@HPCpodcast: Intel Shipping Aurora Blades; Rocky Linux vs. CentOS; Tesla’s ‘Dojo’ AI Supercomputer

Print Friendly, PDF & Email

In this edition of the @HPCpodcast, Shahin and Doug kick things off on the news from Intel Innovation Day that  the company is shipping Sapphire Rapids CPU / Ponte Vecchio GPU-powered blades to the Argonne Leadership Computing Facility for use in the lab’s Aurora exascale supercomputer, due for delivery by late 2022 or early 2023. It’s encouraging news, but still, we can’t but take into account Intel’s problems delivering systems named Aurora (this is the second).

Our overall sense is that Intel made a good impression at its well-crafted and executed Innovation Day, with a whole host of announcements, broken down here by Shahin. We also discuss open source software and the big part it plays in the HPC/AI puzzle, along with the ongoing Linux operating system wars – including the emergence of Rocky Linux after Red Hat’s December 2020 announcement it would no longer support CentOS.

We also share views on Tesla AI day and that company’s home-grown AI chip and the associated “Dojo” HPC system.

You can find our podcasts at insideHPC’s @HPCpodcast page, on Twitter and at the OrionX.net blog. Here’s the RSS feed.