Huh, did not expect our press release to end up on HN, but I'm the PI on this project, so AMA, I guess. Will jump into the questions already asked here and provide some context.
Julia receives DARPA award to accelerate electronics simulation
11–20 of 175 posts
Re: Julia receives DARPA award to accelerate electronics simulation
#12Fix the headline - it should say "Julia Computing Receives DARPA Award to Accelerate Electronics Simulation by 1,000x"
The money is going to a company.
Re: Julia receives DARPA award to accelerate electronics simulation
#13I'm having a lot of trouble understanding how "just add AI" is going to make electronics simulation 1000x faster.
There are ways to surrogatize portions of a simulation, replacing large portions with ML-trained surrogates. There are already demonstrations in different domains (on highly stiff differential-algebraic equations) showing that you can get these kinds of speedups at around 99% accuracy.
Re: Julia receives DARPA award to accelerate electronics simulation
#14Why isn't Rust top at modeling and simulation yet?
This is about Julia Computing, the company, not Julia the language.
Re: Julia receives DARPA award to accelerate electronics simulation
#15Fix the headline - it should say "Julia Computing Receives DARPA Award to Accelerate Electronics Simulation by 1,000x" The money is going to a company.
Yeah, I think most people on this site are going to first assume the language.
Re: Julia receives DARPA award to accelerate electronics simulation
#16I'm having a lot of trouble understanding how "just add AI" is going to make electronics simulation 1000x faster.
the TLDR is that for a lot of high dimensional PDE models, you get a better trade off of speed vs accuracy by using a NN for part of the model that is inefficient to calculate the full physics for. This is already having a lot of success in climate modeling, where NN based solutions do a better job of dealing with some atmospheric effects than previous efforts.
Sounds similar to what stockfish (leading chess computer engine) does. In newer versions, position evaluation comes at least in part from a NN, which lead to an improvement in playing strength.
edit: similar in approach, not as a 1:1 mapping. Replace a deterministic model with a faster, slightly fuzzy one.
Re: Julia receives DARPA award to accelerate electronics simulation
#17LT-Spice is absolute trash and basically why I decided to leave EE for CS in college... among many other reasons! Essentially, because after learning all kinds of math my linear systems prof basically said "yeah, at some point you just have to simulate everything because the math you learned only applies maybe 60% of the time". Granted, I do not think I was exactly destined to be a great electrical engineer. Electron…
Been using LTSpice for the last decade or so and am just fine simulating everything from Buck to current sense circuits to battery monitoring systems to HBridge. Don’t know what your beef is with LTSpice but still can’t get around the fact you quit your discipline for the lack of a better tool. If you didn’t like what you had to deal with why didn’t you pivot to CS and invent a better simulation tool. Just saying.
Re: Julia receives DARPA award to accelerate electronics simulation
#18Can anyone explain the potential benefits of accelerating electronics simulation?
Do they want to generate efficient FPGA programs?
Re: Julia receives DARPA award to accelerate electronics simulation
#19Re: Julia receives DARPA award to accelerate electronics simulation
#20I'm having a lot of trouble understanding how "just add AI" is going to make electronics simulation 1000x faster.
There are ways to surrogatize portions of a simulation, replacing large portions with ML-trained surrogates. There are already demonstrations in different domains (on highly stiff differential-algebraic equations) showing that you can get these kinds of speedups at around 99% accuracy. https://arxiv.org/abs/2010.04004 https://arxiv.org/abs/2103.05244
> can get these kinds of speedups at around 1% accuracy
Shouldn't this be at around "at around 99% accuracy" or "within around 1% accuracy loss"?