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

Jim Keller moves to AI chip startup

reuters.com

Post reply on HN
Print view View original

61–70 of 94 posts

Re: Jim Keller moves to AI chip startup

#61

Post by thu2111 »

dr_faustus wrote: post #17

I often find it hard to believe that a single person can make much of a difference in such intricate problem domains as chip design but in his case the evidence is overwhelming. Also goes to show what a shit show Intel has become since even he was not able to right that ship. I think in the CPU space it will be all ARM and RISC ten years from now and since Intel never really managed to become a dominant player in any…

That's not quite true.

Intel started out with memory. They never left and are on by far the cutting edge with memory tech. In particular Optane NVM DIMMs are so fast they basically define a new layer in the performance/cache hierarchy. Intel might see a shift in their focus over time away from CPUs to chalcogenide based persistent memory, where it seems they have held the lead for some time now.

Re: Jim Keller moves to AI chip startup

#63

Post by marcinzm »

thu2111 wrote: post #61
dr_faustus wrote: post #17

I often find it hard to believe that a single person can make much of a difference in such intricate problem domains as chip design but in his case the evidence is overwhelming. Also goes to show what a shit show Intel has become since even he was not able to right that ship. I think in the CPU space it will be all ARM and RISC ten years from now and since Intel never really managed to become a dominant player in any…

That's not quite true. Intel started out with memory. They never left and are on by far the cutting edge with memory tech. In particular Optane NVM DIMMs are so fast they basically define a new layer in the performance/cache hierarchy. Intel might see a shift in their focus over time away from CPUs to chalcogenide based persistent memory, where it seems they have held the lead for some time now.

Isn't 80+% of Intel's revenue from CPUs with another some percent from mobile chips? So while they may produce memory it's almost irrelevant as far as current revenue goes.

Re: Jim Keller moves to AI chip startup

#64

Post by PaulHoule »

ghaff wrote: post #56
PaulHoule wrote: post #54

Earlier quoted context omitted.

Worse than that I wonder if the trouble at Intel (e.g. inability to develop post 14nm chips plus one insane instruction set extension after another -- I wonder if the point of AMX is to have a big die area that is mostly unused that doesn't need to be cooled) isn't something that people like him are running from but rather something they are going to bring with then wherever they wind up.

>one insane instruction set extension after another You're probably going to see a whole lot more of this sort of thing given the limits to process scaling. Keeping things simple and backwardly compatible made sense when you could just throw more transistors at the problem. Now you're seeing more and more specialized circuitry that software people are just going to have to deal with.

I am not against a new instruction. At first blush the new JavaScript instruction in arm might seem like a boondoggle but it is a simple arithmetic operation.

Compare that to the non-scalable SIMD instructions that mean you have to rewrite your code to take advantage of them and resultingly people don't bother to use them at all.

AMX allocates a huge die area to GEMM functionality that gets used a lot less in real numerics than you'd gather from reading a linear algebra textbook.

There are other approaches to the problems the industry faces other than 'fill up the die with registers that will never be used', nvidia and apple are going that way and that is why they are succeeding and Intel is failing.

Re: Jim Keller moves to AI chip startup

#65

Post by umvi »

PartiallyTyped wrote: post #62
systemvoltage wrote: post #3

Jim is a tour de force: https://www.youtube.com/watch?v=Nb2tebYAaOA

Thank you. This is definitely one of the best interviews I have read. The precision of the statements and the usage of analogies to explain the topics is astonishing.

Is there a transcript of it?

Re: Jim Keller moves to AI chip startup

#66

Post by magicalhippo »

dr_faustus wrote: post #17

I often find it hard to believe that a single person can make much of a difference in such intricate problem domains as chip design but in his case the evidence is overwhelming. Also goes to show what a shit show Intel has become since even he was not able to right that ship. I think in the CPU space it will be all ARM and RISC ten years from now and since Intel never really managed to become a dominant player in any…

Just going by the interview posted by another commenter, it seems to me a big reason is that he seems to enjoy the "people challenge" about as much as the technical challenge.

Re: Jim Keller moves to AI chip startup

#69

Post by azeirah »

dr_faustus wrote: post #17

I often find it hard to believe that a single person can make much of a difference in such intricate problem domains as chip design but in his case the evidence is overwhelming. Also goes to show what a shit show Intel has become since even he was not able to right that ship. I think in the CPU space it will be all ARM and RISC ten years from now and since Intel never really managed to become a dominant player in any…

I only know the name of one prominent individual within the CPU space that is not a CEO or major scientist; and that's Jim Keller.

Why? Because I never ever see any articles talking about any other interesting employees. Every single time it's Jim Keller.

I'm sure he's good, his interview with Lex Fridman shows that he's knowledgeable and creative, but there's no way he's as exclusive a major force as the media portrays him.

Re: Jim Keller moves to AI chip startup

#70

Post by redisman »

systemvoltage wrote: post #3

Jim is a tour de force: https://www.youtube.com/watch?v=Nb2tebYAaOA

He also had the best answer to Lex's meaning of life question (last few minutes of the interview). Really made me stop and re-listen. It's very rare for someone on a podcast to think about every word they say.
Post reply on HN