Live data from Hacker News

AMD's Instinct MI455X: Aiming for the Sun

chipsandcheese.com

1–10 of 38 posts

Re: AMD's Instinct MI455X: Aiming for the Sun

#2
> The basic GCN microarchitecture underpinned every single one of AMD’s compute accelerators for nearly 15 years [...]. With CDNA5 AMD has moved over to a microarchitecture that is based on the RDNA series putting a bookend to the long-lived line that was the GCN microarchitecture.

So everything is new again. Will this be another "buy now, have ROCM work in 3 maybe years if you are lucky"?

Re: AMD's Instinct MI455X: Aiming for the Sun

#3

> The basic GCN microarchitecture underpinned every single one of AMD’s compute accelerators for nearly 15 years [...]. With CDNA5 AMD has moved over to a microarchitecture that is based on the RDNA series putting a bookend to the long-lived line that was the GCN microarchitecture. So everything is new again. Will this be another "buy now, have ROCM work in 3 maybe years if you are lucky"?

Arguably this might reduce it, because now ROCm won't be prioritised for the GCN-based systems?

Re: AMD's Instinct MI455X: Aiming for the Sun

#6
post #5

432 GB of RAM per chip. Tens of terabytes per rack. Clients queuing up to buy them. RAM prices are not coming down any time soon.

Did anyone think RAM prices were coming down soon?

Of course. Wishful thinking is a true staple of human intelligence.

Re: AMD's Instinct MI455X: Aiming for the Sun

#7
It's mind blowing seeing these multi exaflop single rack systems.

The world's first exaflop supercomputer was Frontier. It was launched only 4 years ago in 2022.

It's not a fair comparison of course. FP4 in Helios barely qualifies as floating point. Frontier was proper fp64, 16 times the bit width and probably 256x as many transistors.

All the same just wow. Much compute.

Re: AMD's Instinct MI455X: Aiming for the Sun

#10

432 GB of RAM per chip. Tens of terabytes per rack. Clients queuing up to buy them. RAM prices are not coming down any time soon.

but you have to rewrite all your software to ROCm. And ROCm, to this day, still sucks.

ZLUDA basically crash on high memory demand, and only accounted for ~70% of CUDA API coverage (and it is still buggy).

But hey, at least it does run on Rust-CUDA. I'm one of the few who ported it and fixed a few bugs on ZLUDA. I used it to run a simple SHA256 kernel and it ran sure, but I gave it up because of those fundamental problems on AMD GPUs. You can't believe how messy ROCm is. I wonder if Vulkan compute kernel using SPIR-V would be a better choice.

Post reply on HN