Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Analog optical computer for AI inference and combinatorial optimization

nature.com

Post reply on HN
Print view View original

11–20 of 21 posts

Re: Analog optical computer for AI inference and combinatorial optimization

#11

Post by imtringued »

non_aligned wrote: post #3

I 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…

Your perspective only makes sense in the context of machine learning and general purpose computation.

I'm not really seeing any ASICs that are built for running optimizers. Meanwhile the "AOC" is really good at solving unconstrained/equality-constrained quadratic programs.

Re: Analog optical computer for AI inference and combinatorial optimization

#13

Post by pringk02 »

eru wrote: post #10
mensetmanusman wrote: post #4

Earlier quoted context omitted.

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?

Probably the lower bound on transistor size

https://en.m.wikipedia.org/wiki/Quantum_tunnelling

Re: Analog optical computer for AI inference and combinatorial optimization

#14

Post by econ »

NitpickLawyer wrote: post #8
non_aligned wrote: post #3

I 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.

You can have as many iterations as it takes, you need only one to work. Thousands or millions is fine. If you keep track of what was tried and how hard everything is a gain.

Re: Analog optical computer for AI inference and combinatorial optimization

#15

Post by ww520 »

VMG wrote: post #7
non_aligned wrote: post #3

I 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?

Fiber optic is a communication medium, not a computation device.

Re: Analog optical computer for AI inference and combinatorial optimization

#16

Post by ww520 »

non_aligned wrote: post #3

I 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…

You are right.

> The current hardware includes 16 microLEDs and 16 photodetectors, supporting a 16-variable state vector…

Re: Analog optical computer for AI inference and combinatorial optimization

#17

Post by kaelandt »

the AI inference workloads shown in the paper are extremely far from what is implied when one says "... computer for AI inference". No discussion of issues around the memory hierarchy and how the presented architecture solves those. No mention of transformers, except for a vague reference to energy-based models

Re: Analog optical computer for AI inference and combinatorial optimization

#18

Post by mensetmanusman »

eru wrote: post #10
mensetmanusman wrote: post #4

Earlier quoted context omitted.

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?

kT generated per electron based gate activation.

Re: Analog optical computer for AI inference and combinatorial optimization

#19

Post by mallowdram »

Analog will ultimately leave binary AI/LLMs in the dustpile. Meaning is not accessible through counting, it will require syntax (parallel differences) and analoga in optic flow. We live in a century of toy experiments, not reasoned task variability/scale invariance.

Re: Analog optical computer for AI inference and combinatorial optimization

#20

Post by jbottoms »

This architecture appears to overlap with the, then, Bell Labs LambdaXtreme telephone switch. It was sold to Alcatel as it appears to be an optimum design for a swich that covers the E.U. Switching was likely in the control plane, and perhaps an optical fabric was used for administrative changes in both the control and dats pkane.
Post reply on HN