It requires 4X speed increase every year, production quality scale can’t provide even close to half of that, maybe 25%, then another 25% from design, and regarding increasing die sizes they are already close to the end. So the only way to get from 50 to 400% is by using multi chip designs, meaning they will have to use 8 chips that are bleeding edge. The H200 is estimated at $40K, but the million times faster “chips” ( multi chip packages ) will be more than $300.000 each in today’s money!!! It’s an insane amount of money already, but it will be even more insane.
agent_flounder@lemmy.world 4 months ago
If chips = cpus, here, then I imagine that will hit a limit also (Amdahl’s law).
Buffalox@lemmy.world 4 months ago
A chip is also called a die, it’s the piece cut out from the wafer, which is then packaged onto a chip package.
Since traditionally there were always 1 chip per chip package, the 2 words were used almost synonymously.
I this case it’s basically GPU chips, which AFAIK AMD has already figured out how to use in multi chip packages. Meaning one package contains multiple chips that work “almost” as well as a single chip of similar size.
The advantage of multichip packages are obvious, production costs are way lower because smaller dies causes lower percentage of flawed dies, and allows for better binning of higher end parts.
Additionally it allows designs of way more complex packages, than would be possible with monolithic chips. This is the reason AMD has been taking marketshare in server markets from Intel. Because Intel has not been able to match the multichip design AMD introduced with Epyc in 2016/17, which originally was 4 Ryzen chiplets/chips/dies packaged together as one big 32 core server chip. Where the biggest Intel could make was 28 cores.
But packaging almost 10000 GPU chips together is completely different, and I don’t think that will be relevant within 10 years.
Amdahls law however is part obvious and part bullshit. Everything your mind is able to do semi efficiently, can be multithreaded, it is very few things that can’t.
Amdahls law is basically irrelevant with regard to AI, as AI has a lot of patten recognition, and pattern recognition is perfect for multi threading.
TheGrandNagus@lemmy.world 4 months ago
And to add: currently TSMC nodes have a reticle limit of 858mm². I.e. that’s the largest chips you can make on their wafers. Then in the real world you do it slightly below that.
Future nodes are reducing this to the 350-450mm² range.
High end GPUs/HPC cards basically have to go to multi-die, even in the fantasy world of 100% perfect yields.