172K views · Feb 9, 2020 · 26:02 · 1 HN recommender · 3 mentions · discussed 2021–2025
A clip from Lex Fridman's podcast in which chip architect Jim Keller argues that Moore's Law is not dead and that transistor scaling still has lots of room. He also discusses how to break down hard problems.
Why Hacker News points people here: Used to support the argument that chip engineers see plenty of scaling headroom left.
“According to Jim Keller, yes, there is.”HN comment, 2022
“I got enlightened about many subjects and you took a peak on how Jim Keller perceives some problems”
Jim Keller's view on Moore's Law and breaking down problems
I found it the other way around, I got enlightened about many subjects and you took a peak on how Jim Keller perceives some problems and how he breaks them down - really remarkable. For example, I really liked these two approaches regarding Moore's Law (Jim Keller: this video , and David Patterson : this video )
“According to Jim Keller, yes, there is.”
Keller says Moore's Law still has room
According to Jim Keller, yes, there is. If my memory serves, he said so in a recent Lex Friedman interview. Edit: here is the clip this video
“And indeed, that's what chip engineers like Jim Keller say”
Chip engineers argue transistor scaling has plenty of room
> NVIDIA think it's dead already Perhaps that's what Jensen says publicly, but Nvidia's next generation chip contains more transistors than the last. And the one after that will too. Let me know when they align their $Trillions behind smaller less complex designs, then I'll believe that they think Moore's law is out of juice. Until then, they can sit with the group of people who've been vocally wrong about moore's law's end for the last 50 years. Our chips are still overwhelmingly 2D in design, just a few dozen layers thick but billions of transistors wide. We have quite a ways to go based on a first principles analysis alone. And indeed, that's what chip engineers like Jim Keller say: this video So ask yourself how it benefits Jensen to convince you otherwise.
