High-Performance Computing News Analysis | insideHPC

The European Processor Initiative (EPI) has delivered its first architectural design to the European Commission and is welcoming new partners. "Energy efficient high-performance families of EPI processors will include most advanced general-purpose and accelerator cores that will deliver unprecedented processing capabilities, enabling EU researchers from academia and industry to most efficiently address global challenges. The business sustainability of the initiative is supported by carefully balanced target markets, with primary focus on exascale HPC/AI and automotive markets.”The post EPI delivers first design for high-performance processor appeared first on insideHPC.

Jeff Candy and Igor Sfiligoi from General Atomics gave this talk at the GPU Technology Conference. "Gyrokinetic simulations are one of the most useful tools for understanding fusion science. We'll explain how we designed and implemented CGYRO to make good use of the tens of thousands of GPUs on such systems, which provide simulations that bring us closer to fusion as an abundant clean energy source. We'll also share benchmarking results of both CPU- and GPU-Based systems."The post Advancing Fusion Science with CGYRO using GPU-based Leadership Systems appeared first on insideHPC.

In this special guest feature, Martin Meuer and Thomas Meuer set the stage for the ISC High Performance conference, which takes place June 16-20 in Frankfurt. "The opening keynote also reflects our devotion to raising the level scientific research that is presented at the conference. Our commitment to this goal and the academic program, in general, has helped make ISC High Performance a showcase for some of the best HPC-backed research in the world."The post Welcome to ISC High Performance 2019 appeared first on insideHPC.

The BigTwin Server featuring WekaFS offering is a milestone in our relationship with Supermicro," said Barbara Murphy, Vice President of Marketing at WekaIO. "The solution is already in use by many customers with deep learning applications and exceeding expectations for performance and value. By offering this preconfigured solution with Supermicro, we’ll be able to simplify the customers’ acquisition experience.”The post Supermicro teams with WekaIO for Deep Learning Performance Density appeared first on insideHPC.

GENCI in France has inaugurated their new Joliot-Curie supercomputer. Based on the Atos BullSequana architecture, the system is rated at 9.4 petaflops of peak performance. The system boasts 4.5X increase in computing capacity with half the power consumption of its predecessor. "Joliot-Curie has already been tested as part of the Grands Challenges (Great challenges), organized by GENCI at the TGCC, by running major simulations and other applications."The post Joliot-Curie Supercomputer from Atos Powers Research at GENCI appeared first on insideHPC.

In this podcast, the Radio Free HPC team reviews the results of the ASC19 Student Cluster Competition and HPC workshop in China. "For the first time, a non-mainland-Chinese team wins the top spot. Taiwan takes the gold in part by their stellar performance in HPCG benchmark where they achieved 2 TFlops, some 25% better than the 2nd best team. The system was a 5-node cluster with Infiniband FDR interconnect."The post Radio Free HPC Ponders Amdahl’s Law, GPUs, and the ASC19 Student Cluster Competition appeared first on insideHPC.

AMD engineers executed a physical verification pass of the Radeon Instinct Vega20 – its largest 7nm chip design – in ~10 hours on Microsoft Azure. The job used the TSMC-certified Calibre nmDRC software platform from Mentor, running on the Microsoft Azure cloud platform using HB-series virtual machines, powered by AMD EPYC processors.The post AMD Verifies Vega20 GPU in Record Time on Azure appeared first on insideHPC.

In this Intel Chip Chat podcast, Dr. Felipe Franciosi from Nutanix and Nate Marushak from Intel describe how the open source reference library called SPDK (Storage Performance Development Kit) brings higher performance to the data center. "A decade ago, when slow hard disk drives were the heart of a data center, efficiency was improved by designing software to avoid accessing physical media. Innovations in persistent memory and in networking technology have already brought vast improvements. For systems that are latency-sensitive, applying SPDK can address software bottlenecks and open the way to even higher performance."The post Podcast: Achieving Low Latency with the SPDK Storage Performance Development Kit appeared first on insideHPC.

Andrei Plamada from ETH Zurich gave this talk at the hpc-ch forum on Cloud and Containers. "Singularity is a container solution that promises to both integrate MPI applications seamlessly and run containers without privilege escalation. These benefits make Singularity a potentially good candidate for the scientific high-performance computing community. However, the performance overhead introduced by Singularity is unclear. In this work we will analyze the overhead and the user experience on both traditional HPC and cloud infrastructures."The post Benchmarking MPI Applications in Singularity Containers on Traditional HPC and Cloud Infrastructures appeared first on insideHPC.

In this special guest feature from Scientific Computing World, Robert Roe looks at storage technologies being developed to suit both AI and HPC workloads. "While AI may steal the headlines, HPC is still generating advances in storage technology. Cloud environments have made significant progress over the last five to ten years, going from what was seen as fringe or niche technology to a much more ubiquitous platform, particularly with the advances made by cloud giants such as Google and Amazon."The post Storage Advances for HPC and AI appeared first on insideHPC.

The Jülich Supercomputing Centre in Germany is seeking a Computer Scientist in our Job of the Week. "You will directly support and independently advance the code development of existing and new parallel scientific software. The focus is placed on the adaption of existing, complex software to next generation heterogeneous supercomputer architectures."The post Job of the Week: Computer Scientist at the Jülich Supercomputing Centre appeared first on insideHPC.

NCSA is now accepting team applications for the Blue Waters Petascale Computing Hackathon. The event will take place September 9-13, 2019 at NCSA. "The Hackathon will pair research teams with expert mentors with the goal to enable scientific codes to take full advantage of HPC systems. The end goal is to have applications running efficiently at scale, or with a clear roadmap for enhancing code performance."The post Apply Now for the Blue Waters Petascale Computing Hackathon appeared first on insideHPC.

Are we witnessing the convergence of HPC, big data analytics, and AI? Once, these were separate domains, each with its own system architecture and software stack, but the data deluge is driving their convergence. Traditional big science HPC is looking more like big data analytics and AI, while analytics and AI are taking on the flavor of HPC.The post Converging Workflows Pushing Converged Software onto HPC Platforms appeared first on insideHPC.

In this Big Compute Podcast episode Gabriel Broner interviews Irene Qualters about her career and the evolution of HPC. "Some of the most profound advances that I have seen come from groups of people that have very different perspectives, very different ideas. We have to struggle to collectively bring our different disciplines on our world’s hardest problems, on the world’s most challenging problems."The post Podcast: Irene Qualters from LANL Shares Life Lessons on HPC and Diversity appeared first on insideHPC.

DK Panda from Ohio State University gave this talk at the Swiss HPC Conference. "We will provide an overview of interesting trends in DNN design and how cutting-edge hardware architectures are playing a key role in moving the field forward. We will also present an overview of different DNN architectures and DL frameworks. Most DL frameworks started with a single-node/single-GPU design."The post Scalable and Distributed DNN Training on Modern HPC Systems appeared first on insideHPC.

In this special guest feature from the SC19 Blog, Dan Jacobson and Wayne Joubert from ORNL describes how the Summit supercomputer is helping untangle how genetic variants, gleaned from vast datasets, can impact whether an individual is susceptible (or not) to disease, including chronic pain and opioid addiction.The post Supercomputing Takes on the Opioid Crisis appeared first on insideHPC.

NEC will host their Aurora Forum at ISC 2019. Designed for developers and users SX-Aurora TSUBA vector computing technology, the The half-day meeting takes place June 17 in Frankfurt, Germany. "The NEC SX-Aurora TSUBASA is the newest in the line of NEC SX Vector Processors with the worlds highest memory bandwidth. Implemented in a PCI-e form factor, the NEC processor can be configured in many flexible configurations together with a standard x86 cluster."The post NEC to Host Aurora Forum on Vector Computing at ISC 2019 appeared first on insideHPC.

Today Tachyum announced it has successfully deployed the Linux OS on its Prodigy Universal Processor architecture, a foundation for 64-core, ultra-low power, high-performance processor. “Running an OS directly on the chip, without attaching to another host processor as an accelerator or other workaround, signals to the industry that Tachyum compiler and software is stable, mature, and approaching production-quality.”The post Tachyum Boots Linux on Universal Processor Chip appeared first on insideHPC.

Today Microway announced that the company is now shipping 2nd Generation Intel Xeon Scalable processors in volume, including next-generation NumberSmasher clusters, servers, and WhisperStations. "This new family of processors boosts performance for Microway custom deployments with increased CPU core counts, higher memory capacity and bandwidth, improved clock speeds, and innovative new features for HPC, AI, and Deep Learning. A Microway analysis finds that, without exception, 2nd generation Intel Xeon Scalable CPUs are expected to outperform their predecessors."The post Microway Shipping Intel Cascade Lake Systems in Volume appeared first on insideHPC.

Kevin Roe from the Maui High Performance Computing Center gave this talk at the GPU Technology Conference. "We will characterize the performance of multi-GPU systems in an effort to determine their viability for running physics-based applications using Fast Fourier Transforms (FFTs). Additionally, we'll discuss how multi-GPU FFTs allow available memory to exceed the limits of a single GPU and how they can reduce computational time for larger problem sizes."The post Video: Multi-GPU FFT Performance on Different Hardware Configurations appeared first on insideHPC.

The ALCF Data Science Program at Argonne has issued its Call for Proposals. The program aims to accelerate discovery across a broad range of scientific domains which require data-intensive and machine learning algorithms to address challenging research problems. "Ongoing and past ADSP projects span a diverse range of science domains, e.g. Materials, Imaging, Neuroscience, Engineering, Combustion/CFD, Cosmology; and involve large science collaborations."The post Call for Proposals: Get on Big Iron with the ALCF Data Science Program appeared first on insideHPC.

Today Univa announced its latest version of Navops Launch, version 1.1, which offers enterprise users the ability to migrate their HPC workloads and processes to the cloud with higher efficiency and agility. "The Univa team designed its newest version of Navops Launch to help make the administration of day-to-day cloud usage simpler than an unrestricted cloud queue as a way to help control costs, while still optimizing on efficiency and agility. We strive to make our customers cloud experience as close to a NoOps model as possible."The post Univa Navops Launch Speeds HPC Workload Migration to the Cloud appeared first on insideHPC.

In this special guest feature, Dan Olds from OrionX continues his Epic HPC Road Trip series with a stop at NREL in Golden, Colorado. "When it comes to energy efficient computing, NREL has to be one of the most advanced facilities in the world. It’s the first data center I’ve seen where their current PUE is shown on a LCD panel outside the door. When I was visiting, the PUE of the Day was 1.027 – which is incredibly low."The post Epic HPC Road Trip Continues to NREL appeared first on insideHPC.

Sergio Maffioletti from the University of Zurich gave this talk at the hpc-ch forum on Cloud and Containers. "In this talk, we'll provide an overview of the challenges faced by both research infrastructure providers and Science IT units, along with best practices to improve the reproducibility of data analysis using cloud and container technologies."The post Towards Reproducible Data Analysis Using Cloud and Container Technologies appeared first on insideHPC.

Today the Texas A&M Engineering Experiment Station announced the creation of the new Hewlett Packard Enterprise Center for Computer Architecture Research. Made possible with a donation from HPE, the center’s mission is to lead the way into this new world of data-driven computing architectures through academic-industry collaboration. “There is no other cleanroom in the state of Texas that has all five of the high-end instruments HPE is donating, and we plan to become a regional hub for next-generation nano- and micro-engineering."The post Texas A&M to launch new HPE Center for Computer Architecture Research appeared first on insideHPC.

In the face of unrelenting data growth, rising numbers of high-performance computing (HPC) workloads are memory bound. Caught between the high cost and limited capacity of DRAM and the lower performance of 3D NAND SSDs, HPC users increasingly find that despite workarounds, they’re unable to keep pace with skyrocketing data volumes and increasingly complex challenges. Intel Optane technology is designed to address these challenges.The post Unleashing the Next Wave of HPC Breakthroughs with Intel Optane DC Persistent Memory and Intel Optane DC Solid State Drives appeared first on insideHPC.

MEGWARE has deployed a new HPC cluster at The Leibniz Centre for Agricultural Landscape Research (ZALF) in Germany. The cluster is powered by 125 compute nodes equipped with latest Intel Xeon Scalable 6230 processor technology. "Thanks to the professional advice and support provided by MEGWARE, ZALF has now access to a powerful HPC cluster system, which makes new modeling methods and simulation techniques for complex agricultural landscape research available."The post MEGWARE Powers HPC Cluster for Agriculture Landscape Research at ZALF appeared first on insideHPC.

In this special guest feature, Dr. Rosemary Francis reflects on how a recent film about Ruth Bader Ginsberg has a gender equality lesson for us all in high performance computing. "There’s a real argument that creating a more diverse HPC workforce will help us to create machines that make more diverse decisions. By bringing as many minds together as possible – men and women, of different ages, races and ethnicities – we can make sure all problems are considered on the basis of every possible human angle."The post On the Basis of Sex: HPC in the fight for gender equality appeared first on insideHPC.

Today Excelero and ThinkParQ announced benchmark results from their combined technologies for HPC, AI, ML, and analytics. "With Excelero’s NVMesh, our customers have access to an ultra-low latency, high performance approach to scale-out storage,” said Frank Herold, CEO of ThinkParQ. “We’ve been impressed with NVMesh’s ability to deliver the high IOPS and ultra-low latency of NVMe drives over the network with highly available volumes – as well as options for distributed erasure coding and BeeGFS' unmatched ability to efficiently handle all kinds of access patterns and file sizes.”The post Excelero Integrates NVMesh and BeeGFS for Accelerated I/O appeared first on insideHPC.

Christian Trott from Sandia gave this talk at the GPU Technology Conference. "The Kokkos C++ Performance Portability EcoSystem is a production-level solution for writing modern C++ applications in a hardware-agnostic way. We'll provide success stories for Kokkos adoption in large production applications on the leading supercomputing platforms in the U.S. We'll focus particularly on early results from two of the world's most powerful supercomputers, Summit and Sierra, both powered by NVIDIA Tesla V100 GPUs."The post Video: The Kokkos C++ Performance Portability EcoSystem for Exascale appeared first on insideHPC.

Today TYAN announced that it is teaming with NVIDIA to integrate the NVIDIA EGX platform with its Thunder SX TN76-B7102 edge server, completing TYAN’s GPU server product line. "NVIDIA EGX provides the missing link for low-latency AI computing at the edge with an advanced, light-compute platform, reducing the amount of data that needs to be pushed to the cloud."The post NVIDIA EGX Accelerates AI on TYAN Edge Server appeared first on insideHPC.

Today NVIDIA announced NVIDIA EGX, an accelerated computing platform that enables companies to perform low-latency AI at the edge. “The combination of high-performance, low-latency and accelerated networking provides a new infrastructure tier of computing that is critical to efficiently access and supply the data needed to fuel the next generation of advanced AI solutions on edge platforms such as NVIDIA EGX.”The post New NVIDIA EGX Platform Brings Real-Time AI to the Edge appeared first on insideHPC.

Dell EMC will once again host the HPC Community Meeting at ISC 2019. "The Dell EMC HPC Community is a worldwide technical forum that fosters the exchange of ideas among researchers, computer scientists, technologists, and engineers and promotes the advancement of innovative, powerful HPC solutions. In the Community, members share expertise, insights, observations, suggestions, and experiences to improve current HPC solutions and to influence future technology capabilities & impact."The post Dell HPC Community Meeting returns to Frankfurt for ISC 2019 appeared first on insideHPC.

Henry Newman from Seagate Government Solutions gave this talk at the HPC User Forum in Santa Fe. "Cyber attacks and security breaches have become commonplace with explosion of data. More often than not, these breaches could have prevented or greatly reduced if these institutions would have followed prescribed security standards. As we move to the edge and go to 5G networks, there is going to be more distributed data and therefore protection is going to have to go out to the edge as well."The post Cybersecurity and Risk Management for HPC appeared first on insideHPC.

Kevin Sayers from the University of Basel gave this talk at the hpc-ch forum. "The SIB Swiss Institute of Bioinformatics BioMedIT project is developing the computing infrastructure which will enable biomedical analyses on sensitive human data across multiple sites as part of the Swiss Personalized Health Network. This presentation will focus on our experience assessing Kubernetes to support these biomedical workloads, and the benefits it provides to researchers in the community."The post Video: Kubernetes for Biomedical Analysis appeared first on insideHPC.

Milwaukee School of Engineering (MSOE) invites applications for a full-time HPC Systems Administrator to join our Electrical Engineering and Computer Science department. "The MSOE community is guided by six values – collaboration, excellence, inclusion, innovation, integrity and stewardship – that represent the core of our campus culture."The post Job of the Week: HPC System Administrator at the Milwaukee School of Engineering appeared first on insideHPC.

Researchers are using supercomputers to introduce and assess the impact of different configurations of defects on the performance of a superconductor. "When people think of targeted evolution, they might think of people who breed dogs or horses,” said Argonne materials scientist Andreas Glatz, the corresponding author of the study. ​“Ours is an example of materials by design, where the computer learns from prior generations the best possible arrangement of defects.”The post HPC Powers Evolution of Defects for Superconductors appeared first on insideHPC.

The European ETP4HPC initiative has published a blueprint for the new Strategic Research Agenda for High Performance Computing. "This blueprint sketches the big picture of the major trends in the deployment of HPC and HPDA methods and systems, driven by the economic and societal needs of Europe, taking into account the changes expected in the underlying technologies and the overall architecture of the expanding underlying HPC infrastructure."The post New Blueprint lays out Strategic Research Agenda for HPC in Europe appeared first on insideHPC.

Today ISC 2019 announced the recipients of the ISC Travel Grant this year will be from Columbia and Botswana. The winners will each be awarded a grant of 2500 euros to cover travel expenses and boarding. ISC High Performance will also provide the grant recipients free registration for the entire conference in Frankfurt, Germany.The post Colombian and Botswana Researchers Awarded ISC Travel Grant appeared first on insideHPC.

Pol Forn from the Barcelona Supercomputing Centre gave this talk at the BSC Annual Meeting. "QUANTIC is a joint venture between the Barcelona Supercomputing Center and the University of Barcelona. The research directions are focused on performing quantum computation in a laboratory of superconducting quantum circuits and studying new applications for quantum processors."The post Video: The First Catalan Quantum Computer appeared first on insideHPC.

Researchers are using powerful supercomputers at TACC to process data from Gravity Recovery and Climate Experiment (GRACE). "Intended to last just five years in orbit for a limited, experimental mission to measure small changes in the Earth's gravitational fields, GRACE operated for more than 15 years and provided unprecedented insight into our global water resources, from more accurate measurements of polar ice loss to a better view of the ocean currents, and the rise in global sea levels."The post TACC Powers Climate Studies with GRACE Project appeared first on insideHPC.

The HiPEAC 2020 conference has issued its Call for Workshops. The event takes place January 20-22, 2020 in Bologna, Italy. "The HiPEAC conference is the meeting place for computing systems researchers in Europe. Put your research on the map with a paper presentation and get your paper published in the open access journal ACM TACO: Transactions on Architecture and Code Optimization."The post Call for Workshops: HiPEAC 2020 in Bologna appeared first on insideHPC.

Ian Foster has been selected to receive the 2019 IEEE Computer Society (IEEE CS) Charles Babbage Award for his outstanding contributions in the areas of parallel computing languages, algorithms, and technologies for scalable distributed applications. "Foster’s research deals with distributed, parallel, and data-intensive computing technologies, and innovative applications of those technologies to scientific problems in such domains as materials science, climate change, and biomedicine. His Globus software is widely used in national and international cyberinfrastructures."The post Ian Foster to receive IEEE Charles Babbage Award appeared first on insideHPC.

In this special guest feature, Dan Olds from OrionX continues his Epic HPC Road Trip series with a stop at NCAR in Boulder. "Their ability to increase model precision/resolution and to increase throughput at the same time is becoming more difficult over time due to core speed slowing down as more cores are added. In other words, new chips aren’t providing the same increase in performance as we’ve become accustomed to over the years."The post Epic HPC Road Trip Continues to NCAR appeared first on insideHPC.

Often, it’s not enough to parallelize and vectorize an application to get the best performance. You also need to take a deep dive into how the application is accessing memory to find and eliminate bottlenecks in the code that could ultimately be limiting performance. Intel Advisor, a component of both Intel Parallel Studio XE and Intel System Studio, can help you identify and diagnose memory performance issues, and suggest strategies to improve the efficiency of your code.The post Are Memory Bottlenecks Limiting Your Application’s Performance? appeared first on insideHPC.

TACC has completed a major upgrade of their Ranch long-term mass data storage system. With thousands of users, Ranch archives are valuable to scientists who want to use the data to help reproduce the measurements and results of prior research. Computational reproducibility is one piece of the larger concept of scientific reproducibility, which forms a cornerstone of […]The post TACC Upgrades Ranch Storage System for Wrangling Big Data appeared first on insideHPC.

Over at the Intel AI blog, Casimir Wierzynski writes that Optical Neural Networks have exciting potential for power-efficiency in AI computation. "At last week’s CLEO conference, we and our collaborators at UC Berkeley presented new findings around ONNs, including a proposal for how that original work could be extended in the face of real-world manufacturing constraints to bring nanophotonic neural network circuits one step closer to a practical reality."The post New Paper: Nanophotonic Neural Networks coming Closer to Reality appeared first on insideHPC.

Today Spectra Logic announced the publication of “Digital Data Storage Outlook 2019,” the company’s fourth annual report on the data storage industry. "This report provides a high-level snapshot of the trends that will influence technological advancements in the data storage industry, and the workflows that will impact the way the world uses and preserves its digital information for the long term.”The post Spectra Logic Report: Digital Data Storage Outlook 2019 appeared first on insideHPC.

Today Dell EMC launched a set of new Dell EMC AI Experience Zones in Bangalore, Seoul, Singapore, Sydney, and Tokyo. “The Dell EMC AI Experience Zones provide a unique space where customers and our partners can explore, test out, and learn about the different physical and virtual components that make up an AI ecosystem. This initiative is the focal point of our commitment to fostering knowledge sharing between CIOs, our ready team of technology experts, and industry partners to accelerate AI adoption and innovation for the region.”The post New Dell EMC AI Experience Zones Launch in Asia appeared first on insideHPC.

Nick Wright from Lawrence Berkeley Lab gave this talk at the GPU Technology Conference. "We'll present an overview of the upcoming NERSC9 system architecture, throughput model, and application readiness efforts. Perlmutter, a Cray system based on the Shasta architecture, will be a heterogeneous system comprising both CPU-only and GPU-accelerated nodes, with a performance of more than 3 times Cori, NERSC’s current platform."The post Video: Perlmutter – A 2020 Pre-Exascale GPU-accelerated System for NERSC appeared first on insideHPC.