Hacker News Reader

Comment by Lramseyer | Hacker News Reader

Production grade CPU design is more than just the RTL (the source code.) To achieve the performance numbers that these companies get, you have to do a ton of optimization in your physical design to achieve the power/performance/area (PPA) metrics that make these products competitive. LLMs are not suitable for that kind of work.

There are people working on PPA optimization and trying to shake up how things are done, just not with LLMs.

View on HN

That's exactly where LLMs can shine, because design space exploration requires tedious work and endless simulations.

Yes, but that's only the first part of it. The LLM can create 100 good, working, and verified designs. You still need to lay them out and optimize the physical designs. That kind of optimization is not something language models are good at. You need something fundamentally different.

> LLMs are not suitable for that kind of work.

I wonder why not or you meant not suitable yet?

This is just speculation on my part, but LLMs work best when they get immediate, verifiable feedback on their task, and the kind of physical optimizations they mean might not give that to LLMs.

Also a speculation but I'm almost certain that physical optimizations are first done through simulators running on a computer.

Yes, they are, but the most important subtasks of designing a CPU are not physics related. They are picking the right parameters for things like: how wide do I make this bus, how many registers do I put in the register file, how large do I make this cache, how deep do I make this pipeline, etc., etc. To find optimal parameters requires a lot of simulations, and humans do this, but LLMs could do them just as well and maybe better because they excel at tedious work.

The right way is to throw LLMs at building tools that reframe the problem into a shape LLMs are good at navigating, and then have LLMs use those tools to solve it.

Something that I think is fascinating, though, is that labs are no longer beholden to the limitations of commercial design software. Want to replace your simulator and optimizer with a fully custom verifiable stack of Lean proofs of optimality and correctness? Just throw your unlimited token budget at it.

I don't work in the business, but my understanding was that even with these companies' budgets, it's still too expensive to do any kind of verified performance optimality.

And I think correctness for anything near the size of a CPU is off the table.

That's the sort of the AI (including non-LLM AI) is really good at - even more so than the actual design work.

Reply on news.ycombinator.com