At the the SIGGRAPH conference this morning in Los Angeles, NVIDIA made several generative AI-related announcements, including a partnership with Hugging Face intended to broaden access to generative AI supercomputing (NVIDIA’s DGX cloud hardware) for developers building large language models (LLMs) and other AI applications on the Hugging Face platform. The companies said the combination […]
NVIDIA at SIGGRAPH: DGX Integration with Hugging Face for LLM Training; Announcement of AI Workbench
August 8, 2023 by
HPC and AI Workloads Drive Storage System Design
August 7, 2023 by
Many organizations are tied to outdated storage systems that cannot meet HPC and AI workload needs. Designing high‑throughput, highly scalable HPC storage systems require expert planning and configuration. The Dell Validated Designs for HPC Storage solution offers a way to quickly upgrade antiquated storage….
McKinsey on the Future of Compute: The Rise of Domain-Specific Architectures
August 2, 2023 by
There’s more to the rise in HPC and AI of domain-specific architectures (DSAs), starting with GPUs, than just the superior throughput they can deliver. Yes, the deceleration of Moore’s Law and Dennard scaling are the primary reasons for the CPU’s decline in dominance. But other factors are playing a strong, enabling role for DSAs. Consulting […]
HPC News Bytes Podcast for 20230731: AWS’s GPU-Laden P5 Instance; TACC’s Stampede-3; Micron’s 24GB HBM3; Cineca’s ‘White Space’ Infrastructure
July 31, 2023 by
As August beckons let’s take a quick (4:14) look at the highlights of the latest news in HPC, AI, quantum and other advanced technologies. This week, Shahin and Doug discuss: AWS EC2 P5 cloud instance with Nvidia H100 and AMD Milan; TACC’s Stampede-3 mini Intel Aurora with Cornelis Network’s Omni-Path Express fabric; Micron 8-high 24GB HBM3; Cineca’s “white space” supercomputing infrastructure strategy.
Report: NVIDIA in Talks to Become Arm Anchor Investor, Intel May Join in
July 17, 2023 by
UK chip design company Arm is in negotiations with NVIDIA to be an anchor investor in Arm’s initial public offering, The Financial Times reported last week. The news comes nearly 18 months after NVIDIA ended its attempted acquisition of Arm from Japanese investment company SoftBank due to regulatory hurdles in several countries and Europe. The […]
GigaIO Introduces 32 GPU Single-Node Supercomputer
July 17, 2023 by
Carlsbad, California, July 13, 2023 – GigaIO, provider of workload-defined infrastructure for AI and technical computing, recently announced that it successfully configured 32 AMD Instinct MI210 accelerators to a single-node server utilizing the company’s FabreX PCIe memory fabric. Available today, the 32-GPU engineered solution, called SuperNODE, is designed to offer a simplified system capable of […]
NVIDIA Unveils GH200 Grace Hopper Superchip Platform with HBM3e Processor
July 8, 2023 by
NVIDIA today at the SIGGRAPH conference announced the NVIDIA GH200 Grace Hopper platform — based on a new Grace Hopper Superchip with the first HBM3e processor, according to NVIDIA — built for accelerated computing and generative AI. Built for large language models, recommender systems and vector databases, the new platform will be available in a range of configurations, according to the company. The dual configuration, which delivers up to 3.5x more memory capacity and 3x more bandwidth than the current generation offering, comprises a single server with 144 Arm Neoverse cores, eight petaflops of AI performance and 282GB of the latest HBM3e memory technology.
@HPCpodcast: An Architecture Update from RISC-V International CTO Mark Himelstein
July 6, 2023 by
Mark Himelstein, chief technology officer at RISC-V International, joins us to discuss the latest developments with the RISC-V instruction set architecture and its growing community and footprint. Topics include: HPC use cases from sensors to supercomputer, achieving customization without loss of compatibility, AI and its impact on chips and systems, and the question on everyone’s mind: when will we see RISC-V in servers and supercomputers? Himelstein also looks at RISC-V’s design wins, including EuroHPC’s backing of R&D to develop HPC hardware and software based on RISC-V. You may also be interested in Shahin’s conversation with Mark in August 2020 to hear how things have evolved since then.
Revolutionizing the Electronic Design Industry with Ansys and AWS
June 29, 2023 by
The electronics industry operates in a highly competitive landscape, where companies are constantly striving to launch products faster while meeting evolving consumer demands. However, this quest for speed and innovation comes with challenges. Electronics engineers often encounter complex designs, tight schedules….
MLCommons: MLPerf Results Show AI Performance Gains
June 27, 2023 by
Today ML Commons announced new results from two industry-standard MLPerf benchmark suites: Training v3.0, which measures the performance of training machine learning models, and Tiny v1.1, which measures how quickly a trained neural network can process new data for extremely low-power devices in the smallest form factors. To view the results and to find additional […]
