HPC Guru

Other than HPE, who wants to build OLCF-6 and NERSC-10?

Can #HPC #Cloud providers save DOE from a single vendor procurement?

RFP technical requirements are out for two of the DOE’s next #exascale-class #supercomputers

https://nextplatform.com/2023/10/02/the-first-peeks-at-the-doe-post-exascale-supercomputers/…

#HPC #AI

Oct 3, 2023 at 5:04amWeb
Show threadHPC GuruOct 3, 2023

👏👏Notable quote by TPM:

Intel has had quite enough of being a prime contractor for #supercomputers, and CEO Pat Gelsinger has come to his senses & stopped talking about reaching #Zettascale by 2027.

As far as we can tell, that mike drop broke the mike.

And the Raj.

#HPC

Show threadHPC GuruOct 3, 2023

TPM's view on other on-prem #HPC vendors for these #Exascale #supercomputers:

o Nvidia is making too much $$ on #AI to care

o Dell: Michael Dell doesn’t like to lose money - TACC
seems to be enough for its #HPC

o No way that Atos or Fujitsu can sell into US government labs

Show threadHPC GuruOct 3, 2023

It may be time for #HPC #cloud vendors to join the bid - AWS, Azure, Google Cloud, Oracle Cloud

They are better at dealing with the facilities constraints (power, cooling, etc.) and have the capital needed to play at this level

Azure has already won at the UK Met Office

Show threadJanne MorenOct 3, 2023
@HPC_Guru
Idly wondering what would happen if HPE/Cray decided that with total lifetime demand of 2-4 machines or so, the development cost for post exascale wasn't worth it at any price, and also decided to bow out.
Show threadJanne MorenOct 3, 2023
@HPC_Guru
It's not just that the machines nowadays are eye-wateringly expensive. It's not even that there are very few workloads that can take full advantage. I suspect that ncreasingly the tech development needed for such massive machines isn't all that relevant for the much smaller machines they can actually make money on.
Show threadHPC GuruOct 3, 2023

@jannem The same argument was made when we had the first petascale systems.

Re-cycling one of my past quotes here:

The most exciting thing about Exascale is affordable Petascale.

Show threadJanne MorenOct 3, 2023

@HPC_Guru
I hope you're right but I do wonder. TOFU is a good example: it is an excellent interconnect - above 15k nodes. Below that other tech is better.

But nodes aren't really getting cheaper or less power hungry. The market for 15k+ node machines will remain very small. The cost of TOFU development will never really trickle down to benefit "normal" size machines to a significant degree.

Show threadHPC GuruOct 3, 2023

@jannem

1. HPE/Cray leverages the same tech & product for non-Exascale systems. Look at how many Shasta supercomputers were sold by HPE to non-Exascale customers.

2. IMHO, it is an unlikely scenario. In case it does happen, DOE could subsidize the development cost. It has done this before.

3. Or collaborate with cloud vendors with deep pockets :-)

Show threadBrandon BiggsOct 4, 2023
@HPC_Guru I saw this and had to come back. Zetascale by 2025... https://www.eenewseurope.com/en/tachyum-to-build-50-exaflop-supercomputer/
Tachyum to build 50 exaFLOP supercomputer

Tachyum is to build a 50 exaFLOP supercomputer based on its 5nm Prodigy Universal Processor chip for a US customer.

eeNews Europe
Show threadHPC GuruOct 4, 2023

@brandon

Sigh.

I saw this too.

PRs are easy, actual products that deliver the claimed performance is much more difficult.

I wish folks would stop giving coverage to Tachyum's increasingly ridiculous claims.

I will gladly post about them when they move beyond vaporware to actual benchmarked silicon

#HPC