cross-posted from: https://lemm.ee/post/4443753
In the past 10 years or so, tech specialists have repeatedly voiced concerns that the progress of computing power will soon hit the wall. Miniaturisation has physical limits, and then what? Have we reached these limits? Is Moore’s law dead? That’s what we’ll talk about today.
- 00:00 Intro
- 00:53 Moore’s Law And Its Demise
- 06:23 Current Strategies
- 13:14 New Materials
- 15:50 New Hardware
- 18:58 Summary
Certainly not. Quantum effects begin dominating when you attempt to make transistors much smaller than 2nm, and even using “exotic” materials doesn’t fix the problem very much. Making matters worse, you need to be able to get heat out of those transistors, which becomes increasingly difficult. Beyond that, producing high enough yield on chips, with enough of the die area actually consumed by useful circuitry becomes a massive limitation as flaw rates scale non-linearly.
In either case, Moore’s law actually died a few years after he first wrote it when he revised it. And then again, and again in the 90s. It became a design target, and we’ve failed to deliver on the core principal of the original observation. Sophie Wilson (one of the inventors of ARM) has a great talk about this, as well as an address she gives to university kids once every couple years.