alechammond
Scholar Labs: An AI Powered Scholar Search
> So running 500 sequential kMC simulations would take approximately 125 years - not ideal.
Ah I see. Ya it’s hard to get around this…
> is fundamentally stochastic, and not differentiable
This is actually a common “inverse design pattern” for a variety of applications, and luckily there are tricks to efficiently compute gradients here. In my domain (nanophotonics) we’re often simulating incoherent sources, which are similarly stochastic. But there are ways to reformulate the problem to drastically reduce the number of forward and adjoint solves you need during the design process [1].
That being said, given the cost of the forward problem (3 months per iteration!) this doesn’t help you much…
There are actually a few commercial fabs that will monolithically integrate the photonics, analog electronics, and digital electronics, all in the same CMOS process. See for example GF’s process:
https://www.cmc.ca/globalfoundries-fotonix-45spclo/
Integrating good optical sources in silicon remains a challenge, but companies like Intel have mastered hybrid bonding and other packaging techniques. TSMC too has a strong silicon photonics effort.
Magic Leap partners with Google to advance XR
Nvidia Blackwell Arch Technical Brief
A gymnasium for machine learning assisted computer architecture design
I may be missing something, but MIT has been doing something very similar for awhile now. The student (Dan Oran) even spun out a startup.
https://www.media.mit.edu/projects/implosion-fabrication-1/o...