High-Performance Computing News Analysis | insideHPC

Phil Rogers from NVIDIA gave this talk at SC17. "Like its namesake, In this talk, we describe the architecture of SATURNV, and how we use it every day at NVIDIA to run our deep learning workloads for both production and research use cases. We explore how the NVIDIA GPU Cloud software is used to manage and schedule work on SATURNV, and how it gives us the agility to rapidly respond to business-critical projects. We also present some of the results of our research in operating this unique GPU-accelerated data center."The post Inside SATURNV – Insights from NVIDIA’s Deep Learning Supercomputer appeared first on insideHPC.

Today an HPC Startup called Sylabs entered the market to provide solutions and services based on Singularity, an open source container technology designed for high performance computing. Founded by the inventor and project lead for Singularity, Sylabs will license and support Singularity Pro, an enterprise version of the software, and introduce it to businesses in the enterprise and HPC commercial markets.The post Sylabs Startup forms Commercial Entity behind Singularity for HPC appeared first on insideHPC.

In this Let's Talk Exascale podcast, Franck Cappello from Argonne National Laboratory describes the VeloC project. "The VeloC project endeavors to provide ECP applications an optimal fault-tolerance environment, while the aim of the EZ project is to provide data reduction. Interviewee: Franck Cappello, Argonne National Laboratory."The post Addressing Fault Tolerance and Data Compression at Exascale appeared first on insideHPC.

Researchers at LLNL are using supercomputers to simulate the onset of earthquakes in California. "This study shows that powerful supercomputing can be used to calculate earthquake shaking on a large, regional scale with more realism than we’ve ever been able to produce before,” said Artie Rodgers, LLNL seismologist and lead author of the paper."The post Hayward Fault Earthquake Simulations Increase Fidelity of Ground Motions appeared first on insideHPC.

"NSF’s participation with major cloud providers is an innovative approach to combining resources to better support data science research," said Jim Kurose, assistant director of NSF for Computer and Information Science and Engineering (CISE). “This type of collaboration enables fundamental research and spurs technology development and economic growth in areas of mutual interest to the participants, driving innovation for the long-term benefit of our nation.”The post Big 3 Cloud Providers join with NSF to Support Data Science appeared first on insideHPC.

In this WSJ Podcast, scientists from the IBM's T J Watson Research Center describe how quantum computing will enable a new age of scientific discovery. "Quantum computers are incredibly powerful machines that take a new approach to processing information. Built on the principles of quantum mechanics, they exploit complex and fascinating laws of nature that are always there, but usually remain hidden from view. By harnessing such natural behavior, quantum computing can run new types of algorithms to process information more holistically."The post Podcast: The Age of Quantum Computing is (Almost) Here appeared first on insideHPC.

Vectorization, the hardware optimization technique synonymous with early vector supercomputers like the Cray-1 (1975), has reappeared with even greater importance than before. Today, 40+ years later, the AVX-512 vector instructions in the most recent many-core Intel Xeon and Intel® Xeon PhiTM processors can increase application performance by 16x for single-precision codes.The post Vectorization Now More Important Than Ever appeared first on insideHPC.

Adam Roe from Intel gave this talk at LAD'17 in Paris. "Lustre has had a number of compelling new features added in recent releases; this talk will look at those features in detail and see how well they all work together from both a performance and functionality perspective. Comparing some of the numbers from last year we will see how far the Lustre* filesystem has come in such a short period of time (LAD’16 to LAD’17), comparing the same use cases observing the generational improvements in the technology."The post Video: Lustre Generational Performance Improvements & New Features appeared first on insideHPC.

Today the Numerical Algorithms Group (NAG) in the UK announced the appointment of John Elmer to its Board of Directors. "I am delighted that John Elmer is joining the NAG Board,” said Rob Meyer, CEO, NAG. “His track record of helping technology-driven companies achieve their strategic growth objectives brings a valuable and complementary skill set for the Board. His 30+ years of experience in the upstream oil & gas industry will help us expand our offerings in this key market segment. The NAG Board of Directors welcome John and look forward to his contributions to our success.”The post John Elmer joins NAG Board of Directors appeared first on insideHPC.

The Center for Institutional Research Computing at Washington State University is seeking a Computational Scientist in our Job of the Week. "This position will play a key role in assisting the research community in the development and optimization of applications on high-performance computing clusters across a broad spectrum of application domains."The post Job of the Week: Computational Scientist at Washington State University appeared first on insideHPC.

Today One Stop Systems introduced the new 2U Ion Accelerator Flash Storage Array. The new array offers flexible capacity while maintaining the high-bandwidth and low-latency pedigree of Ion Accelerator arrays deployed in hundreds of global installations. This OSS shared flash storage array boasts the latest Ion Accelerator 5.0 software, NVMe drives, networking options and dual Intel Xeon Scalable Processors to support the most demanding applications.The post One Stop Systems Rolls Out High Bandwidth NVMe Ion Flash Storage Array appeared first on insideHPC.

Jon Masters from Red Hat gave this Keynote at FOSDEM 2018. "Recently disclosed vulnerabilities against modern high performance computer microarchitectures known as 'Meltdown' and 'Spectre' are among an emerging wave of hardware-focused attacks. This talk will describe several of these attacks, how they can be mitigated, and generally what we can do as an industry to bring performance without trading security."The post Exploiting Modern Microarchitectures: Meltdown, Spectre, and other Attacks appeared first on insideHPC.

These days, taking big data further and integrating machine and deep learning means having a competitive edge in the retail industry. Analytics — and their analysis — have always been a cornerstone of retail success. And now, deep learning techniques are going to push the data boom to the next level. A new insideHPC special report, courtesy of Dell EMC and NVIDIA, explores how the retail industry is being transformed by machine and deep learning.The post How Deep Learning is Causing a ‘Seismic Shift’ in the Retail Industry appeared first on insideHPC.

Today Dell EMC announced three new servers powered by AMD EPYC processors. "The Advanced High-Performance Computing Center at the University of Arkansas Fayetteville runs Molecular Dynamics simulation the open-source code: LAMMPS (Large-Scale Atomic/Molecular Massively Parallel Simulator). We found the Dell EMC PowerEdge 7415 single socket server with the AMD EPYC processor runs faster than existing dual socket servers, allowing us to support our continued need for more bandwidth and additional cores, but using less power in a smaller space.”The post Dell EMC Steps up with AMD EPYC Servers for HPC, SDN, and the Edge appeared first on insideHPC.

Today and AI chip startup called Lightmatter announced that it has received $11 million in Series A funding to accelerate development of the industry’s first chip to leverage the unique properties of light to enable fast and efficient inference and training engines. "It is rare to see true innovation in the chip industry today, but Lightmatter has done it. The importance of this groundbreaking technology cannot be overstated,” said Stan Reiss. “The Lightmatter team has applied a major scientific discovery to dramatically increase the power of AI and its reach into our lives.”The post Lightmatter Startup funded to Accelerate AI with Optical Chip appeared first on insideHPC.

Researchers are using XSEDE supercomputers to develop better semiconductors for solar engery. "Dr. Levine models the behavior caused by defects in materials, such as doping bulk silicon to transform it into semiconductors in transistors, LEDs, and solar cells. Levine and his team have used over 975,000 compute hours on the Maverick supercomputer, a dedicated visualization and data analysis resource architected with 132 NVIDIA Tesla K40 "Atlas" GPUs for remote visualization and GPU computing to the national community."The post Podcast: Supercomputing Better Semiconductors for Solar Energy appeared first on insideHPC.

Dr. Tjerk P. Straatsma from ORNL gave this talk at SC17. "The Center for Accelerated Application Readiness (CAAR) projects are using an Early Access Power8+/Pascal system named SummitDev to prepare for the Power9/Volta system Summit. This presentation highlights achievements on this system, and the experience of the teams that will be a valuable resource for other development teams."The post Application Readiness Projects for the Summit Supercomputer Architecture appeared first on insideHPC.

Three types of clouds have been developed: public clouds, private clouds and hybrid clouds. We continue our insideHPC series of features exploring new resource management solutions for workload convergence, such as Bright Cluster Manager by Bright Computing. This article explores the three types of cloud computing, as well as how cloud computing can work to reduce CAPEX.The post The 3 Types of Cloud Computing for HPC Systems Management appeared first on insideHPC.

Today the ISC 2018 conference announced the return of the ISC STEM Student Day, with an attractive program for students and sponsoring organizations. Students attending the program will receive an exclusive tutorial on high performance computing, machine learning and data analytics, and sponsoring organizations will receive an increased visibility during the full-day program. "Unlike regular STEM events, the aim of our program is to connect the next generation of regional and international STEM practitioners with the HPC industry and its key players. We hope this will encourage them to pursue careers in this space, and we will see them as part of the HPC user community in the future.”The post ISC STEM Student Day & Gala is Back with a Stronger Program appeared first on insideHPC.

Today a new Arm server company called Ampere launched with a mission to address memory performance, cost, space and power constraints for the datacenter. Of note is the company's leadership team, which is comprised of semiconductor and cloud computing experts, including several well-known architects from the industry. Renee James, former president of Intel, is the CEO.The post Ampere Computing Startup to Bring Arm to the Datacenter appeared first on insideHPC.

Prof. Simon McIntosh-Smith from the University of Bristol gave this talk at the GoingARM Workshop. "Isambard is a unique system that will enable direct ‘apples-to-apples’ comparisons across architectures, thus enabling UK scientists to better understand which architecture best suits their application.”The post First Public Disclosure of Isambard Supercomputer Performance Results appeared first on insideHPC.

In this podcast, the Radio Free HPC team looks at HPE's new CEO, Antonio Neri, a longtime HPE executive who previously served as President of the company. As the number 1 server vendor in the HPC space, this change will be one to watch as we transition to the exascale era in the next five years or so. "This transistion comes at an interesting time for HPE, as one of their main competitors, Dell Technologies, is reportedly looking at an IPO or reverse acquisition by VMware."The post Radio Free HPC looks at New Leadership at HPE appeared first on insideHPC.

It has been said that artificial intelligence will create the next industrial revolution, the fourth industrial revolution that modern-day society has experienced since the dawn of mechanical production and steam power energy documented in 1784. In this guest article, Mellanox Technologies' Scot Schultz explores how artificial intelligence is shaping up to launch the next big wave of innovation.The post Artificial Intelligence: The Next Industrial Revolution appeared first on insideHPC.

Carlos Thomaz from DDN gave this talk at LAD'17 in Paris. "With the first set of Arm-based HPC servers debuting at SC17 in Denver, the platform is being evaluated for Lustre performance by a number of other organizations including Cray, DDN, and ORNL."The post Video: Lustre File System on ARM appeared first on insideHPC.

Virginia Tech is seeking a Computational Scientist in our Job of the Week. "In this faculty role, you will develop and teach science and engineering educational programs; workshops, lecture series, and for credit courses, for Virginia Tech faculty and students. Pursue a research agenda and collaborate with other Virginia Tech science, engineering, and outside discipline faculty to create opportunities and projects for external grants."The post Job of the Week: Computational Scientist at Virginia Tech appeared first on insideHPC.

The HPC User Forum has posted their speaker agenda for their upcoming meeting in Tucson. Hosted by Hyperion Research, the event takes place April 16-18 at Loews Ventana Canyon. "The April meeting will explore the status and prospects for quantum computing and HPC use of HPC for environmental research, especially natural disasters such as earthquakes and the recent California wildfires. As always, the meeting will also look at new developments in HPDA-AI, cloud computing and other areas of continuing interest to the HPC community. A special session will look at the growing field of processors and accelerators supporting HPC systems."The post Agenda Posted for April HPC User Forum in Tucson appeared first on insideHPC.

In this Let's Talk Exascale podcast, Suren Byna of LBNL and Quincey Koziol of the NERSC describe ExaHDF5, an I/O platform for exascale data. "One milestone that we have achieved so far is a feature called Data Elevator. The Data Elevator, as it says, is an elevator between different stages of memory hierarchy. It moves the data more transparently so that applications just have to use HDF5 API and internally we take over how to move the data between the layers, so that is one of the features."The post Let’s Talk Exascale Podcast looks at Parallel I/O with ExaHDF5 appeared first on insideHPC.

EOFS chairman Frank Baetke writes that he has left HPE. As the long-time liason to the HP-CAST user community, Mr. Baetke played a key role in bringing together HPC thought leaders at worldwide events for many years. The good news is that Frank will continue to be active in High Performance Computing.The post Frank Baetke Leaves HPE, Stays on as EOFS Chairman appeared first on insideHPC.

JISC in the UK is upgrading its Janet Network to world-leading 400Gbit/s connectivity, making it one of the most digitally-advanced national research and education networks globally in terms of scale, automation and network intelligence. "Our vision is for the UK to be at the forefront of scientific research," said Jeremy Sharp, network infrastructure director for Jisc. "To make that happen, we must have a highly robust network powered with industry-leading technology that can scale to support bandwidth-intensive applications like genome editing and the Square Kilometre Array.The post Janet Network upgrades to 400Gbit/s for Global Research appeared first on insideHPC.

Today Optalysys announced the formation of its first Scientific Advisory Board (SAB) comprising experts in AI/machine learning, bioinformatics/genomics and optical pattern recognition. The inaugural SAB members include Professor Douglas Kell of The University of Manchester, Professor Timothy Wilkinson of University of Cambridge and ex-senior NASA scientist, Dr. Richard Juday. "Collectively, these experts have deep knowledge in areas most critical to our long-term success,” said Dr. Nick New, founder and director, Optalysys. “We’re excited to work closely with them through the process of bringing to market our unique optical approach to super-fast, low-power computing to enable more tech innovators and scientists to create a better world.”The post Optalysys Appoints Scientific Advisory Board for Optical Computing appeared first on insideHPC.

Today Bright Computing released version 8.1 of the Bright product portfolio with new capabilities for cluster workload accounting, cloud bursting, OpenStack private clouds, deep learning, AMD accelerators, Kubernetes, Ceph, and a new lightweight daemon for monitoring VMs and non-Bright clustered nodes. "The response to our last major release, 8.0, has been tremendous," said Martijn de Vries, Chief Technology Officer of Bright Computing. "Version 8.1 adds many new features that our customers have asked for, such as better insight into cluster utilization and performance, cloud bursting, and more flexibility with machine learning package deployment.”The post Bright Computing Release 8.1 adds new features for Deep Learning, Kubernetes, and Ceph appeared first on insideHPC.

Stephen Jones from NVIDIA gave this talk at SC17. "The NVIDIA Volta architecture powers the world’s most advanced data center GPU for AI, HPC, and Graphics. Features like Independent Thread Scheduling and game-changing Tensor Cores enable Volta to simultaneously deliver the fastest and most accessible performance of any comparable processor. Join us for a tour of the features that will make Volta the platform for your next innovation in AI and HPC supercomputing."The post Video: Inside Volta GPUs appeared first on insideHPC.

Data analytics deals with making observations with various data sets, and trying to make sense of the data. When dealing with very large data sets, automated tools must be used to find patterns and relationships. One of the most important tasks from large data sets is to find an outlier, which is defined as a sample or event that is very inconsistent with the rest of the data set.The post Outliers – Why So Important for Data Analytics? appeared first on insideHPC.

Today ThinkParQ announced the appointment of Frank Herold as CEO. While the company enjoyed a record-setting year in 2017, the move sets the stage for further growth of the BeeGFS file system for high performance computing. "Frank has a long history in the field of large scale enterprise file systems and is well experienced in expansion into new markets, which is exactly our strategic focus for the years ahead. With his strong technical and management background, I trust that he is the ideal person to manage the company based on a deep understanding of customer and market demands.” says Sven Breuner, former CEO of ThinkParQ.The post ThinkParQ Welcomes New CEO as BeeGFS Continues Record Growth appeared first on insideHPC.

The Department of Energy is seeking industry proposals for public/private projects aimed at applying high performance computing to industry challenges for the advancement of energy innovation. “We are seeing some significant successes with orders of magnitude reduction in simulation times and higher fidelity simulations that more closely match the reality of the manufacturing process. With this solicitation we plan to continue to expand the reach of our program to new companies to help solve new and different problems.”The post HPC4Manufacturing Program Seeks Industry Proposals appeared first on insideHPC.

Today the PASC18 conference announced that Nils P. Wedi from ECMWF will be one of its keynote speakers. "This talk will illustrate the need for and practicality of producing ensembles of km-scale simulations, summarize progress on accelerating state-of-the-art global weather and climate predictions, and discuss outstanding issues and future directions on producing and analysing big weather data while balancing time-critical customer needs with energy- and time-to-solution."The post PASC18 Keynote to Focus on Kilometre-Scale Earth System Simulations appeared first on insideHPC.

In this video from Disruptive Technologies exhibit at SC17, Theodore Omtzigt describes the mission of a new Startup called Posit Research. "Posit Research is a fabless semi designing and marketing posit-based computational solutions for the artificial intelligence and high-performance computing markets. We are creating a new type of artificial intelligence supercomputer that adapts to the application. It uses a new number system called posit."The post A New Way of Supercomputing with Posit Research appeared first on insideHPC.

Today Adaptive Computing announced Moab/NODUS Cloud Bursting, making HPC cloud strategies more accessible than ever before. "Considering that public cloud bursting is usually extremely challenging, the Moab/NODUS Cloud Bursting Solution is brilliant in its ability to integrate seamlessly with existing management infrastructure,” said Art Allen, President, Adaptive Computing Enterprises, Inc.The post Adaptive Computing Launches Moab/NODUS for HPC Cloud Bursting appeared first on insideHPC.

Today the iRODS Consortium announced that the University of Groningen (UG) Center for Information Technology (CIT) is its newest member. The iRODS Consortium is a membership-based organization that leads efforts to develop, support, and sustain the integrated Rule-Oriented Data System (iRODS). "For years there was a need for technical solutions for various problems in the field of research data management that researchers are running into,” said Jonas Bulthuis, IT consultant at the CIT. “iRODS offers building blocks with which we can offer solutions for managing research data.”The post University of Groningen joins iRODS Consortium appeared first on insideHPC.

In this Let's Talk Exascale podcast, David Richard from LLNL discussed the Proxy Apps project, which is curating a collection of proxy apps that will represent the real applications of importance to the ECP. "In this Let's Talk Exascale podcast, David Richard from LLNL discussed the Proxy Apps project, which is curating a collection of proxy apps that will represent the real applications of importance to the ECP."The post Podcast: Proxy Apps set the stage for Exascale Computing Project appeared first on insideHPC.

This video features highlights from the first day at the HiPEAC conference, which took place last week in Manchester. HiPEAC is the premier European forum for experts in computer architecture, programming models, compilers and operating systems for embedded and general-purpose systems. "HiPEAC Coordinator Koen De Bosschere tells us what's been going on, including a great keynote talk from Maria Girone at CERN. Meanwhile, Arm's John Goodacre tells us why Manchester is a great location for the conference and why it's important for companies like Arm to be involved in HiPEAC."The post Video: HiPEAC Conference Looks at Innovations in Computer Architecture appeared first on insideHPC.

In this special guest feature, Parks Fields and Paul Grun from the OpenFabrics Alliance write that the upcoming OFA Workshop in Boulder is an excellent opportunity to collaborate on the next generation of network fabrics. "Come join the community in Boulder this year to lend your voice to shaping the direction of fabric technology in big ways or small, or perhaps just to listen and learn about the latest trends coming down the pike, or to pick up tips and tricks to make you more effective in your daily job."The post OpenFabrics Alliance Workshop 2018 – An Emphasis on Fabric Community Collaboration appeared first on insideHPC.

Today Dell Technologies released a research report that examines the future of human machine partnerships and reveals that business leaders are divided regarding the future. "Half of the 3,800 global business leaders surveyed forecast that automated systems will free up their time, while the other 50% believe otherwise."The post Research Report Reveals Divided Vision of Future Human-Machine Partnership appeared first on insideHPC.

The Stanford HPC Conference has posted it Preliminary Agenda. The two-day event takes place Feb. 20-21 at Stanford University in California. "Join the Stanford High Performance Computing Center, HPC Advisory Council, its members and experts from all over the world for two days of invited and contributed talks and immersive tutorials on topics of great societal impact and responsibility! February's open forum brings industry luminaries and leading subject matter experts together to examine emerging and major domains and share in-depth insights on AI, Data Sciences, HPC, Machine Learning and more."The post Stanford HPC Conference Posts Preliminary Agenda appeared first on insideHPC.

Today HPC Cloud provider Verne Global announced that Analytic Engineering of Germany is moving their GPU infrastructure to Iceland. "At Verne Global’s campus, we can grow our business faster and apply more compute resources to our programs than at any other data center that we evaluated,” said Tobias Seifert, Co-CEO at Analytic Engineering. “This is a critical competitive advantage to us, as we look to deliver highly complex software solutions that enable our customers to iterate faster through applications driven by AI and Machine Learning.”The post Analytic Engineering Moves AI GPU Infrastructure to Verne Global in Iceland appeared first on insideHPC.

Adrian Reber from Red Hat gave this talk at DefConf 2018. "Software provisioning is a common task repeated at many high performance computing sites to provide the local users with scientific applications and libraries. As the effort to compile HPC software is known to be duplicated by many HPC sites, the idea to collaborate in a community led to the creation of the OpenHPC project. In this talk I want to provide an introduction to OpenHPC, its community efforts and how it can help HPC sites."The post Video: OpenHPC Introduction appeared first on insideHPC.

We continue our insideHPC series of features exploring new resource management solutions for workload convergence, such as Bright Cluster Manager by Bright Computing. This article focuses on how clustering servers and utilizing cloud computing can help your enterprise achieve more flexibility and speed — as well as improve HPC systems management.The post Clusters & Cloud Computing: Speeding up HPC Systems Management appeared first on insideHPC.

Engineers from ESnet and the Globus team have designed a new approach that makes data sharing faster, more reliable, and more secure. As described in a new report, the "Science DMZ" provides a new architecture to meet increasing demands for accessing shared data.The post Engineering a Better Portal for Scientific Discovery appeared first on insideHPC.

PSSC Labs is offering HPC clusters solutions for Weather Modeling and Wildfire Analysis in collaboration with Atmospheric Data Solutions (ADS). "The solutions ADS are developing use a comprehensive blend of predictors that are important to large wildfire potential including dead fuel and live fuel moisture, near-surface atmospheric moisture and temperature, wind speed and gusts."The post PSSC Labs offers HPC Solutions for Weather Modeling and Wildfire Analysis appeared first on insideHPC.

Eni in Italy has launched its new HPC4 supercomputer. With a peak performance of 18.6 Petaflops, the HPC4 cluster from Hewlett Packard Enterprise quadruples the Company’s computing power, making it the world’s most powerful industrial system. "With HPC4 we are tracing the path for the use of exascale supercomputers in the energy sector that could revolutionize the way in which oil&gas activities are managed."The post Eni in Italy Launches 18.6 Petaflop HPC4 Supercomputer appeared first on insideHPC.