Live data from Hacker News

Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

servethehome.com

21–30 of 188 posts

Re: Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

#21
post #6

About time. NVIDIA needs some serious competition.

AMD is doing several billion in ai processor sales already and the new chip is selling as fast as they can make them. At least with AMD, a customer can actually get them now as opposed to the nearly 1 year lead time from nVidia.

Confirmed. Buying them up as fast as I can. =)

Re: Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

#22
post #5

So, where can I use instances of Gaudi 3 and what is the hourly price for these instances?

This is something I'd like to offer via my business (Hot Aisle) at some point in the near future. Right now, we are just getting started and focused on MI300x, but the long term goal is to offer any type of high end compute that people are willing to rent.

Re: Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

#23
post #4

The "in the wild" part of the title is misleading. These chips are being presented in a very controlled environment. An interesting aspect of Intel's design is they use Ethernet for connectivity. If they can get the performance on par with NVLink, that by itself could be a win because everybody knows how to manage Ethernet. Very few people know how to manage an NVLink network. To be clear, this is data center hardwar…

> An interesting aspect of Intel's design is they use Ethernet for connectivity.

Interestingly, tenstorrent is doing something similar with their wormhole cards.

I'm not convinced yet that it is the right way to go. If the switching fabric on the card fails, you lose the whole card. Keeping it separated out is a bit less risky, at the cost of some speed.

I'm more partial to composable fabrics, but they aren't ready yet for PCIe5 and we have PCIe6 just around the corner next year.

Re: Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

#24

Earlier quoted context omitted.

Very few people actually know how to provision and manage a lossless Ethernet fabric and I’d wager someone who had literally never touched infiniband would have an easier time accomplishing it from zero with IB than with Ethernet on real vendor gear. Ethernet has so, so many gotchas. Maybe if it was a layer 3 only network it would work. Maybe.

I'm guessing it's RDMA over ethernet too which often has a lot of gotchas depending on the exact hardware being used.

Ironically enough, since NVIDIA bought Mellanox, it's likely that the best documented route to get ROCE v2 going is with switches purchased from NVIDIA...

Edit: and yes, it's RDMA over ethernet https://docs.habana.ai/en/latest/Gaudi_Overview/Gaudi_Archit...

Re: Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

#25
post #6

About time. NVIDIA needs some serious competition.

The only meaningful hardware competition, meaning lower prices, will come from Chinese designed, Chinese manufactured parts. This is still a long ways out. Is it inevitable? I think so. Before 2019 there wasn't an opportunity, now there is. For software, Chinese universities, Alibaba, Tencent and Bytedace are already releasing models, training code and in rare cases datasets that are competitive with private offering…

How much time for that? I wouldn't expect nothing in industrial volumes for the next years, maybe 2028? who knows?

But, anyway, we will prohibited from buying it, probably. We still can't buy Cuban cigars.

Re: Intel Gaudi 3 the New 128GB HBM2e AI Chip in the Wild

#26
post #4

The "in the wild" part of the title is misleading. These chips are being presented in a very controlled environment. An interesting aspect of Intel's design is they use Ethernet for connectivity. If they can get the performance on par with NVLink, that by itself could be a win because everybody knows how to manage Ethernet. Very few people know how to manage an NVLink network. To be clear, this is data center hardwar…

> An interesting aspect of Intel's design is they use Ethernet for connectivity. Interestingly, tenstorrent is doing something similar with their wormhole cards. I'm not convinced yet that it is the right way to go. If the switching fabric on the card fails, you lose the whole card. Keeping it separated out is a bit less risky, at the cost of some speed. I'm more partial to composable fabrics, but they aren't ready y…

You want each ASIC to have 24 external NICs (so 192 NICs for a server?) with all the cabling/backplanes that would require?
Post reply on HN