, Kathy Yelick from LBNL describes why the US needs to accelerate its efforts to stay ahead in AI and Big Data Analytics. "Data-driven scientific discovery is poised to deliver breakthroughs across many disciplines, and the U.S. Department of Energy, through its national laboratories, is well positioned to play a leadership role in this revolution. Driven by DOE innovations in instrumentation and computing, however, the scientific data sets being created are becoming increasingly challenging to sift through and manage."The post Video: Kathy Yelick from LBNL Testifies at House Hearing on Big Data Challenges and Advanced Computing appeared first on insideHPC.

Steve Simms from Indiana University gave this talk at the DDN User Group meeting in Frankfurt. "ZFS backed OST’s can be migrated to new hardware or to existing reconfigured hardware by leveraging ZFS snapshots and ZFS send/receive operations. The ZFS snapshot/send/receive migration method leverages incremental data transfers, allowing an initial data copy to be "caught up" with subsequent incremental changes."The post Video: Lustre / ZFS at Indiana University appeared first on insideHPC.

In this episode of Let's Talk Exascale, Pavan Balaji and Ken Raffenetti describe their efforts to help MPI, the de facto programming model for parallel computing, run as efficiently as possible on exascale systems. "We need to look at a lot of key technical challenges, like performance and scalability, when we go up to this scale of machines. Performance is one of the biggest things that people look at. Aspects with respect to heterogeneity become important."The post Podcast: Evolving MPI for Exascale Applications appeared first on insideHPC.

The difference between a digitally dynamic business, and one who can’t keep up, is the inclusion of a capable technology leader. As the role has evolved, so too have the demands on Chief Information Officers. "Awareness of digital systems is now a key contribution to developing business strategy in several areas, including operations, expansion and marketing. Uncover the skills for success today."The post How to Become a Dynamic Technology Leader appeared first on insideHPC.

In this video from ISC 2018, Mark Seamans from HPC describes how the HPE Data Management Framework optimizes data accessibility and storage resource utilization by enabling a hierarchical, tiered storage management architecture. "With HPE DMF, Data is allocated to tiers based on service level requirements defined by the administrator. For example, frequently accessed data can be placed on a flash, high-performance tier, less frequently accessed data on hard drives in a capacity tier, and archive data can be sent off to tape storage."The post HPE Data Management Framework – Tiering, Organizing and Protecting your Data appeared first on insideHPC.

The perennial question for IT asset acquisition is whether to build or consume, and there is no ‘one size fits all’ answer to the question. Individual components provide the maximum flexibility, but also require the maximum of self support. Reference architectures provide the recipe and guidance, but the customer still has the responsibility for making the system work.The post Where Ready Nodes are the Optimal Choice appeared first on insideHPC.

Today CSCS in Lugano announced plans to archive research data collected by the large-scale research facilities at the Paul Scherrer Institute (PSI) in Villigen. The collaboration between PSI and CSCS enabled major improvements to the data transfer and storage process. "Storing and archiving data is part of everyday life at CSCS. However, transferring huge amounts of data — including ongoing research projects online across Switzerland as well as an entire data archive containing decades of major completed projects — via fibre-optic cable presents a logistical challenge."The post CSCS Takes on Big Data from the Paul Scherrer Institute appeared first on insideHPC.

The October HPC User Forum at HLRS Will Showcase HPC Europe. The event takes place Oct. 1-2, 2018 in Stuttgart, Germany. "Key topics will be HPC in Germany, HPC in Europe, automated driving systems and urban AI uses, plus an update on quantum computing and other emerging technologies."The post Preliminary Agenda Posted for October HPC User Forum in Stuttgart appeared first on insideHPC.

Over at CSCS, Valentina Tamburello writes that more than 400 scientists from all over the world met in Basel in early July for PASC18. With more than 200 talks centered around the conference theme of “Fast and Big Data, Fast and Big Computation” 400 attendees enjoyed the exchange of knowledge in the area of Scientific Computing and Computational Science.The post PASC18 Conference Grows in Attendance and Scope appeared first on insideHPC.

In this video from the HPE booth at ISC 2018, Barbara Murphy from WekaIO describes how the company's fast parallel file system for NVMe devices speeds HPC and Machine Learning workloads. "You invested in the best infrastructure to run your AI and data intensive applications, so don't let data accessibility be the bottleneck to your productivity gains. To maximize your investments and resolve the GPU and CPU starvation problem, you need a shared file system that ensures data is available to the applications. WekaIO delivers all the bandwidth you need, so your applications never have to wait for data."The post HPE Teams with WekaIO for HPC and Machine Learning appeared first on insideHPC.

In this podcast, the Radio Free HPC team offers up a Trip Report from ISC 2018 in Frankfurt. It was a whirlwind week for news with a new USA machine on the TOP500, but the other big news centered around the convergence of HPC & AI. This common theme was all over the show floor, with use cases on display in dozens of exhibits.The post Radio Free HPC Trip Report from ISC 2018 appeared first on insideHPC.

In this video from ISC 2018, Jaan Mannik from One Stop Systems describes the company's HPC systems and new composable infrastructure solutions. OneStop also showcased a wide array of its high-density NVIDIA GPU-based appliances, as well as showcase a live remote connection to one of its machine learning and HPC platforms. "OSS leads the market in external systems that increase a server's performance in HPC applications, reducing cost and impact on data center infrastructure. These technology-hungry applications include AI (artificial intelligence), deep learning, seismic exploration, financial modeling, media and entertainment, security and defense."The post One Stop Systems Showcases Composable Infrastructure for GPU Workloads at ISC 2018 appeared first on insideHPC.

In this video from ISC 2018, Steve Branton from Asetek describes the company's wide array of liquid cooling solutions for HPC. "With 11 systems the TOP500 including the 9th fastest HPC installation in the world, Asetek’s RackCDU D2C is used by HPC sites worldwide to maximize sustained throughput, decrease energy use and increase cluster density. Asetek is the world-leading provider of cost-effective energy efficient liquid cooling systems for data centers, HPC clusters and high-performance PCs."The post Video: Asetek Advances Liquid Cooling at ISC 2018 appeared first on insideHPC.

Today HPC Cloud provider Verne Global announced that it has been approved by the Crown Commercial Service as a UK government supplier under the G-Cloud 10 (G10) framework. "From advances in AI and machine learning right through to breakthroughs in engineering, genetics and life sciences, HPC is critical to driving innovation and gathering intelligence,” said Spencer Lamb, Director of Research, at Verne Global. “The G-Cloud 10 certification of our hpcDIRECT platform provides the UK’s world-class science, technology, weather and medical research institutions with a technically excellent, highly scalable and environmentally sound alternative to running their applications in-house.”The post Verne Global Steps up to G-10 Framework for Scientific Computing in the UK appeared first on insideHPC.

Registration is now open for the next HPC User Forum. The meeting takes place September 4-6 in Dearborn, Michigan. Key topics include AI and other advanced analytics, automated driving systems a.k.a. self-driving vehicles, additive manufacturing and HPC in clouds (and outer space!). "Don't miss the featured presentation by leading auto industry market research firm J.D. Power and Associates and the Miller Canfield law firm on their recent report on legal issues surrounding self-driving vehicles in the U.S. and around the world – or the talks on an important new HPC use: supporting massive urban sensor networks."The post September HPC User Forum to focus on Exascale, AI, Smart Manufacturing, and Clouds appeared first on insideHPC.

Today Hyperion Research announced that Jean Sorensen has joined the company in the newly created position of full-time business manager. "Jean Sorensen’s expertise and organizational skills made her an integral part of Hyperion Research's initial success as an independent company," said Dr. Earl Joseph, the company's CEO. "Going forward, she will oversee our global business operations, working closely with me and with Steve Conway, our COO. Jean will handle our accounting and finance, human resources, and other company logistics. She will continue to be a key element in ensuring that the company runs smoothly."The post Jean Sorensen Joins Hyperion Research appeared first on insideHPC.

The Galicia Supercomputing Center (CESGA) and Appentra Solutions will host the third edition of the hackathon at the Galicia Supercomputing Center, in Santiago de Compostela, from 24th to 28th September 2018. "CESGAHack 3 will help scientists and application developers to answer more scientific question by speeding up their application runtime and also reducing how long they spend coding the improved runtime. Participants get access to the Finis Terrae II supercomputer at CESGA and a team of mentors that are experts in the optimization, parallelization and execution of HPC applications."The post Accelerate Your Applications: CesgaHack returns to Spain in September appeared first on insideHPC.

Intel recently released BigDL. It’s an open source, highly optimized, distributed, deep learning framework for Apache Spark*. It makes Hadoop/Spark into a unified platform for data storage, data processing and mining, feature engineering, traditional machine learning, and deep learning workloads, resulting in better economy of scale, higher resource utilization, ease of use/development, and better TCO.The post Deep Learning Open Source Framework Optimized on Apache Spark* appeared first on insideHPC.

In this video, Steve Conway from Hyperion Research provides a summary of the ISC High Performance Conference in Frankfurt, Germany. "The ISC High Performance conference attracted 3,505 attendees from over 60 countries, as well as 162 companies and research organizations to unveil their latest technologies and services at the event. With this feat, ISC High Performance has officially reached a new milestone in its 33-year conference history."The post Video Highlights from ISC 2018 appeared first on insideHPC.

Princeton’s new flagship TIGER supercomputer is now up and running at their High-Performance Computing Research Center (HPCRC). As a hybrid system, TIGER is built from a combination of Intel Skylake chips and NVIDIA Pascal P100 GPUs, adding up to a peak performance of 2.67 Petaflops peak performance. "Computation has become an indispensable tool in accomplishing that mission,” Dominick said. “With the newest addition to our High-Performance Computing suite, Princeton continues to equip its faculty with the most advanced computational tools available. The TIGER cluster, and the remarkable staff that support it, are symbolic of the University’s commitment to sustained excellence.”The post TIGER Supercomputer Spins Up at Princeton appeared first on insideHPC.

Robert Triendl from DDN gave this talk at ISC 2018. "With their new Whamcloud Business Unit, DDN has already brought key Lustre developers on board to accelerate their high performance computing solutions. The acquisition also enables DDN to expand Lustre’s leading position from HPC and Exascale into high growth markets such as analytics, AI and hybrid cloud."The post Video: Whamcloud is Back – Lustre Today and Future appeared first on insideHPC.

Ian Colle from AWS gave this talk at the Univa Breakfast Briefing at ISC 2018. "To demonstrate the unique ability to run very large enterprise HPC clusters and workloads, Univa leveraged AWS to deploy 1,015,022 cores in a single Univa Grid Engine cluster to showcase the advantages of running large-scale electronic design automation (EDA) workloads in the cloud. The cluster was built in approximately 2.5 hours using Navops Launch automation and comprised more than 55,000 AWS instances in 3 availability zones, 16 different instance types and leveraged AWS Spot Fleet technology to maximize the rate at which Amazon EC2 hosts were launched while enabling capacity and costs to be managed according to policy."The post What would you do with a Million cores? appeared first on insideHPC.

We are pleased to report that Mike Bernhardt has joined the membership of the HPC User Forum Steering Committee. Established in 1999, the HPC User Forum has a mission to promote the health of the global HPC industry and address issues of common concern to users. "As an industry veteran, Mike has the experience and connections to help move the HPC User Forum into the Exascale era," said Rich Brueckner, President of insideHPC. "Mike is one of the nicest people in the business and I think this is a real step forward for the Steering Committee."The post Mike Bernhardt Joins HPC User Forum Steering Committee appeared first on insideHPC.

Storage networks are constantly evolving. From traditional Fibre Channel to IP-based storage networks, each technology has its place in the data center. IP-based storage solutions have two main network topologies to choose from based on the technology and administration requirements. Dedicated storage network topology, shared leaf-spine network, software defined storage, and iSCSI SAN are all supported. Hybrid network architectures are common, but add to the complexity.The post Network Switch Configuration with Dell EMC Ready Nodes appeared first on insideHPC.

The Center for Institutional Research Computing at Washington State University seeks exceptional applicants for the position of High-Performance Computing Systems Administrator. This position will play a vital role in the administration of HPC clusters used by the research community at Washington State University.The post Job of the Week: HPC System Administrator at CIRC in Washington appeared first on insideHPC.

Researchers at Newcastle University are benefitting from a new HPC machine, called Rocket. "Workloads are driving an ever-growing set of data intensive challenges that can only be met with accelerated infrastructure,” said Werner Hofer, Dean of Research & Innovation at Newcastle University. ”Rocket provides the significant memory and fast processing we need for bulky, complex numerical computation. My post-doctoral researcher was able to process half a million CPU hours’ worth of calculations which was not at all possible with our previous processing power.”The post New Rocket Supercomputer Powers HPC at Newcastle University appeared first on insideHPC.

In this video from PASC18 in Basel, Dr. Lukasz Miroslaw from Microsoft describes how the company is helping customers move HPC & Big Compute workloads to the Cloud. "High performance computing, artificial intelligence, and other advanced workloads are increasingly important to companies across all industries. But rapid changes in technology and workloads make it challenging for HPC teams to provide the resources their users need. Microsoft Azure provides one cloud for every HPC workload so that users can get the resources they need when they need them and only pay for what’s used."The post Microsoft Powers the Move to the HPC Cloud at PASC18 appeared first on insideHPC.

"IIT Bombay selected Cray as a partner in extending support in quality education and research programs because of the compelling price/performance and capability that Cray systems deliver,” said John Howarth, vice president of storage at Cray. “The combination of the Cray XC supercomputer and the Cray ClusterStor storage solution enables IIT Bombay to pursue the advanced research that is critical to their strategic discoveries.”The post IIT Bombay deploys Cray XC50 Supercomputer appeared first on insideHPC.

Duncan Poole from NVIDIA gave this talk at the Univa Breakfast Briefing at ISC 2018. "The rise of AI workloads on GPU-enabled systems like RAIDEN in Japan introduces a corresponding and compelling demand for Univa Grid Engine. Aside from being the de facto standard for enterprise-class deployments of shared computational infrastructures for managed HPC and AI workloads, Univa Grid Engine delivers industry-leading integrations with NVIDIA GPUs and Docker containers."The post NVIDIA GPUs Power HPC & AI Workloads in Cloud with Univa appeared first on insideHPC.

In this video from ISC 2018, CoolIT Systems’ Patrick McGinn describes the company's latest energy efficient data center liquid cooling solutions. "As the leading liquid cooling integration partner for OEM server manufacturers, CoolIT showcased liquid-enabled servers from Intel, Dell EMC and HPE. Combined with the broadest range of Coolant Distribution Units, CoolIT and their OEM partners are delivering the most complete and robust liquid cooling solutions to the HPC market."The post Video: CoolIT Systems Enables Liquid Cooled OEM Solutions for HPC and AI Data Centers appeared first on insideHPC.

Today Atos announced the latest version of its Atos Quantum Learning Machine, the "first commercially available and ready-to-use quantum system," capable of simulating up to 41 quantum bits (Qubits). "It also incorporates world-firsts in terms of simulating ‘quantum noise’ in order to make the simulation even more realistic. These advances – combined with our work to develop a quantum accelerator within five years – place Atos and its customers in an ideal position to take advantage of future digital revolutions.”The post Atos Announces New Quantum Simulator with 41 Qubits appeared first on insideHPC.