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

Nvidia R&D chief on how AI is improving chip design

hpcwire.com

Post reply on HN
Print view View original

51–60 of 81 posts

Re: Nvidia R&D chief on how AI is improving chip design

#51

Post by q-big »

marginalia_nu wrote: post #44
maxwells-daemon wrote: post #36

I work on this team! (Specifically: applied deep learning research, chip design). It's a shame to see so many people dismissing this work as marketing. I see lots of clever people working hard on really novel and interesting stuff, and I really do think that ML has real potential to customize a design much more "deeply" than traditional automation tools.

This is directed at AI marketing in general: "AI" has been used to market so much nonsense it's probably becoming a problem communicating actual interesting uses of AI. I very much get a dot com vibe off it, like nobody on the team knows how it works but we're sure we're gonna be rich somehow! In my head, I've begun substituting AI with "wizards" when I read it. It's very much the sort of problems crypto is having. S…

> "AI" has been used to market so much nonsense it's probably becoming a problem communicating actual interesting uses of AI.

On the other hand: if the people who do serious work in this area don't call out this nonsense, they must accept that their (serious) work becomes devalued.

> It's very much the sort of problems crypto is having. So many grifters actual interesting uses of the technology are very hard to identify and take seriously.

Here, the same holds.

Re: Nvidia R&D chief on how AI is improving chip design

#52

Post by lvl102 »

maxwells-daemon wrote: post #36

I work on this team! (Specifically: applied deep learning research, chip design). It's a shame to see so many people dismissing this work as marketing. I see lots of clever people working hard on really novel and interesting stuff, and I really do think that ML has real potential to customize a design much more "deeply" than traditional automation tools.

To be fair, Nvidia does a lot of “selling” when they’re basically making money from crypto and CUDA monopoly.

Re: Nvidia R&D chief on how AI is improving chip design

#53

Post by q3k »

jiggawatts wrote: post #43
bsder wrote: post #41

Earlier quoted context omitted.

> Can you explain why such large numbers are required? Absolutely. Even if you start with 32 bits, you often have polygons with many sides. In the worst case, you are modeling a "circle" and have to increase your precision to enough level to be accurate (please note that nobody in the right mind in VLSI would ever draw a "circle"--however, you wind up with an "implied" one due to DRC, more down below ...) The problem…

Disclaimer: I have zero silicon design experience. However, I have designed computer game engines that use 32-bit floats throughout and encountered rounding errors in practice. I’ve found that there’s always a solution that avoids the need to go past 64 bits, and even that is a last resort. So for example the circle could be approximated with a polygon. Or fixed-point arithmetic can be used. Or simply use a quad-tree…

Please keep in mind that even the slightest error in a silicon mask is likely to cause hundreds of millions of dollars of losses and months of delay in time to market for a modern chip.

With that in mind, does it make more sense to come up with new, experimental, untested algorithms... or just use wider numbers and slowly iterate on well known algorithms? Especially with LVS/DRC you really want the dumbest, easiest to reason about thing that is most likely to catch design issues no matter what. Even if it's excruciatingly slow, it's your last line of defense against writing off a set of masks as a hundreds of millions of dollars loss.

EDA / silicon CAD is a totally different world of design requirements compared to video games or even MCAD software.

EDIT: and just for context, here's a DRC set for the (very much not modern) SKY130 process: https://github.com/RTimothyEdwards/open_pdks/blob/master/sky...

Re: Nvidia R&D chief on how AI is improving chip design

#54

Post by wil421 »

root_axis wrote: post #11
nomel wrote: post #3

Earlier quoted context omitted.

> but it's also extremely NVidia that they're doing it all on their own. Having a lead in chip design is their literal bread and butter. I think it's extremely "publicly traded company" more than "NVidia". Do you have an example of a company releasing an open source version of their secret sauce (foundation of their profits)?

> Having a lead in chip design is their literal bread and butter Sounds tasty, I'll have to take a trip to the nvidia cafe some time =)

The meaning of the word has changed. If everyone uses it incorrectly is it really incorrect?

Re: Nvidia R&D chief on how AI is improving chip design

#55

Post by jiggawatts »

q3k wrote: post #53
jiggawatts wrote: post #43

Earlier quoted context omitted.

Disclaimer: I have zero silicon design experience. However, I have designed computer game engines that use 32-bit floats throughout and encountered rounding errors in practice. I’ve found that there’s always a solution that avoids the need to go past 64 bits, and even that is a last resort. So for example the circle could be approximated with a polygon. Or fixed-point arithmetic can be used. Or simply use a quad-tree…

Please keep in mind that even the slightest error in a silicon mask is likely to cause hundreds of millions of dollars of losses and months of delay in time to market for a modern chip. With that in mind, does it make more sense to come up with new, experimental, untested algorithms... or just use wider numbers and slowly iterate on well known algorithms? Especially with LVS/DRC you really want the dumbest, easiest t…

The exact same arguments were made by CAD people insisting on 64-bit maths for OpenGL. They were wrong. They too were working on projects worth billions of dollars, over decades, where mistakes were very costly.

Your link to a "DRC set" doesn't mean much to me out of context. I see some basic looking code with small-ish numeric constants in it. So what? This is not that different to the input to a simple physics simulation or a computer game.

Re: Nvidia R&D chief on how AI is improving chip design

#56

Post by hoosieree »

maxwells-daemon wrote: post #36

I work on this team! (Specifically: applied deep learning research, chip design). It's a shame to see so many people dismissing this work as marketing. I see lots of clever people working hard on really novel and interesting stuff, and I really do think that ML has real potential to customize a design much more "deeply" than traditional automation tools.

When I briefly used Cadence's stuff I always thought about how fixing DRC errors could be crowdsourced as an "idle game" because it's so puzzle-like. The other thing was how it's even slower than Vivado...

Using RL to automate DRC fixes, and modeling standard cells as graph/flow problems are things I'd love to learn more about. What papers would you recommend reading to get started (for a grad student already familiar with machine learning basics)?

Re: Nvidia R&D chief on how AI is improving chip design

#57

Post by maximus-decimus »

q-big wrote: post #51
marginalia_nu wrote: post #44

Earlier quoted context omitted.

This is directed at AI marketing in general: "AI" has been used to market so much nonsense it's probably becoming a problem communicating actual interesting uses of AI. I very much get a dot com vibe off it, like nobody on the team knows how it works but we're sure we're gonna be rich somehow! In my head, I've begun substituting AI with "wizards" when I read it. It's very much the sort of problems crypto is having. S…

> "AI" has been used to market so much nonsense it's probably becoming a problem communicating actual interesting uses of AI. On the other hand: if the people who do serious work in this area don't call out this nonsense, they must accept that their (serious) work becomes devalued. > It's very much the sort of problems crypto is having. So many grifters actual interesting uses of the technology are very hard to ident…

It's a lost cause, you have to pick a new word.

"Diet" was used for women's food product to the point that men didn't want to buy anything with "diet" on it, so CocaCola created coke zero just for men instead of trying to make them drink "diet" coke. They knew it was a lost battle.

Re: Nvidia R&D chief on how AI is improving chip design

#58

Post by atq2119 »

Taniwha wrote: post #32
beambot wrote: post #29

Earlier quoted context omitted.

IIRC, Place & Route is a known NP complete problem. In this regard, autorouters (whether IC or PCB) can benefit from "better" heuristics -- i.e. it's an optimization problem where AI can help.

So here's my autorouter first-guess analog computer design: On a basketball court create a pile of metal plates with bar codes and hooks, each one represents a gate, robot uses rubber bands of sizes vaguely representing timing budget from synthesis to hook the gates together. Robot picks up the whole thing using rubber bands representing the external ports and gives the whole thing a few shakes. Puts it all back down…

What you've described is actually for placement, not routing, and is in fact a good analogy for the first step in many placement algorithms.

Interestingly, placement is much harder than routing from a complexity theory point of view (specifically, there are fairly strong inapproximability results for placement-style problems).

Re: Nvidia R&D chief on how AI is improving chip design

#59

Post by jonnycomputer »

ImportOllie wrote: post #46

I don't understand the backlash here. The jist seemed to be traditional tools that are exact take a long time to process complex designs. Deep learning offers a statistical approach that can give a 'coarse' prediction and they're using this to reduce development time. That seems to make sense to me, especially in the earlier verification phases of the hardware design lifecycle. To me this sounds like a good use-case…

I seem to recall that the original title of the post was more sensationalist; something about replacing human designers.

Re: Nvidia R&D chief on how AI is improving chip design

#60

Post by PaulHoule »

maxwells-daemon wrote: post #36

I work on this team! (Specifically: applied deep learning research, chip design). It's a shame to see so many people dismissing this work as marketing. I see lots of clever people working hard on really novel and interesting stuff, and I really do think that ML has real potential to customize a design much more "deeply" than traditional automation tools.

I think it's funny how "the old AI" had combinatorical optimization as a major theme, for instance

https://en.wikipedia.org/wiki/Travelling_salesman_problem

which is closely related to the central operation of logic, the canonical NP problem

https://en.wikipedia.org/wiki/Boolean_satisfiability_problem

as well as the playing of games like Chess, Poker, etc.

Modern neural networks also have optimization as a theme even when the output is a classification or something that doesn't look like optimization... That is, the network itself is trained to minimize an error function. People used these kind of algorithms back in the 1980s to layout chips

https://en.wikipedia.org/wiki/A*_search_algorithm

and it's only natural that new techniques of optimization (both direct and through heuristics like the neural network used in AlphaGo) are used today for chips.

Post reply on HN