Quantum #74

This week’s HPC News was written largely at 1300m at Les Gets. By the time you read this I’ll probably be, in equal parts, struggling to keep up with my daughters and embarrassing myself on a downhill mountain bike or VTT in local parlance. The summer equivalent of skiing. Who knew!

Whilst I made some good progress on the white paper that I’m desperately trying to get finished and in front of you all, I still haven’t completed the first draft. Its 20 odd pages and about 3500 words now though so perhaps I should just wrap it up! The current section on the optimisation differences between end of day and intraday risk has been a lot of fun. And I haven’t even started writing the section on power usage analysis yet!

ICYMI the next HPC Club will take place in Bristol where we’ve somehow managed to persuade Simon McIntosh-Smith to talk to us about building out Isambard-AI. 24^th September. Be there or be a homogenous CPU based x86 supercomputer. IYKYK 😁

HPC Club: Bristol Edition - HPC CLUB

HPC Club event on the future of HPC schedulers. Join us for an evening of discussion and networking with industry experts. 24 Sept 2025 @ 17:00, The Forge, Bristol, UK.

HPC CLUB

Everything else in the world of HPC this week that caught my eye is below

The rest of your HPC news is linked in the comments when I get a chance and manage to catch up with my daughters long enough to take a break and post the comment.

In The News

Updates from the big three clouds on all things HPC.

HPC Cloud Updates WE 24 Aug 2025

Updates to AWS, Azure & GCP in the last week relevant for HPC practitioners. New Intel VM family on AWS and how to check your GPU VMs actually work before doing any real work with them.

Flux by HMx LabsHamza

Managing compute across multiple DCs (or cloud regions), especially as it relates to having the right data in the right DC is hard. What if it didn’t matter anymore? NVIDIA seems to think that’s another feather they can add to their cap.

The AI Superfactory: NVIDIA’s Multi-Data Center ‘Scale Across’ Ethernet

Tying multiple data centers together into an integrated whole is a hot topic in data center circles. The goal is to achieve performance beyond what a - Read more from Inside HPC & AI News.

Inside HPC & AI News | High-Performance Computing & Artificial IntelligenceDoug Black

NVIDIA also have made their way into the next generation Fugaku, nick named Godzilla (love it, the name that is).

Nvidia Tapped To Accelerate RIKEN’s FugakuNext Supercomputer

It has been clear for some time that Japan wants to have a certain amount of economic and technical independence when it comes to cloud computing in the

The Next PlatformTimothy Prickett Morgan

From HMx Labs

Full details of the next HPC Club are now available as are tickets to reserve your spot to hear Simon McIntosh-Smith talk about the UK’s most powerful supercomputer Isambard-AI

HPC Club: Isambard-AI

HPC Club @ The Forge in Bristol, about Isambard-AI, the UK’s fastest supercomputer from the man himself, Simon McIntosh-Smith.

Flux by HMx LabsHamza

I’d really like to hear what problems are plaguing your HPC today. Not what you’re worried about coming down the line, but right now

HPC’s Biggest Problem Today?

Let’s talk about what’s frustrating you today instead of what’s on the horizon for once.

Flux by HMx LabsHamza

Know someone else who might like to read this newsletter? Forward this on to them or even better, ask them to sign up here: https://cloudhpc.news