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

How AlphaChip transformed computer chip design

deepmind.google

Post reply on HN
Print view View original

61–70 of 215 posts

Re: How AlphaChip transformed computer chip design

#61

Post by nemonemo »

vighneshiyer wrote: post #41

This work from Google (original Nature paper: https://www.nature.com/articles/s41586-021-03544-w ) has been credibly criticized by several researchers in the EDA CAD discipline. These papers are of interest: - A rebuttal by a researcher within Google who wrote this at the same time as the "AlphaChip" work was going on ("Stronger Baselines for Evaluating Deep Reinforcement Learning in Chip Placement"): http://47.190.8…

What is your opinion of the addendum? I think the addendum and the pre-trained checkpoint are the substance of the announcement, and it is surprising to see little mention of those here.

Re: How AlphaChip transformed computer chip design

#62

Post by amelius »

tdullien wrote: post #58
amelius wrote: post #25

Earlier quoted context omitted.

Exactly what I was thinking. Also: when is this coming to KiCad? :) PS: It would also be nice to apply a similar algorithm to graph drawing (e.g. trying to optimize for human readability instead of electrical performance).

The issue is that in order to optimize for human readability you'll need a huge number of human evaluations of graphs?

Maybe start with minimization of some metric based on number of edge crossings, edge lengths and edge bends?

Re: How AlphaChip transformed computer chip design

#66

Post by hulitu »

jeffbee wrote: post #11
yeahwhatever10 wrote: post #9

Earlier quoted context omitted.

Floorplanning algorithms and solvers already exist https://limsk.ece.gatech.edu/course/ece6133/slides/floorplan...

The original paper from DeepMind evaluates what they are now calling AlphaChip versus existing optimizers, including simulated annealing. They conclude that AlphaChip outperforms them with much less compute and real time. https://www.cl.cam.ac.uk/~ey204/teaching/ACS/R244_2021_2022/...

> They conclude that AlphaChip outperforms them with much less compute and real time.

Of course they do. I'm waiting for their products.

Re: How AlphaChip transformed computer chip design

#67

Post by jebarker »

abc-1 wrote: post #39

Why aren’t they using this technique to design better transformer architectures or completely novel machine learning architectures in general? Are plain or mostly plain transformers really peak? I find that hard to believe.

Because chip placement and the design of neural network architectures are entirely different problems, so this solution won't magically transfer from one to the other.

Re: How AlphaChip transformed computer chip design

#69

Post by thomasahle »

yeahwhatever10 wrote: post #5

Why do they keep saying "superhuman"? Algorithms are used for these tasks, humans aren't laying out trillions of transistors by hand.

Believe it or not, but there was a time where algorithms were worse than humans at layout out transistors. In particular at the higher level design decisions.
Post reply on HN