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

TSMC bets on unorthodox optical tech

spectrum.ieee.org

Post reply on HN
Print view View original

51–60 of 110 posts

Re: TSMC bets on unorthodox optical tech

#51

Post by wyager »

EA-3167 wrote: post #8
Liftyee wrote: post #2

As I understand it (from designing high-speed electronics), the major limitations to data/clock rates in copper are signal integrity issues. Unwanted electromagnetic interactions all degrade your signal. Optics is definitely a way around this, but I wonder if/when it will ever hit similar limits.

The energy densities required for photon-photon interactions are so far beyond anything we need to worry about that it's a non-issue. Photons also aren't going to just ignore local potential barriers and tunnel at the energy levels and scales involved in foreseeable chip designs either.

P-p interactions are not an issue but we do have high enough field intensities in high bandwidth fibers to run into p-f nonlinearity issues.

Re: TSMC bets on unorthodox optical tech

#52

Post by momoschili »

ls612 wrote: post #25
qwezxcrty wrote: post #22

Earlier quoted context omitted.

I think the most fundamental reason is that there is no efficient enough nonlinearity at optical frequencies. So two beams(or frequencies in some implementation) tends not to affect each other in common materials, unless you have a very strong source (>1 W) so the current demonstrations for all-optical switching are mostly using pulsed sources.

I wonder if considerably more engineering and research effort will be applied here when we reach the limit of what silicon and electrons can do.

Contrary to the prior commenter, there is definitely significant engineering going toward this, but it's not clear or likely that photonic computing will supplant electronic computing (at least not anytime soon), but rather most seem to think of it as an accelerator for highly parallel tasks. Two major ways people are thinking of achieving this are using lithium niobate devices which mediate nonlinear optical effects via light-matter interaction, and silicon photonic devices with electrically tunable elements. In the past there was a lot of work with III-V semiconductors (GaAs/InAs/GaN/AlN etc) but that seems to have leveled off in favor of lithium niobate.

Photonics has definitely proved itself in communications and linear computing, but still has a way to in terms of general (nonlinear) compute.

Re: TSMC bets on unorthodox optical tech

#53

Post by nullc »

cycomanic wrote: post #38
Taek wrote: post #12

Earlier quoted context omitted.

This comment appears insightful but I have no idea what it means. Can someone elaborate?

What the previous poster is implying is that electrons interact much more strongly than photons. Hence electrons are very good for processing (e.g. building a transistor), while photons are very good for information transfer. This is also a reason why much of the traditional "optical computer" research was fundamentally flawed, just from first principles one could estimate that power requirements are prohibitive.

> This is also a reason why much of the traditional "optical computer" research was fundamentally flawed

presumably also because photons at wavelengths we can work with are BIG

Re: TSMC bets on unorthodox optical tech

#54

Post by adgjlsfhk1 »

cycomanic wrote: post #44
qwezxcrty wrote: post #41

Earlier quoted context omitted.

I guess they are doing direct modulated IMDD for each link so the DSP burden is not related to the coherence of diodes? Also indeed very short reach in the article.

The problem with both leds and imaging fibres is that modal dispersion is massive and completely destroys your signal after only a few meters of propagation. So unless you do MMSE (which I assume would be cost prohibitive), you really can only go a few meters. IMDD doesn't really make a difference here.

I think this is intended for short distances (e.g. a few cm). cpu to GPU and network card to network card still will be lasers, the question is whether you can do core to core or CPU to ram with optics

Re: TSMC bets on unorthodox optical tech

#55

Post by ls612 »

momoschili wrote: post #52
ls612 wrote: post #25

Earlier quoted context omitted.

I wonder if considerably more engineering and research effort will be applied here when we reach the limit of what silicon and electrons can do.

Contrary to the prior commenter, there is definitely significant engineering going toward this, but it's not clear or likely that photonic computing will supplant electronic computing (at least not anytime soon), but rather most seem to think of it as an accelerator for highly parallel tasks. Two major ways people are thinking of achieving this are using lithium niobate devices which mediate nonlinear optical effects…

Yeah that was sorta what I was thinking is there a clever way to exploit light interacting with matter to turn the gate on/off.

Re: TSMC bets on unorthodox optical tech

#56

Post by cycomanic »

abdullahkhalids wrote: post #48
cycomanic wrote: post #35

Earlier quoted context omitted.

Phase variations will not introduce any issues here, they most certainly are talking about intensity modulation. You can't really (easily) do coherent modulation using incoherent light sources like leds. SNR is obviously an issue for any communication system, however fiber attenuation is orders of magnitude lower than coax. The bigger issues in this case would be mode-dispersion, considering that they are going throu…

Mode dispersion is frequency dependent phase changes.

That's chromatic dispersion, mode dispersion is spatial "path" dependent phase changes. Vibration is actually somewhat more relevant because if it wasn't for that we could theoretically undo mode dispersion (we would need phase information though).

That said all of that is irrelevant to what the previous speaker said, vibration induced phase variation as an impairment. Thats just not an issue, vibrations are way too slow to impair optical comms signals.

Re: TSMC bets on unorthodox optical tech

#57

Post by cycomanic »

adgjlsfhk1 wrote: post #54
cycomanic wrote: post #44

Earlier quoted context omitted.

The problem with both leds and imaging fibres is that modal dispersion is massive and completely destroys your signal after only a few meters of propagation. So unless you do MMSE (which I assume would be cost prohibitive), you really can only go a few meters. IMDD doesn't really make a difference here.

I think this is intended for short distances (e.g. a few cm). cpu to GPU and network card to network card still will be lasers, the question is whether you can do core to core or CPU to ram with optics

But why are they talking about multicore fibres then? I would have expected ribbons. You might be right though.

Re: TSMC bets on unorthodox optical tech

#58

Post by mystified5016 »

amelius wrote: post #9

> The transmitter acts like a miniature display screen and the detector like a camera. So if I'm streaming a movie, it could be that the video is actually literally visible inside the datacenter?

Not any more than if you blinked an LED each time a bit comes across your network connection.

Re: TSMC bets on unorthodox optical tech

#59

Post by programjames »

seventytwo wrote: post #45
cycomanic wrote: post #43

Earlier quoted context omitted.

The issue with optical neuromorphic computing is that the field has been doing the easy part, i.e. the matrix multiplication. We have known for decades that imaging/interference networks can do matrix operations in a massively parallel fashion. The problem is the nonlinear activation function between your layers. People have largely been ignoring this, or just converted back to electrical (now you are limited again b…

Seems hard to imagine there’s not some non-linear optical property they could take advantage of

There is, and people have trained purely optical neural networks:

https://arxiv.org/abs/2208.01623

The real issue is trying to backpropagate those nonlinear optics. You need a second nonlinear optical component that matches the derivative of the first nonlinear optical component. In the paper above, they approximate the derivative by slightly changing the parameters, but that means the training time scales linearly with the number of parameters in each layer.

Note: the authors claim it takes O(sqrt N) time, but they're forgetting that the learning rate mu = o(1/sqrt N) if you want to converge to a minimum:

    Loss(theta + dtheta) = Loss(theta) + dtheta * dLoss(theta) + O(dtheta^2)
                         = Loss(theta) + mu * sqrtN * C (assuming Lipschitz continuous)
    ==>     min(Loss)    = mu * sqrtN * C/2

Re: TSMC bets on unorthodox optical tech

#60

Post by dtgriscom »

qwezxcrty wrote: post #41
cycomanic wrote: post #33

That article is really low on details and mixes up a lot of things. It compares microleds to traditional WDM fiber transmission systems with edge emitting DFB lasers and ECLs, but in datacentre interconnects there's plenty of optical links already and they use VCSELs (vertical cavity surface emitting lasers), which are much cheaper to manufacture. People also have been putting these into arrays and coupling to multi-…

I guess they are doing direct modulated IMDD for each link so the DSP burden is not related to the coherence of diodes? Also indeed very short reach in the article.

[flagged]
Post reply on HN