Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Jeff Dean responds to EDA industry about AlphaChip

twitter.com

Post reply on HN
Print view View original

51–60 of 221 posts

Re: Jeff Dean responds to EDA industry about AlphaChip

#51

Post by phonon »

griomnib wrote: post #28
jeffbee wrote: post #27

Earlier quoted context omitted.

We're actually talking about the difference between Cheng using 8 GPUs and 2 CPUs while Google used 16 GPUs and 40 CPUs. These are under-your-desk levels of resources. Cheng et al authors are all affiliated with UCSD which owns the Expanse supercomputer which is orders of magnitude larger than what you would need to reproduce the original work. Cheng et al does not explain why they used fewer resources.

That’s a fair complaint then.

No it's not. They ran it longer instead.

Re: Jeff Dean responds to EDA industry about AlphaChip

#53

Post by bushbaba »

wholehog wrote: post #50
vighneshiyer wrote: post #38

I have published an addendum to an article I wrote about AlphaChip ( https://vighneshiyer.com/misc/ml-for-placement/ ) at the very bottom that addresses this rebuttal from Google and the AlphaChip algorithm in general. In short, I think the Nature authors have made some reasonable criticisms regarding the training methodology employed by the ISPD authors, but the extreme compute cost and runtime of AlphaChip still ma…

We're talking 16 GPUs for ~6 hrs for inference, and 48 hrs for pre-training. This is not an exorbitant amount of compute. A GPU costs $1-2/hr on the cloud market. So, ~$100-200 for inference, and ~$800-1600 for pre-training, which amortizes across chips. Cloud prices are an upper bound -- most CS labs will have way more than this available on premises. In an industry context, these costs are completely dwarfed by the…

h100 GPU instances are multiple orders of magnitude more expensive.

Re: Jeff Dean responds to EDA industry about AlphaChip

#54

Post by radq »

bushbaba wrote: post #53
wholehog wrote: post #50

Earlier quoted context omitted.

We're talking 16 GPUs for ~6 hrs for inference, and 48 hrs for pre-training. This is not an exorbitant amount of compute. A GPU costs $1-2/hr on the cloud market. So, ~$100-200 for inference, and ~$800-1600 for pre-training, which amortizes across chips. Cloud prices are an upper bound -- most CS labs will have way more than this available on premises. In an industry context, these costs are completely dwarfed by the…

h100 GPU instances are multiple orders of magnitude more expensive.

Not true, H100s cost $2-3/GPU/hr on the open market.

Re: Jeff Dean responds to EDA industry about AlphaChip

#55

Post by asveikau »

AtlasBarfed wrote: post #41

How the hell would you verify an AI-generated silicon design? Like, for a CPU, you want to be sure it behaves properly for the given inputs. Anyone remember that floating point error in, was it Pentium IIs or Pentium IIIs? I mean, I guess if the chip is designed for AI, and AIs are inherently nonguaranteed output/responses, then the AI chip design being nonguaranteed isn't any difference in nonguarantees. Unless it i…

The famous FPU issue that I can think of was the original Pentium.

Re: Jeff Dean responds to EDA industry about AlphaChip

#56

Post by lobochrome »

bsder wrote: post #4

The fact that the EDA companies are garbage in no way mitigates the fact that Google continues to peddle unsubstantiated snake oil. This is easy to debunk from the Google side: release a tool. If you don't want to release a tool, then it's unsubstantiated and you don't get to publish. Simple. That having been said: 1) None of these "AI" tools have yet demonstrated the ability to classify "This is datapath", "This is…

Agreed, in particular on #2

Given infinite time and compute - maybe the approach is significantly better. But that’s just not practical. So unless you see dramatic shifts - no one is going to throw away proven results on your new approach because of the TTM penalty if it goes wrong.

The EDA industry is (has to be) ultra conservative.

Re: Jeff Dean responds to EDA industry about AlphaChip

#57

Post by raverbashing »

bsder wrote: post #4

The fact that the EDA companies are garbage in no way mitigates the fact that Google continues to peddle unsubstantiated snake oil. This is easy to debunk from the Google side: release a tool. If you don't want to release a tool, then it's unsubstantiated and you don't get to publish. Simple. That having been said: 1) None of these "AI" tools have yet demonstrated the ability to classify "This is datapath", "This is…

Honestly this does not compute

> None of these "AI" tools have yet demonstrated the ability to classify "This is datapath", "This is array logic", "This is random logic".

Sounds like a good objective, one that could be added to training parameters. Or maybe it isn't needed (AI can 'understand' some concepts without explicitly tagging)

> If I have the compute power to run EDA tools with a couple of different random seeds, at least one run will likely be a couple percentage points better.

Then do it?! How long does it actually take to run? I know EDA tools creators are bad at some kinds of code optimization (and yes, it's hard) but let's say for a company like Intel, if it takes 10 days to rerun a chip to get 1% better, that sounds like a worthy tradeoff.

> I put this snake oil in the same category as "financial advice"--if it worked, they wouldn't be sharing it and would simply be printing money by taking advantage of it.

Yeah I don't think you understood the problem here. Good financial advice is about balancing risks and returns.

Re: Jeff Dean responds to EDA industry about AlphaChip

#60

Post by joatmon-snoo »

bayarearefugee wrote: post #10
danpalmer wrote: post #6

Earlier quoted context omitted.

> But saying "they couldn't replicate it because they're idiots, therefore it's replicable" is not a rebuttal, just bullying That's not an argument made in the linked tweet. His claim is "they couldn't replicate it because they didn't follow the steps", which seems like a very reasonable claim, regardless of the motivation behind making it.

At the end of the day my question is simply why does anyone care about the drama over this one way or another? Either the research is as much of a breakthrough as is claimed and Google is about to pull way ahead of all these other "idiots" who can't replicate their method even when it is described to them in detail, or the research is flawed and overblown and not as effective as claimed. This seems like exactly the s…

> This seems like exactly the sort of question the market will quickly decide over the next couple of years and not worth arguing over.

Discussions like this are _how_ the market decides whether or not this achievement is real or not.

Post reply on HN