High-Performance Computing News Analysis | insideHPC

"These topical workshops are bringing together hardware and software trends spanning various subjects including data analysis, visualization, machine learning for HPC, deep learning, performance benchmarking, parallel computing, correctness, computational reproducibility along with education for HPC. This broader set of topics is just another testimony of how SC19 is reaching out and including new communities."The post SC19 Posts Workshop Schedule appeared first on insideHPC.

Today Google announced that its Google Cloud TPU Pods are now publicly available in beta. Designed to help Machine Learning researchers iterate faster and train more capable machine learning models, TPU Pods can include more than 1,000 individual TPU chips connected by an ultra-fast, two-dimensional toroidal mesh network.The post Google Cloud TPU Pods Speed Machine Learning appeared first on insideHPC.

The general availability of Red Hat Enterprise Linux 8 was announced this week at the Red Hat Summit in Boston. In this special guest feature, Ian Lumb writes that the company's Singularity containers can ease the transition to RHEL 8. "RHEL 8 is a transition over time, not a discrete event in time. Singularity containers preserve your heavily vested legacy deployments, while enabling you to make the transition on your terms."The post How Singularity Containers can ease the Transition to RHEL 8 appeared first on insideHPC.

Hyperion Research will hold their annual HPC Market Update briefing at ISC 2019 in Frankfurt. "As Hyperion Research, we continue all the worldwide activities that spawned the world’s most respected HPC industry analyst group. For more than 25 years, we’ve helped IT professionals, business executives, and the investment community make fact-based decisions on technology purchases and business strategy."The post Hyperion Research to host HPC Market Update Breakfast at ISC 2019 appeared first on insideHPC.

In this video from the HPC User Forum, Frank Alexander from Brookhaven National Laboratory presents: ExaLearn - ECP Co-Design Center for Machine Learning. "It is increasingly clear that advances in learning technologies have profound societal implications and that continued U.S. economic leadership requires a focused effort, both to increase the performance of those technologies and to expand their applications. Linking exascale computing and learning technologies represents a timely opportunity to address those goals."The post ExaLearn: The ECP Co-Design Center for Machine Learning appeared first on insideHPC.

"InstaDeep offers a pioneering AI as a Service solution enabling organizations of any size to leverage the benefits of AI and Machine Learning without the time, costs and expertise required to run their own AI stacks. Excelero’s NVMesh, in turn, allows InstaDeep to access the low-latency, high-bandwidth performance that is essential for running customer AI and ML workloads efficiently – and gain the scalability vital to InstaDeep’s own rapid growth."The post Excelero Powers AI as a Service with Shared NVMe at InstaDeep appeared first on insideHPC.

Engineers at General Atomics have completed fabrication of the first ITER Central Solenoid Module for nuclear fusion. When the ITER fusion energy project in France powers up in 2025, its first operations will be enabled by the largest pulsed superconducting magnet ever built – a magnet that has roots in Southern California.The post General Atomics Fabricates First ITER Central Solenoid Module for Nuclear Fusion appeared first on insideHPC.

In this video, Mao Ye from the University of Illinois describes how his high performance computing computing is shaping the future of Finance. "Ye's research lies at the intersection of big data, high-performance computing and the economics, and finance realm. Using computing resources, Ye tackles large amounts of data currently being collected by companies and finance institutions. “The high-performance computing is more like a tool,” he said, “because we are basically doing big data research.”The post Video: Shaping the Future of Finance with HPC appeared first on insideHPC.

Today CoolIT Systems announced an integrated liquid cooling solution to support the Intel Server System S9200WK. "The Intel Server System S9200WK uses CoolIT’s innovative Rack DLC coldplate solution, featuring patented Split-Flow design. The liquid cooling solution for this 2U, four node server manages heat from the recently announced dual Intel Xeon Platinum 9200 processor CPUs, voltage regulators, and memory."The post CoolIT Systems Launches Liquid Cooling Solution for Intel Server System S9200WK appeared first on insideHPC.

Today AMD announced a new exascale-class supercomputer to be delivered to ORNL in 2021. Built by Cray, the “Frontier” system is expected to deliver more than 1.5 exaFLOPS of processing performance on AMD CPU and GPU processors to accelerate advanced research programs addressing the most complex compute problems. "The combination of a flexible compute infrastructure, scalable HPC and AI software, and the intelligent Slingshot system interconnect will enable Cray customers to undertake a new age of science, discovery and innovation at any scale.”The post AMD to Power Exascale Cray System at ORNL appeared first on insideHPC.

Today One Stop Systems announced plans to demonstrate its award winning AI on the Fly system platforms at the Sea-Air-Space 2019 conference in Maryland. The company’s AI-system platforms accelerate autonomous vehicles, record high-speed surveillance data, detect real-time threats, deploy countermeasures and sift through mountains of radio transmission data to keep the warfighter at the forefront of AI technology.The post OSS rolls out GPUltima Rugged Rack-Scale AI Solution appeared first on insideHPC.

Today DDN announced its intent to acquire Nexenta, the market leader in Software Defined Storage for 5G and Internet of Things (IoT). “Our clients benefit from the flexibility and performance of Nexenta’s robust SDS solutions and platform-agnostic strategy, which provide great differentiation for the HPC, AI, and high-performance data analytics (HPDA) verticals we serve. With escalating demands from our clients for ultra-scalable compute and data storage platforms, we look forward to the exciting developments which will result from this new relationship.”The post DDN Moves Closer to the Edge with Nexenta Acquisition appeared first on insideHPC.

Researchers at the Jülich Supercomputing Centre have installed the first-ever Cluster Module from MEGWARE as part of the European DEEP-EST project for Exascale computing. The Cluster Module consist of a single rack with 50 Intel Xeon Scalable Processor-based dual-socket nodes with a Mellanox EDR-InfiniBand 100Gbps high-performance cluster fabric. "The DEEP-EST prototype will demonstrate that a Modular Supercomputer is much more flexible than a monolithic one, and matches very diverse application profiles in a cost-effective way."The post Jülich installs first Cluster Module for DEEP-EST Exascale Project appeared first on insideHPC.

Lance Wilson from Monash University gave this talk at the GPU Technology Conference. "We'll review the last two years of development in single-particle cryo-electron microscopy processing, with a focus on accelerated software, and discuss benchmarks and best practices for common software packages in this domain. Our talk will include videos and images of atomic resolution molecules and viruses that demonstrate our success in high-resolution imaging."The post Video: How to Scale from Workstation through Cloud to HPC in Cryo-EM Processing appeared first on insideHPC.

The impact of AI is just starting to be realized across a broad spectrum of industries. Tim Miller, Vice President Strategic Development at One Stop Systems (OSS), highlights a new approach — 'AI on the Fly' — where specialized high-performance accelerated computing resources for deep learning training move to the field near the data source. Moving AI computation to the data is another important step in realizing the full potential of AI.The post ‘AI on the Fly’: Moving AI Compute and Storage to the Data Source appeared first on insideHPC.

The need for more young people in STEM careers in a growing concern for the HPC community. Along these lines, more than 70 undergraduate and graduate students participated in the recent XSEDE/DIRECT-STEM training workshops at Cal State LA. "We instruct the students in scientific computing and data science," said Paul Nerenberg, assistant professor of physics and biology and research advisor for the DIRECT-STEM program funded by NASA. "These are going to be core skills for them in their careers no matter what they do."The post XSEDE Teams with Cal State for Advanced Computing Training appeared first on insideHPC.

Dr. Jean-Laurent Philippe from Intel gave this talk at the Swiss HPC Conference. "Intel continues to deliver performance leadership with the introduction of the 56-core, 12 memory channel Intel Xeon Platinum 9200. This processor is designed to deliver leadership socket-level performance and unprecedented DDR memory bandwidth in a wide variety of HPC workloads, AI applications, and high-density infrastructure"The post Video: Intel HPC Platform and Memory Technologies appeared first on insideHPC.

KAUST is seeking an HPC Systems Administrator in our Job of the Week. "The HPC senior systems administrator will work with other Advanced Computing Infrastructure team members to administer the 850 node Ibex+ supercomputer, storage systems, other support computers, networking fabrics and other related systems and services. The required competencies of the senior administrator are: high degree of systems design skill with respect to service dependencies and overall systems availability."The post Job of the Week: HPC Systems Administrator at KAUST appeared first on insideHPC.

In this podcast, the Radio Free HPC looks at the recent ASC Student Cluster Competition in Dalien, China. Dan got to witness the finals last week, with 20 teams facing off in a race for HPC performance. "As always, the team, and the rest of humanity, is highly supportive of the student cluster tournaments that take place at SC, ISC, and this Asian one, in addition to many regional supporting events."The post Radio Free HPC reviews the ASC19 Student Cluster Competition appeared first on insideHPC.

Today Atipa Technologies announced the deployment of its Polaris High Performance Computing and Visualization (HPCV) platform at Northern Illinois University. The platform is a turnkey Intel® Select Solution for Professional Visualization, enabling cost effective and performance verified scientific simulation and visualization. "The ddiLab at Northern Illinois University is extremely excited to integrate Atipa Polaris HPCV Cluster and Intel Rendering Framework into our visualization courses," says Mike Papka, Professor of Computer Science at NIU. "The infrastructure will allow us to train the next generation of visualization experts using tools and software infrastructure that they will encounter at National Laboratories and in the most advanced industry settings."The post Intel Powers Atipa Visualization Cluster at NIU appeared first on insideHPC.

Researchers at Los Alamos National Lab have developed new software to distribute computation more efficiently and across increasing numbers of supercomputer processors. This new decomposition approach for molecular dynamics simulation is called the heterogeneous spatial domain decomposition algorithm, or HeSpaDDA. "In a nutshell, the proposed algorithm will make use of a priori knowledge of the system setup. Specifically, the region which is computationally less expensive."The post New HeSpaDDA Algorithm Distributes Parallel Workloads on LANL Supercomputers appeared first on insideHPC.

Wyatt Gorman from Google and Abhishek Gupta from Schlumberger gave this talk at the GPU Technology Conference. "Demand for GPUs in High Performance Computing is only growing, and it is costly and difficult to keep pace in an entirely on-premise environment. We will hear from Schlumberger on why and how they are utilizing cloud-based GPU-enabled computing resources from Google Cloud to supply their users with the computing power they need, from exploration and modeling to visualization."The post Get Your Head in the Cloud: Lessons in GPU Computing with Schlumberger appeared first on insideHPC.

In this Chip Chat podcast, Jason Kennedy from Intel describes how Intel Deep Learning Boost works as an embedded AI accelerator in the CPU designed to speed deep learning inference workloads. "The key to Intel DL Boost – and its performance kick – is augmentation of the existing Intel Advanced Vector Extensions 512 (Intel AVX-512) instruction set. This innovation significantly accelerates inference performance for deep learning workloads optimized to use vector neural network instructions (VNNI). Image classification, language translation, object detection, and speech recognition are just a few examples of workloads that can benefit."The post Podcast: Accelerating AI Inference with Intel Deep Learning Boost appeared first on insideHPC.

Over at the IBM Blog, Rahil Garnavi writes that IBM researchers have developed new techniques in deep learning that could help unlock earlier glaucoma detection. "Earlier detection of glaucoma is critical to slowing its progression in individuals and its rise across our global population. Using deep learning to uncover valuable information in non-invasive, standard retina imaging could lay the groundwork for new and much more rapid glaucoma testing."The post IBM Research Applies Deep Learning for Detecting Glaucoma appeared first on insideHPC.

Researchers at the University of Pittsburgh are using XSEDE supercomputing resources to develop new materials that can capture carbon dioxide and turn it into a commercially useful substances. With global climate change resulting from increasing levels of carbon dioxide in the Earth's atmosphere, the work could lead to a lasting impact on our environment. "The basic idea here is that we are looking to improve the overall energetics of CO2 capture and conversion to some useful material, as opposed to putting it in the ground and just storing it someplace," said Karl Johnson from the University of Pittsburgh. "But capture and conversion are typically different processes."The post Pitt Researchers using HPC to turn CO2 into Useful Products appeared first on insideHPC.

Today Italian HPC and AI specialist E4 Computer Engineering announced a strategic partnership with bluechip Computer AG, a leading German manufacturer of server, storage, workstation and client systems. Under the agreement, the two companies will co-market bluechip servers and storage along with consulting, installation, and support services for HPC and AI applications. "Thanks to the strategic partnership with E4 Computer Engineering, we will be able to implement HPC solutions in a much more efficient way in the DACH region. Both companies will benefit from their specialized knowledge, which complements each other and will enable bluechip to deliver an excellent German-language support to its customers in this area.“, said Bogdan Kruszewski, Head of product marketing at bluechip Computer AG.The post E4 teams with bluechip Computer AG in Germany for HPC appeared first on insideHPC.

Mario Kovač from EPI gave this talk at the Swiss HPC Conference. "EPI will provide to the European industry and research a competitive HPC platform and data processing solutions at world class level in the best interest of data security and ownership. Thanks to such new European technologies, European scientists and industry will be able to access exceptional levels of energy-efficient computing performance. This will benefit Europe's scientific leadership, industrial competitiveness, engineering skills and know-how and the society as whole."The post European Processor Initiative: The EuroHPC Industrial Cornerstone appeared first on insideHPC.

In this interview, Joseph George from Cray describes the company's new offerings for Cray in Azure. "The Cray and Microsoft Azure teams have been actively working on numerous customer engagements together, in an effort to clearly understand the optimal cloud model for large scale HPC workloads, and the best consumption model for HPC users. With all that research as a foundation, it has become clear to us that a dedicated and reserved instance cloud model allows for an ideal HPC experience at large scale."The post Interview: Cray in Azure Steps up with Dedicated Supercomputing in the Cloud appeared first on insideHPC.

A team of researchers from Virginia Tech is helping supercomputers to work more efficiently in a novel way, using machine learning to properly distribute, or load balance, data processing tasks across the thousands of servers that comprise a supercomputer. By incorporating machine learning to predict not only tasks but types of tasks, researchers found that load on various servers can be kept balanced throughout the entire system.The post Virginia Tech Team Using AI for Supercomputer Load Balancing appeared first on insideHPC.

Researchers at Sandia National Laboratories have collaborated with Stanford University and University of Massachusetts, Amherst to address the challenges of neuromorphic computing, which mimics the way the human brain carries out data-centric tasks. The work has lead to recent breakthroughs in neuromorphic computing and the broader fields of organic electronics and solid-state electrochemistry.The post Sandia Powers Breakthroughs in Neuromorphic Computing appeared first on insideHPC.

A novel supercomputer developed by a University of Pittsburgh team is set to journey to the International Space Station on May 1. The supercomputer will serve as a research “sandbox” for space-based experiments on computing, sensing, image processing and machine learning. "It will be “one of the most powerful space-qualified computers ever made and flown,” said Alan George, department chair of the Swanson School of Engineering’s Department of Electrical and Computer Engineering, who led Pitt researchers and graduate students on the project."The post NASA to Launch University of Pittsburgh Supercomputer into Space appeared first on insideHPC.

In this video, Mike Croucher from NAG demonstrates the company's new Total Cost of Ownership Calculator for HPC. "Should your next HPC procurement be on-premise or in the cloud? This is one of the questions that our clients ask us to help with and part of the answer involves Total Cost of Ownership of the resulting facility. This calculator is provided as a working example of a TCO model."The post Video: NAG Launches HPC Cost of Ownership Calculator appeared first on insideHPC.

The Cornell University Center for Advanced Computing (CAC) is collaborating with RightScale, recently acquired by Flexera, to understand how to best manage and optimize costs in a multi-cloud world. "Universities and research facilities are beginning to recognize that cloud management platforms (CMPs) are a useful tool for monitoring and controlling research expenditures, particularly as scientists seek different clouds for different capabilities," said David A. Lifka, vice president for information technologies and CIO at Cornell. "By working with the Optima team, we’re adding to our current CMP experience and gaining knowledge on how to effectively address the unique needs of research computing and education users."The post Cornell Investigates Multi-cloud Cost Management with RightScale appeared first on insideHPC.

In this special guest feature, Scot Schultz from Mellanox writes researchers are benefitting in a big way from HPC in the Cloud. "HPC has many different advantages depending on the specific use case, but one aspect that these implementations have in common is their use of RDMA-based fabrics to improve compute performance and reduce latency."The post HPC Breaks Through to the Cloud: Why It Matters appeared first on insideHPC.

Today Ayar Labs announced that the company has secured additional funding to fuel its growth as it drives to productize its TeraPHY optical I/O chiplets and SuperNova multi-wavelength lasers in 2019. The company aims to disrupt the traditional performance, cost, and efficiency curves of the semiconductor and computing industries by driving a" 1000x improvement" in interconnect bandwidth density at 10x lower power.The post New Funding and DARPA Grant to Propel Optical Interconnects at Ayar Labs appeared first on insideHPC.

Bill Dally from NVIDIA gave this talk at the Matroid Scaled Machine Learning Conference. "The world of computing is experiencing an incredible change with the introduction of deep learning and AI. Deep learning relies on GPU acceleration, both for training and inference, and NVIDIA delivers it everywhere you need it—to data centers, desktops, laptops, the cloud, and the world’s fastest supercomputers."The post Bill Dally from NVIDIA presents: Accelerating AI appeared first on insideHPC.

The 7th annual MVAPICH User Group (MUG) meeting has issued its Call for Presentations. MUG will take place from August 19-21, 2019 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 with MVAPICH developers, etc."The post Call for Presentations: MVAPICH User Group in August appeared first on insideHPC.

Today Liqid announced unified multi-fabric support for composability across all major fabric types including PCIe Gen 3, PCIe Gen 4, Ethernet, Infiniband, and laying the foundation for the up-coming Gen-Z specifications. "Providing Ethernet and Infiniband composability in addition to PCIe is a natural extension of our expertise in fabric management and aligns with our mission to facilitate data center disaggregation,” said Sumit Puri, CEO and Co-founder, Liqid.The post Liqid Enables Multi-Fabric Support for Composable Infrastructure appeared first on insideHPC.

Calcul Québec has deployed a new supercomputer to power research in Canada. With over 28,000 compute cores and 688 NVIDIA V100 GPUs, the new Béluga system was first made available at the beginning of April and is now the main high performance computing infrastructure in the province. "Béluga is a state-of-the-art supercomputer and was made available through the exceptional teamwork of our research and teaching institutions. It will become an essential part of advancing research in Quebec.”The post Beluga Supercomputer comes to Calcul Québec appeared first on insideHPC.

NVIDIA's GPU Technology Conference will returns to Washington, D.C. Nov 5-6, 2019. "GTC is the premier AI and deep learning conference series, providing you with training, insights, and direct access to experts from NVIDIA and other leading organizations. Join NVIDIA for the latest breakthroughs in self-driving cars, accelerated data science, healthcare, big data, high-performance computing, virtual reality, and more."The post GPU Technology Conference Returns to DC in November appeared first on insideHPC.

Altair invites engineering students from across the globe to participate in their Student Competition for Innovation in Electromagnetics. “At a time when energy efficiency is a global priority, students can use Altair software to design future generation e-motors and other electric equipment. Think of what a tremendous impact they can make on the planet. Altair software solutions are broadly used in the academic engineering communities and am already looking forward to the many innovative entries in both areas of electromagnetics.”The post Register for the Altair Student Competition for Innovation in Electromagnetics appeared first on insideHPC.

Robert Triendl from DDN gave this talk at the Swiss HPC Conference. "The Portable Operating System Interface (POSIX) is a family of standards specified by the IEEE Computer Society for maintaining compatibility between operating systems. Since it was developed over 30 years ago, storage has changed dramatically. To improve the IO performance of applications, many users have called for the relaxation in POSIX IO that could lead to the development of new storage mechanisms to improve not only application performance, but management, reliability, portability, and scalability."The post Long Live Posix – HPC Storage and the HPC Datacenter appeared first on insideHPC.

Micron recently unveiled its new series of flagship solid-state drives (SSDs) featuring the NVMe protocol, bringing industry-leading storage performance at higher capacities to cloud and enterprise computing markets. The Micron 9300 series of NVMe SSDs enables companies with data-intensive applications to access and process data faster, helping reduce response time.The post Micron steps up with NVMe SSDs appeared first on insideHPC.

Frank Herold from ThinkParQ gave this talk at the HPC User Forum. "Together with our partners around the globe, we work hard to create the fastest, most stable and most flexible turn-key solutions for every performance-oriented environment. Therefore, you can find BeeGFS powered solutions not only in HPC, but also in all other markets where performance matters: Life Sciences, Artificial Intelligence, Finance, Oil & Gas, Media & Entertainment, and Automotive."The post BeeGFS – Dealing with Extreme Requirements in HPC appeared first on insideHPC.

In this Chip Chat podcast, Trish Damkroger from Intel outlines a few of the key technologies coming to the Aurora supercomputer in 2021. To enable Exascale levels of performance, Aurora will be built with a future generation Intel Xeon Scalable processor, the recently announced Intel Xe compute architecture, and Intel Optane DC persistent memory. Built by subcontractor Cray, Aurora will enable ground-breaking science such as precision medicine, climate modeling, weather forecasting, and materials science.The post Podcast: Intel to Deliver Exascale for the Advancement of Science appeared first on insideHPC.

In this special guest feature from Scientific Computing World, Mahesh Pancholi from OCF writes a growing number of universities are taking advantage of public cloud infrastructures that are widely available from large companies like Amazon, Google and Microsoft. "Public cloud providers are surveying the market and partnering with companies, like OCF, for their pedigree in providing solutions to the UK Research Computing community. In order to help Universities take advantage of their products by integrating them with the existing infrastructure such as HPC clusters."The post Is Ubiquitous Cloud Bursting on the Horizon for Universities? appeared first on insideHPC.

Argonne is now accepting proposals for the ALCF Data Science Program (ADSP) through July 1, 2019. "The ADSP open call provides an opportunity for researchers to submit proposals for projects that will employ advanced statistical, machine learning, and artificial intelligence techniques to gain insights into massive datasets produced by experimental, simulation, or observational methods."The post Call for Proposals: ALCF Data Science Program appeared first on insideHPC.

CGG in Houston is seeking a Linux Administrator in our Job of the Week. CGG is a fully integrated Geoscience company providing leading geological, geophysical, and reservoir capabilities. "We bring our clients a unique range of technologies, services and equipment designed to acquire extremely precise data and images of the Earth's subsurface. We also provide state-of-the-art software and services for analyzing that data and developing a deeper understanding of the subsurface for exploration, production and optimization of oil and gas reservoirs."The post Job of the Week: Linux Administrator at CGG in Houston appeared first on insideHPC.

In this Big Compute Podcast, Steve Reinhardt from D-Wave Systems describes how quantum computing can be used to find optimal solutions in complex optimizations. “For decades quantum computers will be used in a hybrid mode with classical computers. So as a developer you don’t have to solve your complete problem. You can look at where the time is spent in computation and move those models to quantum computers. These modules may be optimized to be billions of times faster.”The post Big Compute Podcast Looks at Quantum Computing Today appeared first on insideHPC.

ISC 2019 has announced the finalists for this year’s Hans Meuer Award, which honors the most outstanding research paper submitted to the ISC High Performance Conference. The award was introduced in 2015 in memory of the late Dr. Hans Meuer, general chair of the ISC conference from 1986 through 2014, and co-founder of the TOP500 […]The post Finalists Chosen for Hans Meuer Award appeared first on insideHPC.