Google’s New AI-Focused ‘A3’ Supercomputer Has 26,000 GPUs

May 10, 2023

Cloud providers are building armies of GPUs to provide more AI firepower. Google is joining the gang with a new supercomputer that has almost 2.5 times the number of GPUs than the world’s third-fastest supercomputer called LUMI. Google announced an AI supercomputer with 26,000 GPUs at its developer conference on Wednesday. Read more…

Groq Designs Chip that Hands Over Controls to Software

August 25, 2022

Groq has deconstructed the conventional CPU, and designed its chip in which software takes over control of the chip. The Groq Tensor Streaming Processor Architecture follows a growing trend of software controlling system functions, which has happened in autonomous cars, networking and other hardware. The architecture hands over hardware controls of the chip to the compiler. The chip has integrated... Read more…

Video: Sneak Preview of the AI Hardware Summit

August 19, 2022

Next month the AI Hardware Summit returns to the Bay Area, bringing AI technologists and end users together to share ideas and get up to speed on all the latest AI hardware developments. The event – which takes place September 13-15, 2022, at the Santa Clara Marriott, Calif. – will be co-located with the Edge AI Summit. Both events are organized by... Read more…

AI Silicon Startup Graphcore Launches Channel Partner Program

September 23, 2020

AI compute platform vendor Graphcore has launched its first formal global channel partner program to promote and boost the sales of its AI processors and blade computing products. The formalized, all-new Graphcore Elite Partner Program follows the company’s past history of working with several... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow

Whitepaper

Penguin Computing Scyld Cloud Central™: A New Cloud-First Approach to HPC and AI Workloads

Making the Most of Today’s Cloud-First Approach to Running HPC and AI Workloads With Penguin Scyld Cloud Central™

Bursting to cloud has long been used to complement on-premises HPC capacity to meet variable compute demands. But in today’s age of cloud, many workloads start on the cloud with little IT or corporate oversight. What is needed is a way to operationalize the use of these cloud resources so that users get the compute power they need when they need it, but with constraints that take costs and the efficient use of existing compute power into account. Download this special report to learn more about this topic.

Download Now

Sponsored by Penguin Solutions

Whitepaper

QCT POD- An Adaptive Converged Platform for HPC and AI

Data center infrastructure running AI and HPC workloads requires powerful microprocessor chips and the use of CPUs, GPUs, and acceleration chips to carry out compute intensive tasks. AI and HPC processing generate excessive heat which results in higher data center power consumption and additional data center costs.

Data centers traditionally use air cooling solutions including heatsinks and fans that may not be able to reduce energy consumption while maintaining infrastructure performance for AI and HPC workloads. Liquid cooled systems will be increasingly replacing air cooled solutions for data centers running HPC and AI workloads to meet heat and performance needs.

QCT worked with Intel to develop the QCT QoolRack, a rack-level direct-to-chip cooling solution which meets data center needs with impressive cooling power savings per rack over air cooled solutions, and reduces data centers’ carbon footprint with QCT QoolRack smart management.

Download Now

Sponsored by QCT

Advanced Scale Career Development & Workforce Enhancement Center

Featured Advanced Scale Jobs:

SUBSCRIBE for monthly job listings and articles on HPC careers.

HPCwire Resource Library

HPCwire Product Showcase

Subscribe to the Monthly
Technology Product Showcase:

HPCwire