• Report: China ‘Seizing’ HPC High Ground, Plans 10 Exascale Systems by 2025

    Exascale supercomputing – which systems vendors can deliver it, which supercomputing centers can access it, which countries have it – will no doubt be a hot topic at the ISC 2022 conference in Germany later this month and in government policy circles concerned with HPC’s geopolitical impact. The discussion is only heating up with a new article in the Financial Times reporting on China’s apparent 12-month-plus exascale lead over the US, Japan and Europe along with China’s plan to have 10 exascale systems in place by 2025. While most of the article in the FT restates much that’s already been [READ MORE…]

Featured Stories

Featured Resource

Rugged COTS Platform Takes On Fast-Changing Needs of Self-Driving Trucks

This white paper by Advantech, "Rugged COTS Platform Takes On Fast-Changing Needs of Self-Driving Trucks" discusses how the fast-changing needs of self-driving trucks are forcing compute platforms to evolve. Advantech and Crystal Group are teaming up to power that evolution based on AV trends, compute requirements, and a rugged COTS philosophy converging for breakthrough innovation in self-driving truck designs.

HPC Newsline

Industry Perspectives

  • HPC: Stop Scaling the Hard Way

    …today’s situation is clear: HPC is struggling with reliability at scale. Well over 10 years ago, Google proved that commodity hardware was both cheaper and more effective for hyperscale processing when controlled by software-defined systems, yet the HPC market persists with its old-school, hardware-based paradigm. Perhaps this is due to prevailing industry momentum or working within the collective comfort zone of established practices. Either way, hardware-centric approaches to storage resiliency need to go.

  • New, Open DPC++ Extensions Complement SYCL and C++

    In this guest article, our friends at Intel discuss how accelerated computing has diversified over the past several years given advances in CPU, GPU, FPGA, and AI technologies. This innovation drives the need for an open and cross-platform language that allows developers to realize the potential of new hardware, minimizes development cost and complexity, and maximizes reuse of their software investments.

RSS Featured from insideBIGDATA

  • The Next Data Revolution is Here – AI Will Understand What Isn’t Being Said
    In this special guest feature, Ran Margaliot, COO and VP R&D for Affogata, discusses how analyzing and sorting through unstructured data saves countless hours and recognizes patterns in seconds that even skilled data professionals may never uncover. That data “superpower” can lead to better products that adapt in real-time, responsive customer service,  and a sharing of insights across an organization magnifies […]

Editor’s Choice

  • Chip Geopolitics: If China Invades, Make Taiwan ‘Unwantable’ by Destroying TSMC, Military Paper Suggests

    US military planners are taking notice of a suggestion by two military scholars calling for the destruction of semiconductor foundry company Taiwan Semiconductor Manufacturing Co. (TSMC), whose fabs produce advanced microprocessors used in HPC and AI, in the event China invades the island nation A news story in today’ edition of Data Center Times cites the Nikkei Asia news service and a paper in the U.S. Army War College’s scholarly journal, Parameters, discussing the possibility of Taiwan adopting “’a scorched earth policy’ and wipe out its own semiconductor foundries in the wake of any Chinese invasion as a deterrent, U.S. [READ MORE…]

  • Exascale: Rumors Circulate HPC Community Regarding Frontier’s Status

    By now you may have expected a triumphant announcement from the U.S. Department of Energy that the Frontier supercomputer, slated to be installed by the end of 2021 as the first U.S. exascale-class system, has been stood up with all systems go. But as of now, DOE (whose Oak Ridge National Laboratory will house Frontier) is foregoing a “mission accomplished” announcement and instead has issued a somewhat formal statement about Frontier’s status. Left unaddressed are rumors circulating through the HPC community of difficulties encountered in the late stages of Frontier system integration and fine tuning. Here’s the official statement on [READ MORE…]

  • How Machine Learning Is Revolutionizing HPC Simulations

    Physics-based simulations, that staple of traditional HPC, may be evolving toward an emerging, AI-based technique that could radically accelerate simulation runs while cutting costs. Called “surrogate machine learning models,” the topic was a focal point in a keynote on Tuesday at the International Conference on Parallel Processing by Argonne National Lab’s Rick Stevens. Stevens, ANL’s associate laboratory director for computing, environment and life sciences, said early work in “surrogates,” as the technique is called, shows tens of thousands of times (and more) speed-ups and could “potentially replace simulations.” Surrogates can be looked at as an end-around to two big problems [READ MORE…]

  • Double-precision CPUs vs. Single-precision GPUs; HPL vs. HPL-AI HPC Benchmarks; Traditional vs. AI Supercomputers

    If you’ve wondered why GPUs are faster than CPUs, in part it’s because GPUs are asked to do less – or, to be more precise, to be less precise. Next question: So if GPUs are faster than CPUs, why aren’t GPUs  the mainstream, baseline processor used in HPC server clusters? Again, in part it gets back to precision. In many workload types, particularly traditional HPC workloads, GPUs aren’t precise enough. Final question: So if GPUs and AI are inextricably linked, particularly for training machine learning models, and if GPUs are less precise than CPUs, does that mean AI is imprecise? [READ MORE…]

  • 6,000 GPUs: Perlmutter to Deliver 4 Exaflops, Top Spot in AI Supercomputing

    The U.S. National Energy Research Scientific Computing Center today unveiled the Perlmutter HPC system, a beast of a machine powered by 6,159 Nvidia A100 GPUs and delivering 4 exaflops of mixed precision performance. Perlmutter is based on the HPE Cray Shasta platform, including Slingshot interconnect, a heterogeneous system with both GPU-accelerated and CPU-only nodes. The system is being installed in two phases – today’s unveiling is Phase 1, which includes the system’s GPU-accelerated nodes and scratch file system. Phase 2 will add CPU-only nodes later in 2021. “That makes Perlmutter the fastest system on the planet on the 16- and 32-bit [READ MORE…]

Sign up for our newsletter and get the latest big data news and analysis.
Daily
Weekly