Fiber Optics and computing
Stephen Cass: Hi, I’m Stephen Cass, for IEEE Spectrum’s Fixing the Future. This episode is brought to you by IEEE Xplore, the digital library with over 6 million pieces of the world’s best technical content. Today I have with me our own Samuel K. Moore, who has been covering the semiconductor beat pretty intensely for Spectrum for— well, how many years has it been, Sam?
Sam Moore: 7 years, I would say.
Cass: So Sam knows computers down at the level most of us like to ignore, hidden underneath all kinds of digital abstractions. This is down where all the physics and material science that make the magic possible lurk. And recently, you wrote an article about the race to replace electricity with light inside computers, which is letting chips talk to each other with fiber optics rather than just using fiber optics to communicate between computers. I guess my first question is, what’s wrong with electricity, Sam?
Moore: I have nothing against electricity, Stephen. Wow… It knows what it did. But really, this all comes down to inputs and outputs. There just aren’t enough coming off of processors for what they want to do in the future. And electronics can only push signals so far before they kind of melt away, and they consume quite a bit of power. So the hope is that you will have better bandwidth between computer chips, consuming less power.
Cass: So it’s not just a question of raw speed, though, when you talk about these signals and melting away, because I think the signal speed of copper is about, what, two-thirds the speed of light in a vacuum. But then I was kind of surprised to see that, in a fiber optic cable, the speed of light is about two-thirds of that in a vacuum. So what’s going on? What’s kind of the limitations of pushing a signal down a wire?
Moore: Sure. A wire is not an ideal conductor. It’s really resistance, inductance, and capacitance, all of which will reduce the size and speed of a signal. And this is particularly a problem at high frequencies, which are more susceptible, particularly to the capacitance side of things. So you might start with a beautiful 20 GHz square wave at the edge of the chip, and by the time it gets to the end of the board, it will be an imperceptible bump. Light, on the other hand, doesn’t work like that. It has things that— there are things that mess with signals in optical fibers, but they work at much, much, much longer length scales.
Cass: Okay, great. So you talked about there are two companies that are in this sort of race to put light inside computers. So we can talk a little bit? Who are they, and what are their different approaches?
Moore: Sure, these are two startups, and they’re not alone. There are very likely other startups in stealth mode, and there are giants like Intel that are also in this race as well. But what these two startups, Ayar Labs, that’s A-Y-A-R—and I’m probably pronouncing it a little weird—and Avicena, those are the two that I profiled in the January issue. And they’re representative of two very different sort of takes on this same idea. Let me start with Ayar, which is really sort of the— it’s sort of what we’re using right now but on steroids. Like the links that you find already in data centers, it uses infrared laser light, kind of breaks it into several bands. I can’t remember if it’s 8 or 16, but so they’ve got multiple channels kind of in each fiber. And it uses silicon photonics to basically modulate and detect the signals. And what they bring to the table is they have, one, a really good laser that can sit on a board next to the chip, and also they’ve managed to shrink down the silicon photonics, the modulation and the detection and the associated electronics that makes that actually happen, quite radically compared to what’s out there right now. So really they are sort of just— I mean, it’s weird to call them a conservative play because they really do have great technology, but it is just sort of taking what we’ve got and making it work a lot better. .... '
No comments:
Post a Comment