IBM Creates Commercially Viable, Electronic-Photonic Integrated Chip 71
An anonymous reader writes "After more than a decade of research, and a proof of concept in 2010, IBM Research has finally cracked silicon nanophotonics (or CMOS-integrated nanophotonics, CINP, to give its full name). IBM has become the first company to integrate electrical and optical components on the same chip, using a standard 90nm semiconductor process. These integrated, monolithic chips will allow for cheap chip-to-chip and computer-to-computer interconnects that are thousands of times faster than current state-of-the-art copper and optical networks. Where current interconnects are generally measured in gigabits per second, IBM's new chip is already capable of shuttling data around at terabits per second, and should scale to peta- and exabit speeds."
More info (Score:5, Informative)
The article is remarkably lacking in technical details.
This article from two years ago is a little more detailed: http://www.eetimes.com/electronics-news/4211151/IBM-debuts-CMOS-silicon-nanophotonics [eetimes.com]
or this press release: http://www-03.ibm.com/press/us/en/pressrelease/33115.wss [ibm.com]
Original press release [Re:More info] (Score:5, Informative)
And here's the IBM press release
http://researcher.ibm.com/researcher/view_project.php?id=2757 [ibm.com]
which has a sidebar that has "links to additional information" with a lot more details.
Re: (Score:3, Insightful)
It's also remarkably misleading. Infinera has been doing Photonic Integrated Circuits for a while now, but they're definitely not cheap.
The only thing IBM may have pioneered is doing it on Silicon. Infinera uses Indium Phosphide.
Re:More info (Score:5, Insightful)
The only thing IBM may have pioneered is doing it on Silicon. Infinera uses Indium Phosphide.
What they've done hardly sounds like a small thing. They've gone from lab-scale to commercial-scale, at least in the lab (if that makes sense).
They're not the first to make this kind of chip, but they've advanced the state of the art. There aren't many times when a completely new invention comes out, most of the time it's baby steps like this.
Re: (Score:3)
Infinera was at commercial scale around 7 years ago, at 100Gigabit speeds (10x10Gbit/s). They're very expensive, but cheaper than 10 discrete OTU2/OC192/10GbE LAN-PHY transponders with optics. From what I've read in article, IBM may possibly be able to use this to lower the cost of LR4 optics in routers, at least that's what they seem to be aiming at. It won't give us the ability to do anything we can't already do today, though.
Re:More info (Score:5, Insightful)
It won't give us the ability to do anything we can't already do today, though.
Yes, it will. It will give you the ability to afford the technology, so that applications may turn up in places where you would not be able to put an Infinera type device.
Re: (Score:2)
Re: (Score:3)
You can't afford RAM at L2 speeds, and thats what the problem has always been.
Re:More info (Score:4, Informative)
Re: (Score:1)
Compared to disk, maybe, but time from request to first byte at the pin level on DRAM is still at least 60 CPU clock cycles (@ 3 GHz.) Add in all the rest of the delays (memory controller, caches, TLBs, etc., etc.) and you get a situation where you might as well context-switch if you get a cache miss, since your pipeline is going to be empty or stalled for hundreds or thousands of clock cycles.
Re: (Score:2)
You're comparing different types of RAM and pretending they are the same.
I said you can't afford gigabytes of RAM running at those speeds. You can not afford gigabytes of SRAM running at full CPU speed. I'd say it again, but you'll still pretend I said something else.
IF you could, you wouldn't need a memory controller in the way.
And those few CPU cycles you speak of ... are nothing compared to the waits spent while the data is fetched, buffered and latched by DRAM. Of course some of those cycles are spe
Re: (Score:2)
Re: (Score:2)
The hypothetical IBM chip is not a competitor to the Infinera device, it's a competitor to CFPs and CXPs produced using discrete optical and electronic components.
Re: (Score:3)
Because, they have not demonstrated that it can be mass-produced cheaply. They're still doing these in a lab. They may be using standard 90mm lithography process, but they're using non-standard wafers with some exotic bits stuck in there like germanium and carbon nanotubes. Whether they can produce this with the kind of success rate needed to make it worthwhile is yet to be seen.
Re: (Score:2)
How is it misleading? It says right in the summary that their claim is that the use silicon and "standard 90nm semiconductor processes". The Infinera site says that Infinera were able to accomplish their stuff 'by not having to evolve existing manufacturing'. So it sounds quite a bit different to me.
Re: (Score:2)
I say misleading because both TFS and TFA headlines say commercially viable. When you actually dig into it you find out this has never left the lab. It also implies that something like this hasn't been done before. It has, just not on silicon. And, IBM still can't do it purely on doped silicon. If you read deeper the wafer has to include a germanium layer and carbon nanotubes for the optical components.
Re: (Score:2)
Re: (Score:2)
Re: (Score:3)
The article is remarkably lacking in technical details.
Maybe they are waiting for the patent applications to be processed, before giving out too many details . . . ?
Re: (Score:2)
The article is remarkably lacking in technical details.
It's just a prototype. The commercially-viable article will be ready in two years.
OpSIS (Score:5, Interesting)
http://opsisfoundry.org/ [opsisfoundry.org]
OpSIS is a foundry service for integrated photonics/CMOS electronics, similar to MOSIS for CMOS. Academic and research institutions can get small lots of experimental designs built as part of a multi-chip wafer run. They support libraries of standard and example components, some modelling and rules decks. They plan several fab runs a year, and access, last time I checked, three different processes from different vendors. Carver Mead is a booster.
I had hoped to start designing with their rules a while ago, and got pulled into more immediate projects. I still think it's pretty cool, and would like to get back to it if ever I get a quiet moment.
Re:OpSIS (Score:4, Informative)
One thing that's worth looking into - OpSIS hosts or points to web-based training and seminars several times a year, sometimes given by CAD vendors that support their design and fab processes. They are well worth sitting in for if you're trying to spin up on this stuff. Not a plug, just my own experience.
Don't plan a desktop upgrade yet (Score:3)
Re:Don't plan a desktop upgrade yet (Score:4, Insightful)
Isn't that true of all computer technology?
Re:Fast, Cheap n' Frigid (Score:5, Interesting)
You've got to remember that all those rules are easily dismissed by converse. There's always a trade-off, you can make something faster but it becomes hotter, or more expensive, or less durable... lies. You can demonstratably make something expensive, slow, high-power, and low-durability by extremely inefficient process.
In economics people like to discuss job creators and wealth movement, trickle-up and trickle-down, the loss of businesses, poor people and rich people... but they fail to understand wealth. Take the "shop locally" thing... if you have a local bookstore versus Amazon, people tell you to shop locally because it "keeps the money in the community." Problem is the local bookstore is crap, they order from the big publishers and distributors, etc; some folks argue Walmart or B&N are as bad as Amazon and not like a local bookstore, but their stores still pay local taxes on their income, they still pay rent, hire sales people, and order from the same distributors.
Now let's say you order from Amazon because it's $10 cheaper. That money leaves the local community, but $10 stays ... you're $10 wealthier. The local bookstore has terrible selection and is expensive... it goes out of business. Meanwhile you've got a local farmer's market and you shop there with the extra $10 you have. That's wealth creation: you have the same goods (a book) plus more money ($10) to buy other goods (fresh food). If this is the general trend, the Farmer's Market garners that much more business, expands, and replaces the local book shop's place in the community--the community demand for a farmer's market was higher than a local bookstore, the community is now wealthier.
The same principle applies to the manufacture of goods. If you're doing something sloppy, develop a refinement. We didn't get to 3GHz CPUs by overclocking a 486 by 100 times and slapping on a big fan and heat sink; we streamlined the process to be 100 times more efficient, then paid the extra expense to downsize the process, took a smaller efficiency hit, jacked up the CPU speed, and added a big fan. Truth be told, we could run these things at half the speed and find that they last forever, they're a lot faster than the old 486, and they need all of a tiny little heat sink and maybe a fan (maybe not). Instead of building 32nm, we could continue to build 60nm and not pay the expense--but the 60nm equipment has gotten better and we get fewer bad chips and fewer defects and so much longer component life. We're there, we just threw more chips in 'cause we had 'em.
Essentially, we got faster, cheaper, and lower power, all at once. Then, we cranked up the speed, put more dollars into cutting-edge technology, and things became faster, hotter, and more expensive. We've gained wealth, though--we've gained it and we've spent it to get even more speed. We had all of speed, power consumption, and cost, and we paid the cost and power consumption gains back in and opted for even more speed. In the end, though, the output's still bigger than our original input.
We violated the silly "can't have everything" law every step of the way.
Re:Fast, Cheap n' Frigid (Score:5, Funny)
Re: (Score:3, Insightful)
In economics people like to discuss job creators and wealth movement, trickle-up and trickle-down, the loss of businesses, poor people and rich people... but they fail to understand wealth. Take the "shop locally" thing... if you have a local bookstore versus Amazon, people tell you to shop locally because it "keeps the money in the community." Problem is the local bookstore is crap, they order from the big publishers and distributors, etc; some folks argue Walmart or B&N are as bad as Amazon and not like a local bookstore, but their stores still pay local taxes on their income, they still pay rent, hire sales people, and order from the same distributors. Now let's say you order from Amazon because it's $10 cheaper. That money leaves the local community, but $10 stays ... you're $10 wealthier. The local bookstore has terrible selection and is expensive... it goes out of business. Meanwhile you've got a local farmer's market and you shop there with the extra $10 you have. That's wealth creation: you have the same goods (a book) plus more money ($10) to buy other goods (fresh food). If this is the general trend, the Farmer's Market garners that much more business, expands, and replaces the local book shop's place in the community--the community demand for a farmer's market was higher than a local bookstore, the community is now wealthier.
The problem is that the local bookstore doesn't have to be crap to go out of business, and why does someone who decides to save $10 by buying from amazon decide to shop at a farmer's market (less convenient, can be more expensive) instead of a grocery store? I know you have a good point about what makes the community wealthier, but there are advantages to having retail stores in your area beyond price and selection - I like having a downtown to stroll around and look at things in shops, and I know I'm not
Re: (Score:2)
The problem is that the local bookstore doesn't have to be crap to go out of business, and why does someone who decides to save $10 by buying from amazon decide to shop at a farmer's market (less convenient, can be more expensive) instead of a grocery store?
The point was to show wealth creation. In any case the community is less interested in a local bookstore than in having $10; having $10 instead of not having $10 (you have the book either way) is having more. In all cases, something else will replace a failed business--it always does. Usually many somethings--where I live, dozens of businesses start and fail every day; I've been down to town hall to start a business, I've seen how many people come in and out every day, most of them will fail. Something
Re: (Score:3)
"In all cases, something else will replace a failed business--it always does."
Now, that's just flat-out religious belief. Places like Detroit or other pure ghost towns serve as counterexamples.
Re: (Score:2)
Well, there's two different things here - will certain places run out of work or will the world "run out" of work, as certain post-post-post-modern world futurists have predicted. Despite what is happening in the US and parts of Europe, if you look at the BRIC countries (Brazil, Russia, China, India) or the OECD report you'll see that the world isn't exactly running out of jobs, they're just not created in the "Old World". In fact despite all the trouble in the developed world, extreme poverty is on its way
Re: (Score:2)
Re: (Score:2)
Now let's say you order from Amazon because it's $10 cheaper. That money leaves the local community, but $10 stays ... you're $10 wealthier. The local bookstore has terrible selection and is expensive... it goes out of business. Meanwhile you've got a local farmer's market and you shop there with the extra $10 you have. That's wealth creation: you have the same goods (a book) plus more money ($10) to buy other goods (fresh food). If this is the general trend, the Farmer's Market garners that much more business, expands, and replaces the local book shop's place in the community--the community demand for a farmer's market was higher than a local bookstore, the community is now wealthier.
Interesting but oh, so very wrong. And it's wrong because it's a localized and on short term thinking. Its like the joke about drinking alcohol to kill weaker neurons, thus becoming smarter (or the "corporate fat trimming" game)
Let's extend a bit the frame of reference: say all in that community that want books will buy from Amazon and "earn" the $10. The $10 become disposable income and assuming enough of them decide to spend the $10 at Farmer's Market, the price for your vegies will increase - it's only
Re: (Score:2)
As for the meaning of "wealth": ever since the currency was floated, the "absolute wealth" is relative: the society no longer values it, but values "wealth increase rate". Doesn't strike you as peculiar that the finance people never judge an economy by the absolute value of the GDP, but only by the "grow rate"? To put the problem in your term: as big would it be your current output, after so many businesses being shot down (and relocated in China), what are the chances that you'll still be able to stay relevant in the "growing race"? And if you are not able, how long until your "bigger output" will mean exactly nothing?
Well the vast majority of the "poor" in this country--those who the US Census has established are living in abject poverty--own their home (46%), have air conditioning (76%, compared to 36% of all households in the US 30 years ago), are not overcrowded (94%, with over 67% having more than 2 rooms per person in their house), has more living space than the average person (modal average of all--i.e. the middle class) living in European big cities like Paris or London, owns a car (over 70%, with nearly 70% own
Re: (Score:2)
If America weren't a debt society living on the edge of credit and facing imminent foreclosure, I'd say we were pretty wealthy here. As it is, we as a nation have run up our credit cards to the max and can't afford to pay them much longer, and we're just running them up further. All money is loaned into existence, loaned to the banks who loan to the people (businesses, mortgages, credit cards...) who buy stuff and pass those dollars to pay salaries supported ultimately by debt. The Federal Government borrows money from other countries, collecting debt money in taxes, with no asset base to work from. How dysfunctional.
Quite a big if, indeed. Because the wealth defined like this is illusory, as not being sustainable... ran the race in the last 10 years on "performance enhancement drugs"... to bad they not a substitute for real performance.
And what pushed the Americans in living on debt rather than on honest earnings?
In my opinion, exactly the false dichotomy of "be efficient or die" and the corporatist way of action of "profit now, externalize the costs and the risks, responsibility towards the society be damned".
To exemp
Re: (Score:2)
Nah, the answer of artificially funding a business because it's "better for the local economy" is as far off the mark as you can be. It simply doesn't correlate. What do you have then? A local business that's propped up by debt dollars injected into the economy by all the student loans and mortgages. Held for historical reasons, but not practically useful, and essentially acting as a broken window.
The debt economy came from FDR trying to get out of a depression by mandating that mortgages should be 30
Re: (Score:2)
Nah, the answer of artificially funding a business because it's "better for the local economy" is as far off the mark as you can be. It simply doesn't correlate. What do you have then? A local business that's propped up by debt dollars injected into the economy by all the student loans and mortgages. Held for historical reasons, but not practically useful, and essentially acting as a broken window.
Without meaning any disrespect, I'd classify the above as a failure of imagination... (the risks of looking to the world through "principle based, black-and-white only glasses" - one doesn't look how to solve a problem, only how well possible solutions fit to some principle one keeps so dear)
E.g. what about transforming the bookstore in a coffee shop where one can read books? With a minor investment [aliexpress.com], even some eBooks can be made available on tablets owned by the coffee-shop. I know I'd spend some hours (and
Re: (Score:2)
Changing the function of a bookstore is also an indication of a failing business model. If the bookstore can survive on its own, it's just a valuable evolution... unless another bookstore with a coffee shop opens, becomes vastly more popular, and the first bookstore dies out. On the other hand, if the first bookstore was going to die out anyway, they could still try to attract customers by altering the atmosphere. Of course, if the bookstore was going to die out, it means people are going to stop buying
Re: (Score:2)
Changing the function of a bookstore is also an indication of a failing business model.
Wasn't this exactly the scenario that we were discussing? Like "the expensive and crappy bookstore goes out of business. People are actually saving $10 buying from Amazon, so they can reward the local farmers. No damage done to the community if the bookstore goes bankrupt"?
To which I said: maybe there are other possibilities that would worth exploring to keep the local bookstore keeper busy in a beneficial way for the community, even if the bookstore as a business goes under. Maybe
Re: (Score:2)
No, it's the other way around. Closing a local business is a loss for the community on a short term. The building is eventually filled with a new business performing a different function. Alternate scenarios include existing businesses changing around (adding/altering services), or being pre-emptively replaced (a similar business with different services becomes more popular, or a new business appears and people are more interested in spending their extra dollars there--indirect competition).
Claiming an
Re: (Score:2)
No, it's the other way around. Closing a local business is a loss for the community on a short term. The building is eventually filled with a new business performing a different function.
etc...
Well, I feel the community is being affected on long term by job losses, even if business closures may be better on short term. Since there's an "active experiment of this kind" running now in US, I guess we can only wait and see how it will evolve.
Re: (Score:2)
It's short-term because you lose 5 jobs, then a new business opens and hires people again. It'd be long-term if that closed down Wal-Mart was replaced with a derelict parking lot and a crumbling old Wal-Mart building 80 years in the future.
Retail is always hiring. We have like 70% labor participation here and people are wandering the streets complaining they have no job, but the retail and fast food places are hiring like crazy, complaining they can't find employees. I know chronic poor folks that are i
Re: (Score:2)
In economics people like to discuss job creators and wealth movement, trickle-up and trickle-down, the loss of businesses, poor people and rich people... but they fail to understand wealth. Take the "shop locally" thing... if you have a local bookstore versus Amazon, people tell you to shop locally because it "keeps the money in the community." Problem is the local bookstore is crap, they order from the big publishers and distributors, etc; some folks argue Walmart or B&N are as bad as Amazon and not like a local bookstore, but their stores still pay local taxes on their income, they still pay rent, hire sales people, and order from the same distributors.
Now let's say you order from Amazon because it's $10 cheaper. That money leaves the local community, but $10 stays ... you're $10 wealthier. The local bookstore has terrible selection and is expensive... it goes out of business. Meanwhile you've got a local farmer's market and you shop there with the extra $10 you have. That's wealth creation: you have the same goods (a book) plus more money ($10) to buy other goods (fresh food). If this is the general trend, the Farmer's Market garners that much more business, expands, and replaces the local book shop's place in the community--the community demand for a farmer's market was higher than a local bookstore, the community is now wealthier.
This only works in communities that are big enough to absorb the job losses from the bookstore closing. In big cities, the bookstore closes, the workers all eventually get other jobs, often in new industries. The economy expands. Labor is moved to more efficient uses. Everything works great.
In small towns, when the bookstore closes, there might not be any other new industry to pick up the slack. Not only are those people out of work, but lots of other jobs in small towns become obsolete at the same tim
Re: (Score:2)
Mechanization and an increase in product lifespan are much larger, very much different effects. Essentially the same but on a whole different scale--closing a bookstore occurs because the bookstore doesn't supply anything the customers want in one specific location from one outlet. Mechanization eliminates employees because they don't supply anything employers want--same thing, really. Mechanization is, however, not restricted to circumstance; if you can mechanize the production and distribution of books,
Re: (Score:2)
Those things are not really different from an economic perspective. What really matters is that they reflect increases in productivity (some combination of labor productivity and capital productivity). When productivity increases in an industry, a market economy will find other ways to utilize the labor and capital that was saved. The problem I was pointing out was that a market economy may not be able to utilize that labor and capital in the same location. Small towns are much less likely to develop ne
Re: (Score:2)
Optical computing? (Score:3)
Data transmission using photons rather than electrons is better. IBM has figured out how to do parts of that on silicon.
Processing the data using photons instead of silicon might be better too. How much does what IBM has done help us towards being able to produce photonic logic?
Re:Optical computing? (Score:4, Informative)
How much does what IBM has done help us towards being able to produce photonic logic?
None of it. They're just working toward miniaturizing and reducing the cost of these things. https://www.google.com/shopping/product/8819852028889869930?q=LR4%20CFP [google.com]
Translation? (Score:2)
Does it mean we can beat the 3-4Ghz CPU limit?
Or does it mean we can treat DRAM as if it were more like next-to-the-metal L2 cache?
Or does it mean we can have faster internet download speeds or quicker latency?
Re: (Score:2)
1. No, probably not.
2. No, probably not, but in theory may get higher bandwidth, but latency should be similar to current DRAM
3. Probably, should make for cheaper fiber optics transmitters.
4. (which you didn't say). You can electrically disconnect components on a board, aka, not on the same ground plane, less issues with electrical noise and signal propagation.
Re: (Score:2)
.
Now, does it mean we can have faster internet
Big ol' Blue eyes set on the future (Score:1)
I see bussiness
These are exciting times we live on
Logic enters the 4th dimension
Huzzah! (Score:2)
Faster? (Score:3)
Nope. Electrons and photons still moving at the speed of light, which is relatively constant. (c what I did there?!?)
Ok, mostly I'm just being a smart ass. This may improve throughput and/or latency. But our chips are running into constraints due to the fact that the electrons can only go so far in on clock cycle. The stuff is cool, but it's not going to fix those problems.
Re: (Score:2)
Re: (Score:2, Insightful)
Electrons don't move at the speed of light. The electric field generated by moving electrons propagates at the speed of light. In other words, when an electron starts moving at one end of a wire, the electric field propagates down the wire at the speed of light and starts the electrons at the other end moving.
Image sensors (Score:2)
Does this have any use in the image sensor market?
Full Circle (Score:2)
Light wins over electricity. (Score:1)