High-Performance Computing News Analysis | insideHPC

Today One Stop Systems introduced the world’s first PCIe Gen 4 backplane. "Delivering the high performance required by edge applications necessitates PCIe interconnectivity traveling on the fast data highway between high-speed processors, NVMe storage and compute accelerators using GPUs or application specific FPGAs,” continued Cooper. “‘AI on the Fly’ applications naturally demand this capability, like the government mobile shelter application we announced earlier this year.”The post OSS Introduces World’s First PCIe Gen 4 Backplane at GTC appeared first on insideHPC.

The European Commission has approved a multi-million funding program for developing applications in High Performance Computing. The funds will be used to help build HPC Centers of Excellence in 10 member countries. From computing the reduction of noise and fuel for passenger airplanes to assessing the effects of climate change – Applications in High Performance […]The post European Commission Funds 10 Centers of Excellence for HPC appeared first on insideHPC.

Paul Grun from Cray gave this talk at the OpenFabrics Workshop in Austin. "Persistent Memory exhibits several interesting characteristics including persistence, capacity and others. These (sometimes)competing characteristics may require system and server architects to make tradeoffs in system architecture. In this session, we explore some of those tradeoffs and take an early look at the emerging use cases for Remote Persistent Memory and how those may impact network architecture and API design."The post Characteristics of Remote Persistent Memory – Performance, Capacity, or Locality? appeared first on insideHPC.

Today Quantum Corp. announced the Texas Advanced Computing Center has selected Quantum StorNext as their archive file system, with a Quantum Scalar i6000 tape library providing dedicated Hierarchical Storage Management. "Our ability to archive data is vital to TACC’s success, and the combination of StorNext as our archive file system managing Quantum hybrid storage, Scalar tape and our DDN primary disk will enable us to meet our commitments to the talented researchers who depend on TACC now and in the future,” said Tommy Minyard, Director of Advanced Computing at TACC.The post TACC to power HSM Archives with Quantum Corp Tape Libraries appeared first on insideHPC.

Today Inspur announced that their new NF5488M5 high-density AI server supports eight NVIDIA V100 Tensor Core GPUs in a 4U form factor. "The rapid development of AI keeps increasing the requirements for computing performance and flexibility of AI infrastructure. The NF5488M5 help users shorten AI model development cycles, and accelerate AI technology innovation and application development."The post New Inspur AI Server Supports Eight NVIDIA V100 Tensor Core GPUs appeared first on insideHPC.

In this Intel on Ai Podcast, Dr. David Ellison from Lenovo describes the Lenovo Intelligent Computing Orchestration (LiCO). "Dr. Ellison explains how LiCO accelerates artificial intelligence training and traditional high performance computing (HPC) deployment by providing a single software solution that simplifies resource management and the use of a cluster environment. He discusses an exciting real-world deployment where data scientists use LiCO to help analyze satellite images of crop fields to drive drought prevention and increase food security."The post Podcast: How Lenovo Intelligent Computing Orchestration is Simplifying HPC & AI appeared first on insideHPC.

"The all-new hyperscale configuration of AI-Ready Infrastructure (AIRI) from Pure Storage is designed to deliver supercomputing capabilities for enterprises that pioneer real-world AI initiatives and have grown beyond the capabilities of AI-ready solutions available in the market today. Built jointly with the leaders of AI supercomputing, NVIDIA and Mellanox, hyperscale AIRI delivers multiple racks of NVIDIA DGX-1 and DGX-2 systems with both Infiniband and Ethernet fabrics as interconnect options. In addition, Pure Storage announced FlashStackTM for AI, a solution built jointly with Cisco and NVIDIA to bring AI within reach for every enterprise."The post Pure Storage Unveils NVIDIA-Powered Ai Solutions appeared first on insideHPC.

Xiaoyi Lu from Ohio State University gave this talk at the 2019 OpenFabrics Workshop in Austin. "Google's TensorFlow is one of the most popular Deep Learning (DL) frameworks. We propose a unified way of achieving high performance through enhancing the gRPC runtime with Remote Direct Memory Access (RDMA) technology on InfiniBand and RoCE. Through our proposed RDMAgRPC design, TensorFlow only needs to run over the gRPC channel and gets the optimal performance."The post Accelerating TensorFlow with RDMA for High-Performance Deep Learning appeared first on insideHPC.

Today HPC cloud provider Nimbix announced a new strategic partnership with Lenovo Data Center Group (DCG). "Lenovo DCG and Nimbix have teamed up to deliver flexible, powerful solutions based on Lenovo HPC clusters and the Nimbix Cloud. By bringing together Lenovo’s supercomputing expertise with JARVICE, the purpose-built, container-based, bare metal HPC Cloud platform from Nimbix, customers can tailor their hardware and software resources to meet their business requirements, no matter how demanding."The post Lenovo HPC Clusters come to the Nimbix Cloud appeared first on insideHPC.

Today Microway announced that it has been recognized with the Americas 2018 NVIDIA Partner Network (NPN) HPC Partner of the Year Award. Microway was presented with this award at the NPN Reception and Awards Ceremony held during the 2019 NVIDIA GPU Technology Conference (GTC). "Microway lives and breathes high performance computing,” said Craig Weinstein, Vice President of the Americas Partner Organization at NVIDIA. “They’ve been a long-time partner of ours for many years and it has been a pleasure to see them flourish into one of the most well-respected, knowledgeable companies in the industry.”The post Microway Receives NVIDIA HPC Partner of the Year Award appeared first on insideHPC.

This week at GTC, DDN is showcasing its high speed storage solutions, including its A³I architecture and new customer use cases in autonomous driving, life sciences, healthcare, retail, and financial services. DDN next generation of A³I reference architectures include NVIDIA’s DGX POD, DGX-2, and the DDN’s AI400 parallel storage appliance. “DDN’s commitment to developing highly parallel and scalable architectures matches well with the high performance requirements of compute and AI applications."The post DDN Accelerates Ai, Analytics, and Deep Learning at GTC appeared first on insideHPC.

In this video, NVIDIA CEO Jensen Huang delivers a sweeping opening keynote at San Jose State University, describing the company’s progress accelerating the sprawling datacenters that power the world’s most dynamic industries. "As a highlight, Mellanox CEO Eyal Waldman joined Huang on stage to describe how the two company's technologies power more than half the world’s TOP500 fastest supercomputers."The post Video: Jensen Huang Keynote and News Recap from GPU Technology Conference appeared first on insideHPC.

AI is a game changer for industries today but achieving AI success contains two critical factors to consider — time to value and time to insights. Time to value is the metric that looks at the time it takes to realize the value of a product, solution or offering. Time to insight is a key measure for how long it takes to gain value from use of the product, solution or offering.The post AI Critical Measures: Time to Value and Insights appeared first on insideHPC.

Today Intel announced plans to deliver the first exaflop supercomputer in the United States. The Aurora supercomputer will be used to dramatically advance scientific research and discovery. The contract is valued at more than $500 million and will be delivered to Argonne National Laboratory by Intel and sub-contractor Cray in 2021. "Today is an important day not only for the team of technologists and scientists who have come together to build our first exascale computer – but also for all of us who are committed to American innovation and manufacturing,” said Bob Swan, Intel CEO."The post Video: Intel and Cray to Build First USA Exascale Supercomputer for DOE in 2021 appeared first on insideHPC.

Today a coalition led by Pacific Northwest National Laboratory, Microsoft Quantum, and the University of Washington will convene in Seattle to launch the Northwest Quantum Nexus. The invite-only Summit will establish a center of geographic and intellectual gravity in the Northwest, where a talent pool can flourish and contribute to the quantum economy, through knowledge sharing, skill and experience development, research impacts, and community engagement. “By establishing this partnership in quantum computing, we are planting a seed in fertile ground. We are forming a nexus for nurturing a talent pool and establishing the quantum economy through knowledge sharing, skill and experience development, and community engagement.”The post PNNL Leads Quantum Nexus Summit in Seattle appeared first on insideHPC.

John Fragalla from Cray gave this talk at the Rice Oil & Gas Conference. "In Oil and Gas, when using shared storage, mixed workloads can have a big impact on I/O performance causing considerable slowdown when running small I/O alongside large I/O on the same storage system. In this presentation, Cray will share real benchmark results on the impacts of the "Noisy Neighbor" application has on sequential I/O, and with the right storage tuning and flash capacity, how to optimize the storage to meet the demanding workloads of Oil and Gas to accelerate performance for a mixed workload environment."The post Video: Solving I/O Slowdown and the “Noisy Neighbor” Problem appeared first on insideHPC.

Today Mellanox announced that its HDR 200G InfiniBand with the “Scalable Hierarchical Aggregation and Reduction Protocol” (SHARP) technology has set new performance records, doubling deep learning operations performance. The combination of Mellanox In-Network Computing SHARP with NVIDIA 100 Tensor Core GPU technology and Collective Communications Library (NCCL) deliver leading efficiency and scalability to deep learning and artificial intelligence applications.The post Mellanox HDR 200G InfiniBand Speeds Machine Learning with NVIDIA appeared first on insideHPC.

Computer systems are about to get a whole lot faster. This year starting at the high end of the market a transition will begin toward systems based on PCI Express 4.0. The interconnect speed will double to 64GB/sec in a 16 lane connection. Tim Miller, Vice President Strategic Development for One Stop Systems, explores the expected speed and innovation stemming from the introduction of PCI Express 4.0.The post 2019: The Year of PCI Express 4.0 appeared first on insideHPC.

NVIDIA’s GPU Technology Conference (GTC) kicks off today in Silicon Valley. In this video, Ned Finkle from NVIDIA previews some of the public sector sessions this week at GTC. "GTC is the premier AI and deep learning conference, providing training, insights, and direct access to experts from leading research institutions and national labs. At GTC, you can explore hundreds of sessions on cutting edge AI research and applications across industries."The post GPU Technology Conference to put HPC and Ai front and center appeared first on insideHPC.

In this video from the Rice Oil & Gas Conference, Andrew Jones from NAG moderates a panel session on the challenges for meeting computing-capacity demand in the energy industry for the next decade. "This panel gives an opportunity for younger people to get valuable career experience and exposure, for the audience to hear from new and diverse ideas, and to stimulate the community discussion of HPC opportunities in O&G from a fresh viewpoint."The post Panel session: Meeting compute demand for the energy industry in the next decade appeared first on insideHPC.

"The Manager of HPC Systems within Information Technology Services will be responsible for enabling both existing and emerging high performance computing solutions and related infrastructure, providing a high level of service in the deployment and maintenance of HPC supercomputer hardware and software to the research communities of LSU and its collaborators. The Manager will be responsible for managing the system administration group in monitoring daily cluster operations, troubleshooting cluster problems, researching and implementing new technologies, and providing appropriate support for LSU's research initiatives."The post Job of the Week: Information Technology Manager at Louisiana State University appeared first on insideHPC.

In this podcast, the Radio Free HPC team discusses AI, bias in AI, and just how real AI actually is. "Ethics in AI, policy, legal framework are all big threads here. The trigger is the rather funny article from The Register: Artificial Intelligence, You Know it isn’t real, yeah?"The post Podcast: How Real is Ai Anyway? appeared first on insideHPC.

A new distributed file system for HPC being distributed today via GitHub provides unprecedented performance for creating, updating and managing extreme numbers of files. "We designed DeltaFS to enable the creation of trillions of files,” said Brad Settlemyer, a Los Alamos computer scientist and project leader. “Such a tool aids researchers in solving classical problems in high-performance computing, such as particle trajectory tracking or vortex detection.”The post Video: LANL Open Sources DeltaFS software for Wrangling Trillions of Files appeared first on insideHPC.

Computationally, EXAALT’s goal is to develop a comprehensive molecular dynamics capability for exascale. "The user should be able to say, ‘I’m interested in this kind of system size, timescale, and accuracy,’ and directly access the regime without being constrained by the usual scaling paths of current codes,” said Danny Perez of Los Alamos National Laboratory (LANL) and the EXAALT team.The post Podcast: ECP EXAALT Program Extends the Reach of Molecular Dynamics appeared first on insideHPC.

Brent Gorda from ARM gave this talk at the Rice Oil & Gas Conference. "With the recent Astra system at Sandia Lab (#203 on the Top500) and HPE Catalyst project in the UK, Arm-based architectures are arriving in HPC environments. Several partners have announced or will soon announce new silicon and projects, each of which offers something different and compelling for our community. Brent will describe the driving factors and how these solutions are changing the landscape for HPC."The post Video: Arm in HPC appeared first on insideHPC.

What are the economic benefits of HPC? A new study by the University of Colorado Boulder's Leeds School of Business indicates that the economic impact of NREL amounted to more than $1.1 billion nationwide, while the impact on Colorado's economy came in at nearly $748 million. “The lab’s highly skilled workforce, innovative facilities, and business partnerships are key to the region’s economic vitality.”The post Report: NREL Economic Impact Tops $1 Billion appeared first on insideHPC.

Over the past two years, we’ve seen a dramatic acceleration in cloud adoption for HPC. Intuitively cloud computing makes sense — it enables organizations to rent rather than buy expensive HPC hardware, deploy solutions faster, reduce capital investments, and focus on core competencies. Software company Univa highlights the reason behind the recent cloud adoption boom among the HPC community, and the benefits of the hybrid HPC cloud.The post Building the business case for Hybrid HPC Cloud appeared first on insideHPC.

Today the European Submer startup announced that their latest SmartPod Immersion Cooling System conforms to both standard server formats and to Open Compute Project (OCP) specifications for high-performance, supercomputing, and hyperscale infrastructures – the SmartPodX. "The Open Compute Project exists to develop open standards that bring greater efficiency, scalability, openness, and positive impact to datacenters and hardware – making all of our lives better," said Submer CEO Daniel Pope. "This makes the OCP Global Summit the perfect opportunity to launch our hyper-efficient SmartPodX that will power the next generation of high-performance servers and supercomputers that usher in the next wave of research and technical innovation.”The post Submer SmartPodX Platform launches for OCP Immersion Cooling appeared first on insideHPC.

Earlier this week, countries involved in the Square Kilometre Array (SKA) Project came together in Rome to sign an international treaty establishing the intergovernmental organization that will oversee the delivery of the world’s largest radio telescope. "Two of the world’s fastest supercomputers will be needed to process the unprecedented amounts of data emanating from the telescopes, with some 600 petabytes expected to be stored and distributed worldwide to the science community every year, or the equivalent of over half a million laptops worth of data."The post In a boon for HPC, Founding Members Sign SKA Observatory Treaty appeared first on insideHPC.

Today the RISC-V Foundation announced that Calista Redmond has been appointed Chief Executive Officer (CEO), effective immediately. I’ve always understood the potential short- and long-term impact of the RISC-V license-free ISA on the open source community. Having spent a lot of my career working in the open source ecosystem, I’m excited to help RISC-V grow and deliver on the Foundation’s mission of paving the way for the next 50 years of computing design and innovation,” said Redmond, CEO of the RISC-V Foundation."The post Calista Redmond named CEO of RISC-V Foundation appeared first on insideHPC.

Coming up in April, AI and HPC practitioners share passions for cutting-edge technology and breakthrough R&D in Lugano, Switzerland at the tenth annual Swiss Conference and HPCXXL User Group. The joint sessions take place at Palazzo dei Congressi, April 1-4, bringing leaders together from academia, government and industry to share first-hand insights on innovative research, techniques, tools and technologies that are fueling economies, productivity and progress globally.The post Swiss HPC Conference to Focus on Intersecting Interests, Industries, and Initiatives appeared first on insideHPC.

A computer science research group from the Hebrew University of Jerusalem has mathematically proven that artificial intelligence (AI) can help us understand currently unreachable quantum physics phenomena. The results have been published in Physical Review Letters. "Our research proves that the AI algorithms can represent highly complex quantum systems significantly more efficiently than existing approaches," said Prof. Amnon Shashua, Intel senior vice president and Mobileye president and CEO."The post New Study: Algorithms based on deep neural networks can be applied to quantum physics appeared first on insideHPC.

"At the 2019 American Physical Society March Meeting, IBM unveiled a new scientific milestone, announcing its highest quantum volume to date. Quantum Volume is a measurement, a procedure developed by IBM, that determines how powerful a quantum computer is, accounting for both gate and measurement errors, device cross talk, as well as device connectivity and circuit compiler efficiency. It follows that the higher the Quantum Volume, the more real-world, complex problems quantum computers can potentially solve, such as simulating chemistry, modeling financial risk, and supply chain optimization."The post Video: Benchmarking Performance with Quantum Volume appeared first on insideHPC.

As Machine Learning advances, how will we know that these systems are making the right decisions? In this story from the Fraunhofer Heinrich Hertz Institute, researchers are looking at the learning strategies of today's Ai systems. "We were very surprised by just how broad the range of learned problem-solving strategies is. Even modern AI systems have not always found a meaningful approach, at least not from a human perspective, instead sometimes adopting what we call ‘Clever Hans’ strategies."The post Any better than Clever Hans? Putting AI systems to the test appeared first on insideHPC.

Today chip startup Tachyum announced that it has received capital from the Slovak government of almost $17 million dollars to help build a new R&D center within the country. This funding will assist in the final development phase of the company’s Prodigy Universal Processor Chip, the smallest and fastest general-purpose, 64-bit processor, requiring 10x lower power and 3x lower sell price than competing products with equivalent performance. Together, these two attributes result in Prodigy reducing data center annual total cost of ownership (CapEx + OpEx) by a factor of 4x.The post Tachyum Chip Startup gets $17 Million Capital Infusion from Slovak Government appeared first on insideHPC.

Satoshi Matsuoka from RIKEN gave this talk at the Rice Oil & Gas Conference. "Rather than to focus on double precision flops that are of lesser utility, rather Post-K, especially its Arm64fx processor and the Tofu-D network is designed to sustain extreme bandwidth on realistic applications including those for oil and gas, such as seismic wave propagation, CFD, as well as structural codes, besting its rivals by several factors in measured performance. Post-K is slated to perform 100 times faster on some key applications c.f. its predecessor, the K-Computer, but also will likely to be the premier big data and AI/ML infrastructure."The post Video: The Game Changing Post-K Supercomputer for HPC, Big Data, and Ai appeared first on insideHPC.

Today Mellanox announced NVMe SNAP (Software-defined, Network Accelerated Processing), a storage virtualization solution for public cloud, private cloud and enterprise computing. This new SNAP technology allows customers to compose remote server-attached NVMe Flash storage and access it as if it were local, to achieve all the efficiency and management benefits of remote storage, with the simplicity of local storage.The post Mellanox NVMe SNAP Technology to Simplify Composable Storage appeared first on insideHPC.

In this video from the 2019 Rice Oil & Gas conference, Trish Damkroger from Intel presents: A New Era in HPC. "In this keynote presentation, Trish will discuss the changing landscape of high performance computing, key trends, and the convergence of HPC-AI-HPDA that is transforming our industry and will fuel HPC to fulfill its potential as a scientific tool for business and innovation. Trish will highlight not only key forces driving this shift but discuss how this transformation requires a fundamental paradigm shift and is opening up unprecedented opportunities for HPC."The post Video: A New Era in HPC appeared first on insideHPC.

Today the University of Edinburgh announced plans to deploy ARCHER2, a £79 million national supercomputer that will be five times faster than the UK’s current capabilities. "ARCHER2 will provide UK science with an unparalleled capability to model and simulate the world around us," said Professor Mark Parsons, EPCC Director. "This is a real vote of confidence in the University’s supercomputing centre, EPCC, which is internationally recognised for its excellence in computational science."The post ARCHER2 Supercomputer coming to University of Edinburgh appeared first on insideHPC.

In this podcast, the Radio Free HPC team looks at NVIDIA's acquisition of Mellanox. "This called for an emergency session of our crack panel. While it will be several months before the full impact of this merger is felt, the RFHPC team believes this will change both the HPC and the Datacenter markets. It also signals Nvidia's journey towards becoming more of a systems company and gives them a better shot at the enterprise AI market."The post Radio Free HPC Looks at NVIDIA’s acquisition of Mellanox appeared first on insideHPC.

The increasing consumerization of IT means that even staid business applications like accounting need to have the performance and ease of use of popular consumer apps. Fortunately, developers now have access to a powerful group of libraries that can instantly increase application performance – with little or no rewriting of older code. Here’s a quick rundown of Intel-provided libraries and how to get them.The post Achieving the Best QoE: Performance Libraries Accelerate Code Execution appeared first on insideHPC.

This feature story describes how the computational power of Frontera will be a game changer for research. Late last year, the Texas Advanced Computing Center announced plans to deploy Frontera, the world's fastest supercomputer in academia. To prepare for launch, TACC just published the inaugural edition of Texascale, an annual magazine with stories that highlight the people, science, systems, and programs that make TACC one of the leading academic computing centers in the world.The post New Texascale Magazine from TACC looks at HPC for the Endless Frontier appeared first on insideHPC.

Today Quobyte announced announced plans to showcase distributed storage technology at NVIDIA’s GPU Technology Conference in Silicon Valley next week. Quobyte software defined storage turns commodity servers into a reliable and highly automated data center file system. "As machine learning increasingly becomes an indispensable tool for organizations looking to make critical decisions derived from their cumulative data, there is an increasing need for unified storage infrastructure that enables faster results and the ability to fully leverage GPUs,” said Bjoern Kolbeck, Quobyte co-founder and CEO. “We are excited to have the opportunity to present to attendees of NVIDIA’s GTC how they can quickly and easily speed up their ML workloads by overcoming data challenges associated with scale, throughput and access to all data throughout the organization.”The post Quobyte to showcase software defined storage for Machine Learning at GTC appeared first on insideHPC.

Today NVIDIA announced plans to acquire Mellanox for approximately $6.9 billion. The acquisition will unite two of the world’s leading companies in HPC. Together, NVIDIA’s computing platform and Mellanox’s interconnects power over 250 of the world’s TOP500 supercomputers and have as customers every major cloud service provider and computer maker.The post NVIDIA to Purchase Mellanox for $6.9 Billion appeared first on insideHPC.

Today the OpenFabrics Alliance (OFA) posted the OFA Workshop 2019 Agenda & Abstracts for their upcoming OFA Workshop. With sessions on ranging from interoperability and remote persistent memory to deployment of fabric technologies, the meeting takes place March 19-21 in Austin, Texas. "Over the three-day event, attendees will be treated to a brand-new Workshop activity that further underscores the OFA’s commitment to fostering collaboration and adoption within the advanced fabrics community."The post Agenda Posted: OFA Workshop in Austin March 19-21 appeared first on insideHPC.

David Wade from Integral Engineering gave this talk at the Stanford HPC Conference. "In this talk, a design is sketched for an engine to ingest data from the IOT massively into a cluster for analysis, storage and transformation using COTS methods from High Performance Computing techniques in hardware and software."The post Video: A Fast, Scaleable HPC Engine for Data Ingest appeared first on insideHPC.

In this video, Diarmoid Daltun from Submer and Daniele Rispoli from ClusterVision describe how Immersion Cooling applies to a HPC installation, including the benefits, challenges, economics, practicality, and more. "We are a cleantech company that designs, builds and installs Liquid Immersion cooling solutions for HPC, hyperscaler, datacenters, Edge, AI, deep learning and blockchain applications. Set apart by its modular design, our technology is the most practical, resilient, eco-friendly and highly efficient Immersion Cooling solution."The post Video: Submer Technology for HPC Immersion Cooling appeared first on insideHPC.

The National Energy Technology Laboratory (NREL) in Golden, Colorado is seeking a Computer Engineer in our Job of the Week. "At NREL, we focus on creative answers to today's energy challenges. From breakthroughs in fundamental science to new clean technologies to integrated energy systems that power our lives, NREL researchers are transforming the way the nation and the world use energy.":The post Job of the Week: Computer Engineer at NETL appeared first on insideHPC.

NVIDIA has gained traction in datacenter Machine Learning with their DGX platforms. Now Bay Area provider Colovore has signed up as a colocation partner supporting NVIDIA DGX deployments. “NVIDIA’s DGX-1 and DGX-2 platforms are leading the way in solving complex AI challenges and we are proud to partner with NVIDIA and their customers to provide the most cost-effective, flexible, and scalable data center home for these servers. With close to 1,000 DGX platforms already deployed and operating at Colovore, we have tremendous experience providing the optimal footprint for DGX and HPC infrastructure success.”The post Nvidia Certifies Colovore As DGX-Ready Data Center Partner appeared first on insideHPC.

Over at TACC, Faith Singer-Villalobos writes that researchers are using supercomputers to better understand the lung development of premature babies. The insight derived from large datasets could help save lives. In 2016, over a dozen scientists and engineers toured a neonatal intensive care unit, the section of the hospital that specializes in the care of ill […]The post How Supercomputing could help save newborn babies with LungMap appeared first on insideHPC.