Analog optical computer for AI inference and combinatorial optimization
1–10 of 21 posts
Re: Analog optical computer for AI inference and combinatorial optimization
#2Spatial light modulators are many orders slower than a cpu clock cycle. How many of these in parallel would be required to compete with an H100?
Re: Analog optical computer for AI inference and combinatorial optimization
#3I really want to believe, but if I had a penny for every time that analog, optical, ternary, clockless, or other radically non-standard computing paradigms were supposed to revolutionize the industry... I'd have a nice pile of pennies.
Electronic signaling is just so marvelously easy to scale that the right path was clear pretty much from day one. We don't have that path for other operating principles right now. As for synchronous operation, binary signaling, and so forth, they're once again just scaling tools that let us crank out designs with billions of transistors without hand-crafting every piece or making the abstractions more leaky than they already are.
Re: Analog optical computer for AI inference and combinatorial optimization
#4I really want to believe, but if I had a penny for every time that analog, optical, ternary, clockless, or other radically non-standard computing paradigms were supposed to revolutionize the industry... I'd have a nice pile of pennies. Electronic signaling is just so marvelously easy to scale that the right path was clear pretty much from day one. We don't have that path for other operating principles right now. As f…
A difference now is that moore’s law per power density has been dead a few years and physics says it can’t get much better.
The other difference is that computers are now powerful enough to do the 10^20 calculations required to design efficient optical metamaterials for optical inference.
Re: Analog optical computer for AI inference and combinatorial optimization
#5This is important work.
I'd wondered whether optics could do maths, this looks to show it can.
Re: Analog optical computer for AI inference and combinatorial optimization
#6Spatial light modulators are many orders slower than a cpu clock cycle. How many of these in parallel would be required to compete with an H100?
In performance per watt? One ;)
Re: Analog optical computer for AI inference and combinatorial optimization
#7I really want to believe, but if I had a penny for every time that analog, optical, ternary, clockless, or other radically non-standard computing paradigms were supposed to revolutionize the industry... I'd have a nice pile of pennies. Electronic signaling is just so marvelously easy to scale that the right path was clear pretty much from day one. We don't have that path for other operating principles right now. As f…
naive question: isn't fiber optic cables for communication a counter-example to your thesis?
Re: Analog optical computer for AI inference and combinatorial optimization
#8I really want to believe, but if I had a penny for every time that analog, optical, ternary, clockless, or other radically non-standard computing paradigms were supposed to revolutionize the industry... I'd have a nice pile of pennies. Electronic signaling is just so marvelously easy to scale that the right path was clear pretty much from day one. We don't have that path for other operating principles right now. As f…
Progress doesn't happen out of thin air. Someone has to go in and do the work, and find out the limits or feasibility of such and such tech. More interest in this is good in the long run, even if the first few iterations don't prove revolutionary.
Re: Analog optical computer for AI inference and combinatorial optimization
#9See also: https://en.wikipedia.org/wiki/TWINKLE
Re: Analog optical computer for AI inference and combinatorial optimization
#10I really want to believe, but if I had a penny for every time that analog, optical, ternary, clockless, or other radically non-standard computing paradigms were supposed to revolutionize the industry... I'd have a nice pile of pennies. Electronic signaling is just so marvelously easy to scale that the right path was clear pretty much from day one. We don't have that path for other operating principles right now. As f…
A difference now is that moore’s law per power density has been dead a few years and physics says it can’t get much better. The other difference is that computers are now powerful enough to do the 10^20 calculations required to design efficient optical metamaterials for optical inference.
> [...] and physics says it can’t get much better.
What part of physics do you have in mind?