On: Advances in semiconductors are feeding the AI boom

[HarHarVeryFunny]

We already have a 4 trillion transistor "GPU" in the Cerebras WSE-3 (wafer-scale engine), used in Cerebras' data centers.

https://www.youtube.com/watch?v=f4Dly8I8lMY

[DesiLurker → HarHarVeryFunny]

how many regular sized GPU (say 4080 or nvidia L4) dies can be cut out from a full-sized wafer? I suppose thats what OP means by reaching integration density of 1T GPU.

[moralestapia → DesiLurker]

I think the whole premise of TFA is flawed, as there already chips with way more than a trillion transistors (as GP points out).

Arguing about what is the size limit to consider something a GPU or not is a bit like bikeshedding.

As to why wouldn't a supercomputer be considered for this? Because it's not a single chip.

[denimnerd42 → DesiLurker]

here's some discussion about yields for H100 per wafer. I'd assume a 4080 is smaller? regardless, the calculator is supplied.

https://news.ycombinator.com/item?id=38588876

[ksec → DesiLurker]

At close to reticle limit of around ~810mm2, you could fit around 65 chips.

[IshKebab → DesiLurker]

It's somewhere around 20 if you go as large as possible IIRC.

[IshKebab → HarHarVeryFunny]

Yeah that doesn't really count. It's the equivalent to like 20 GPUs and costs 200x as much.

[HarHarVeryFunny → IshKebab]

Well, yeah, that's what a few trillion transistors look like with today's tech. No doubt it will get smaller/cheaper in the future (although EUV is expensive, so maybe prices won't keep dropping as much as in the past). The point is that even with today's tech a (4) trillion transistor chip can already be built.

[edward28 → IshKebab]

It's meant to compete with nvidia's DGX systems with 8 GPUs per node.

[IshKebab → edward28]

Yes exactly. It's not comparable to one GPU.