Search Results for: gpu

HPC News Bytes 20231023: Flared Gas GPU Cloud, IBM AI Chip, TSMC Q3 Earnings, Aurora Install; AI and More AI

Our fleet-footed (5:20) run through recent HPC news looks at: HPE Cray supercomputers  to be used at flared gas generative AI data centers; IBM announces NorthPole AI chip prototype, TSMC’s down Q3 earnings; new trends in advanced AI, including detection of brain waves as an AI input; an Aurora installation update….

HPC News Bytes 20231016: China and 300eFLOPS, Samsung’s 3nm Order, Exascale Day, Women and Coding, the Coming GPU Battle

A happy mid-October morning to you! Today’s HPC News Bytes podcast offers a rapid (5:08) romp through recent HPC developments, including: China’s goal of 300 exaflops in 2025; Samsung’s 3nm chip win; Exascale Day; fewer women computer scientists since 1984; the GPU competition between NVIDIA, AMD and Intel….

Federated GPU Infrastructure for AI Workflows

[Sponsored Guest Article] With the explosion of use cases such as Generative AI and ML Ops driving tremendous demand for the most advanced GPUs and accelerated computing platforms, there’s never been a better time to explore the “as-a-service” model to help get started quickly.  What could take months of shipping delays and massive CapEx investments can be yours on demand….

AMD MI300 Accelerators Expected to Bring Choice to GPU Market

[Sponsored Guest Article]  If you agree that generative AI signifies a new chapter in IT, then you may also agree there’s a major storm gathering among GPU accelerator chip vendors vying for position in the GenAI market. It’s a competition with the potential to roil not only the microprocessor sector….

HPC News Bytes 20231002: Lisa Su on AMD-NVIDIA GPU Competition; ASML EUV at Intel Fab in Ireland; AI Job Elimination; SC23 Coming up

A happy October morning to you! Our lineup of quick (4:36) commentary on recent HPC news includes: AMD’s Lisa Su on the AMD-NVIDIA GPU competition; ASML EUV at Intel-4 fab in Ireland starts volume production; AI’s job elimination impact; SC23 is coming Nov 12-17….

HPC News Bytes 20230821: Intel Ends Tower Bid; Hot Chips Conference; GPU Demand; Samsung’s Texas 4nm Fab

Good Monday morning! Here’s a quick summation of recent HPC news: Intel kills Tower Semi deal; Hot Chips preview; GPU shortage as generative AI heats up; Samsung’s Texas 4nm chip fab….

Exxact Corporation Systems to Feature NVIDIA Ada Generation GPUs

Fremont, CA, August 8, 2023 — Exxact Corporation today announced it will feature new NVIDIA RTX professional GPUs in its configurable workstations, servers, and clusters to offer computational performance edge in real-time rendering, graphics, and AI, as well as accelerated simulation in engineering, scientific, and molecular research. These integrations include four new additions to the […]

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

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.

NVIDIA L4 GPU Breakthrough Data Center Universal Accelerator for Efficient Video, AI, and Graphics

Breakthrough Data Center Universal Accelerator for Efficient Video, AI, and Graphics The NVIDIA Ada Lovelace architecture L4 Tensor Core GPU is NVIDIA’s most compact data center accelerator for use in mainstream PCIe-based servers and is an ideal means of adding GPU acceleration to CPU-based systems. Delivering universal acceleration and energy efficiency for video, AI, virtual […]

GigaIO Introduces 32 GPU Single-Node Supercomputer

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 […]