Fiber On Your Motherboard...Soon!

km790816 writes: "In this post I joked about wanting an optical bus on my PC. In the last week I've seen two articles from The Register and EETimes discussing the real possibility. Both mention high bandwidth and lower heat and power usage. Sounds good to me."

Comments

I've been wondering ...

[WyldOne]

how long this would take. Its getting cheaper to use fiber. The boards are getting tighter packed etc. I wonder if they will design a board that you don't have to swap the motherboard every time a new cpu/bus archetechure comes out.

Backplane anyone? the S100 had it - It was a good idea at the time.

Re:I've been wondering ...

[alienmole]

how long this would take. Its getting cheaper to use fiber. The boards are getting tighter packed etc. I wonder if they will design a board that you don't have to swap the motherboard every time a new cpu/bus archetechure comes out.

Backplane anyone? the S100 had it - It was a good idea at the time.

This could work for CPU upgrades, which is probably one reason manufacturers don't do it - they like built-in obsolescence.

But there's more to it than that. Other than CPU upgrades, the problem with a common bus in the past has been that the bus itself is a limiting factor. Think of commonly used buses and other interconnects, whether PCI, SCSI, IDE, the CPU/RAM FSB, etc. Every one of these has gone through multiple iterations of getting faster. Similiary, every time there was an improvement in backplane performance, you'd need to upgrade your backplane. Typically, during such an upgrade, you also want to upgrade other components, like CPU & RAM - so the most efficient way to do this is with a single motherboard that contains it all.

If it were possible to set up a backplane that had humongous speeds that far outstripped anything the components were capable of, the backplane approach might make more sense. Still, something like that sounds expensive, and actually adds complexity to systems from the point of view of manufacturers and even end users.

Optical on the motherboard..

[ldopa1]

This would put SCSI on the skids. Right now SCSI is the only really fast interface commonly available between devices, but it's cost has kept it from becoming the standard. But if you could just plug in a fiber connection, you'd be rocking. Another thought is that fiber network cards wouldn't be far away. It'd be cool to buy a LinkSys Fiberboard at CompUSA for 30 bucks and be able to network all of your computers in house that way. Of course wireless technology is already pushing the limit farther.

Also, Time magazine reported last year about this, and they pointed out that the kind of speed offered by fiber is the only real bottleneck to creating a truly self aware computer. They also mentioned that MIT was working on a Laser circuit, where logic is figured out by the paths of a laser moving through space.

The only real application of this at the current time is in device to device communications. We'd have to rework all silicon chips to use the new protocols.

Another problem is that we'd still have the silicon-to-light translation bottleneck. i.e. and electrical signal from a pin on a chip needs to be converted to laserlight somehow. To make this truly work, you'd need a chip that reponds via light, and I haven't seen any IC's that communicate via light yet. Of course, I doubt that they are very far around the corner.

Re:Optical on the motherboard..

[Sj0]

Also, Time magazine reported last year about this, and they pointed out that the kind of speed offered by fiber is the only real bottleneck to creating a truly self aware computer.

In that case, Time magazine is filled with idiots. Computers will never be self aware as long as they are the glorified calculators they are.
People who talk about self aware computers are usually ignorant of what computers do. They do not do incredible things, they do what they are programmed to do. One cannot program in self awareness. The closest we can get is a convincing emulation of self awareness. if you write a program to print "I think therefore I am" on the screen, the computer doesn't suddenly see any value or meaning in those words, simply a string of Ascii characters. Even with the hal project (remeber that article?), all they accomplished was a sophisticated simulation using years of statistical data of what a self aware organism may say, NOT self awareness itself. the greatest emulation is still an emulation. Science fiction paints a strange picture that powerful computers will eventually become sentient. This is mistaken. Build the worlds fastest and most powerful calculator, and you still have to press 1+1 in order to get it to answer the question -- and the computer will never ask the question...Unless we tell it to.

Re:Optical on the motherboard..

[maggard]

Also, Time magazine reported last year about this, and they pointed out that the kind of speed offered by fiber is the only real bottleneck to creating a truly self aware computer.

Oh please, that old canard about intelligence spontaniously arising out of sufficient processing power.

Throwing hardware at AI hasn't resulted in any fundamental breakthroughs and it isn't likely to. Oh it makes things happen more in scale with us and enables a lot larger cycle budget for increasingly lower-yield strategies but it's really just more of the same.

Self-organizing systems and emergent complexity happen due to underlying architecture. Life has had billons of years and the best incentive possible to evolve this - we're only now beginning to understand the subject.

Assembling a computer with the speed and density of a human brain won't mean it'll suddenly magically become self-aware, open it's IO and and engage us in conversation.

Re:Optical on the motherboard..

[sharkey]

God, can you imagine a self-aware Windows PC?

"Those look like comfortable VBS"
"Life is like a Microsoft EULA. You never know what your gonna get."
"I don't know much about metadata, but I think every file needs a proper extension."

Re:Optical on the motherboard..

[mskfisher]

Well put. It's like saying "if we add enough horsepower to that car, it'll turn into plutonium!"

Computers are not inherently self-aware...
making them more of what they are won't change them into something else.

Cool, people finally starting to publish

[bstrahm]

I love hearing that people are finally starting to publish intentions. I have been hearing rumors about this for a year or so now, since an EVP where I worked started talking about plugging a Fibre into the side of the microprocessor (and he wanted to own that connection)
As is normal, he missed completely thinking it would be a 10GbE fiber for networking, rather than a 40+GB connection to main memory...

The comments on working on the I/O side of the processor were right on (I read the EETimes article, rather than the Register article to get "real" facts ). For years Sun was known for having the slowest RISC processor in the business, however they had the fastest boxes. No one seemed to understand this, until they realized that they were running multiple 128 bit memory buses at rather good clock rates. That was better than 10 years ago, and just now we are starting to see memory busses approaching this level in their competitors hardware.

Re:First post on this one

[Water Paradox]

Of course it will have a 20 second "Slow Down, Cowboy!" timer. That's how long it will take to boot XP 2002. Linux will, of course, boot in .3 seconds on that motherboard.

From the article: "But it may not take divine intervention to get more mileage out of copper interconnect. Intel claims it can reach speeds of 10 GHz and beyond in five to eight years using copper. "We're confident we can get to 10 GHz. And there's reason to believe we can double that," Pinfold said."

I'd put my money on copper; we're still using
gasoline, when hydrogen-powered cars have
been viable for years.

http://www.auto.com/industry/iwirn22_20010822.ht m

-wp

What about extension cards ?

[Rosco P. Coltrane]

I've seen telco people install fiber in our offices, and they had to brind a hugely expensive machine with some kind of microscope and mounts to splice and "weld" 2 fiber optic cables together (sort of like how audio tapes were spliced and glue together in the old days). On top of the price of the machine (100000 GPB if I remember), the procedure looked delicate and required quite a lot of skill from the technicians.

So, in a totally optical computer, how are they going to solve the problem of extension cards ? if the optical signals are converted back to electric signals so people can connects daughterboards, I assume it would defeat the purpose. If the optical signals are kept optical, are they going to invent some kind of optical connector to pass it across the "bus" ? I can't see people doing what those BT guys did in our office.

Optical links to the CPU?

[Rackemup]

Promises Promises... optical computing was promised a long time ago, along with persistant RAM and lots of other vapourware. The problem with optical computing is how to trap and store the light...

Maybe this is an intermediary step.. instead of trying to do everything with light we'll start with the component connectors and go from there.

Having several high-bandwidth optical links to the CPU would definatly speed things up, but there will always be another bottleneck to deal with.... I'd be more concerned with the optical/digital conversion process that would have to take place every time a new signal is sent. Wouldnt that be a lot of overhead?

And don't forget the new Serial ATA standard that's supposed to greatly speed up the transfer speeds for hard drives... still another way of using good old metal connectors.

I'm not picky, I'll take any system performance enhancements I can get.

Fiber vs. Fibre

[crow]

It is important to note that this is really about fiber, not fibre. So it really is about optics, not the fibre channel storage interface.

For reference, fibre channel is a high end storage interconnect which is replacing SCSI in corporate data centers. While fibre channel was designed with optical transport in mind, it also runs over copper. While I would not be surprised to hear about high-end server motherboards with fibre channel on the motherboard (instead of IDE or SCSI), that would be a far less interesting story than having actual optical transmission on the motherboard.

Cool.

fiber vs copper

[headwick]

Does that mean magic light instead of magic smoke will come out of the board when it gets fried?

Add fibre to your PC

[sharkey]

The TV-only Limited Offer of Tomorrow:

"Our New, Improved Motherboards have Fibre Added!! This will loosen your pipes, and help Windows shit itself faster and easier! Be the first on your block to own one!"

I love the smell of vapor in the morning

[bflong]

Honestly...
There is no way this is going to be useful in consumer grade pc's for a long, long time. The only possible use I can see is ultra-high-end servers and graphics boxes that cost >$200K and thats not for another 5 years. Right now, we have a glut of processing power in our pc's. Dual Athlon 1.5ghz? Are you nutz? I'm still amazed by how fast my 1ghz tbird is! We need processers and internal components that are more reliable and do more, not just do the same things faster.
Who the hell needs 10,000fps in quake, anyway... :)

Re:Not a troll

[RollingThunder]

While most folks are correct in that the biggest latency source is the drives right now, there is a fair bottleneck on the RAM to CPU bus. I think it's up around a 8:1 ratio right now (4:1 if you have a 266 MHz FSB), which means that your CPU can spend a large portion of its time waiting for data from memory.

True, that's what the L1 and L2 cache are supposed to prevent, but some apps (games, mostly) blow through that cache without even thinking about it. WWIIOnline, for instance, gets bitchy with only 256MB. It's only happy once you have 512MB. How long will even a 4 MB on-die cache last?

If we can increase the speed that we can toss bits between the CPU and RAM, we'll reduce one more sticking point (and RDRAM, expensive as it is, was meant to do that), and higher framerates for all! :)

Free space optical busses

[maggard]

There's been some interesting discussion recently about shifting data transmission off of electrical busses within computers.

The idea is that subsystems could communicate within a computer chassis entirely by light across open space or reflected off of the interior of the chassis. Instead of the complex process of wiring hundreds of chip leads down into packaging all of the data would be sent off and on the chip by tiny lasers & receivers, all built into the chip itself during fabrication. Through a window on the chip case and the CPU could "see" the RAM controller, perhaps even the RAM directly, the graphics controller, the high-speed IO subsystems, etc.

Card edge connectors would still be used for electrical supply and some signaling but it'd be relegated to slow-speed stuff. This would greatly simplify motherboard design as well as chip packaging. Of course this would come with it's own problem: Dust would be a showstopper. Reflections - their propagation and interference properties would become issues. The signaling systems might require an uneconomical transistor count on the chips. Overclockers would obsess about albedo and air filters.

I'm trying to find some good links for this but not finding any - anyone else come across any good discussion on this recently?

Re:Free space optical busses

[maggard]

Reflection. It need not be line-of-sight. (I really thought I made that clear.) Indeed that was what the research I was reading was about: How to handle reflections and other aberations with a low transistor count.

The plus would be that you'd not need point-to-point optical cables or some sort of optical router. Put a device in the case, give it electricity and it could "see", directly or indirectly all of the other components.

Re:Free space optical busses

[maggard]

But what happens when the computer frame is bent a fraction of a degree. How can one possibly compensate for that and keep the sizes so small.

Everything would have to be right up against eachother and secured beyond firmly.

No - you're completely missing the design.

Imagine you're inside one of these next-gen computers. The bus inside the computer supplies power and low-frequency signalling. Arrayed across the mother board and daughter cards are these next-gen optical IO chips.

Instead of an opaque case these chips have a window transparent to whatever frequency is being used. Wherever on a traditionial chip the circuitry would head off to a lead in this case there's a tiny solid-state laser & adjacent reciever (with some support circuitry.)

Whenever a signal needs to be sent the laser serving as an optical IO point fires. They may differ in frequency, they may use coded pulses of light, however it works they'd be addressable. These picosecond flashes of light illuminate the interior of the PC bathing the other components in varying degrees of brightness.

Whatever other component is being address recieves the signal with it's own optical IO point and acts on it, replying back with it's own coded flash of light.

No line-of-sight is required as long as the primary reflective surfaces in the case have a high enough albedo and sufficient light scattering ability. If you need an anology imagine a bunch of kids flashing signals to each other with flashlights in the woods. Oftentimes one won't see another hidden behind a tree but the light reflecting off nearby bushes reflect the signal.

Some of the proposed benefits:

• Significent amounts of complex high-speed IO is taken off of the backplane and optically transmitted (directly & indirectly.)
• Greatly lessened signal-noise problems and EMF transmissions. Todays PC's are moving from being little radio broadcasters to little microwave ovens - this would obviate much of that problem.
• The lasers and recievers can be built into the chips using conventonial photolithographic processes.
• The chips would be cheaper to manufacture then traditionial ones as the number of complex pads connecting the chips to their carriers and then to the pins would be decreased by an order of magnitude.
• Internally the chip's subsystems wouldn't require routing to outside edges - optical IO points could be put wherever on the chip surface most convenient.
• Bandwith shouldn't be a problem as the frequencies are certianly high enough.

Re:Question

[tswinzig]

HOWEVER if it doesn't, does this mean that there will be random strips on my m-board that will glow from fiberoptic cables passing data back and forth.... I might have to build a clear case if something like that happens!

I'm not fiber optic guru, but if the wire is glowing, that means light (information, in this case), is escaping out of the wire before it reaches its destination. Not a good thing, right?

The problem

[Uttles]

The problem with this is that ever single component on the motherboard that uses the bus will need a redesign in order to communicate over a fiber bus. It's something that definitely can and will be done, but it's not going to be "soon." It also won't be cheap. Why do you think they keep making new RAM that's not backwards compatible? Becuase the old stuff is almost as good and is dirt cheap. When they start making fiber ready hard drives and such, they are going to charge an arm and a leg. One positive: the normal stuff will then go dirt cheap, but they'll probably stop makign it after a few months or so.

Re:Question

[sharkey]

Kind of like the "Visible Computer" from the Knowledgeum on the Simpson's?

Frink: The section now illuminated is the floating point unit. One of my personal favorite units.
Bart: How do you get this thing to play Blackjack?
Frink: Stop that, you're hurting it.
Bart: So how is it supposed to work?
Frink: Well...
Bart: Boring. Am I on the Internet?
Frink: No, you can only access the...
Bart: Boring! What's that fire for?
Nerd: The hard drive is crashing at an alarming speed!
Frink: No more pictures!

Re:Fibre on-board

[.sig]

Well, nothing new is usually cost-effective. The point is, though, that after it's been the expensive high-end for awhile, it'll eventually get cheaper and cheaper to make, and thus sell. Eventually even the cheap motherboards will all be optical. (Assuming that it's sucessfull)

There are reasonably priced motherboards out there, but if you want the latest and greatest technologies, you're going to have to pay for them.

Is it practical yet?

[Mike McTernan]

I'm sure I've seen this discussed before and that a number of problems exist with an optical bus in a non-optical system.

Firstly, the length of the bus on a motherboard is so short that there are few real gains over a copper/gold track, and those gains that are made are outweighed by the encoders/decoders that do the photonelectron conversions.

Also, it would probably put the cost of add-in cards up since the row of gold contacts has to be replaced with something far more sophistocated.

Also, one of the problems with existing bandwidth to the memory is not only the speed, but also the bus width. Unfortunately a wider bus gives more bandwidth (assumming that data lines are added, and not address), but also means more pins on the chip, which costs more.

In a pure optical system, it maybe possible to eliminate all these problems, but I'm not convinced from what I have read that it is a solution for todays computers...

Serial communications & SCSI

[Klox]

I just wanted to address two types of comments I've seen posted here:

* Encoding / decoding speeds are done at the speed of the medium. Encoding and decoding optical signals doesn't have any more overhead than PCI or IDE. The spec. writers and endec designers are well aware of these issues. That's why technologies like 10Gb Fibre Channel or Eithernet aren't ready yet -- not because we can't transmit at that speed, but that we can't build an entire NIC to sustain those speeds. (Give us some time: we'll be there soon enough.)

* Serial interfaces like Fibre Channel and Infiniband (and even Gigabit Eithernet) aren't replacing SCSI. They are replacing what you think of as SCSI: the 50 or 68-pin cable in your case. But SCSI is the protocol being used to talk to all those FC & Gig-E storage devices. SCSI over FC is called FCP (see T11's specs for more on FC). For Gig-E, most companies are looking into iSCSI, iFCP or FCIP (SCSI over IP or SCSI over FC over IP) for SAN-to-SAN communications. I forget the name of the spec for SCSI over Infiniband, but it pretty much rips it's ideas from the above specs. (sorry, no links for Gig-E and Infiniband at the moment: start at T10 or The SCSI Trade Association)

BTW, I refer to "serial interfaces" above instead of "optical interfaces" because a lot of this is actually copper. Most likely, Infiniband on the motherboard will be copper and off the motherboard it will be optical. Most of the Fibre Channel equipment I have isn't "fibre" but copper.

Intel's serial obsession?

[MrResistor]

I've had serious doubts about the actual advantages of Intel's obsession with putting everything on high-clock serial busses, rather than lower-clock paralell busses that seem to provide the same bandwidth with less heat, interferance, and latency.

However, optical fiber would eliminate interferance, which seems to be the main barrier on clock speed. Heat would likely be reduced also, and cranking up the clock-speed would likely eliminate the latency issues. Not to mention the cool-factor inherent in optical.

What would be really cool would be to replace firewire and USB with fiber. There are hybrid fiber coax systems that could provide whatever power you're mouse/keyboard/etc would need, up to a certain point anyway. It probably wouldn't be enough to power an external drive.

Re:speed up HD's

[gmhowell]

I'm not sure that it is a troll. I can definately see the uses for this. Load everything except your data into the ramdisk. Granted, moving the mp3's off the drive and onto the ethernet might be a pain, but I imagine that loading of shared libraries, etc. would go pretty damned quick. Ditto for spawned processes.

Now, in a large environment, 4GB likely wouldn't be enough for the RAM that the programs use as well as a usable RAMdisk, but for the home environment, it could work.

Problem with that is that the benefits would probably be least in that environment. But, it would eliminate my concern about yanking the power cord accidentally, or the CA brown/blackouts you alluded to. OTOOH (on the other other hand) Does replaying the journal (you are using a journaling fs, aren't you?) take any less time than loading up the RAM disk in the first place? Probably not. But, if you are still on ext2, it makes sense. Put / on RAM. Then, even though loading the RAMdisk would be a long time, it wouldn't be much longer than fsck, but you don't have to worry about a hosed disk. (But, again... If you have 4GB of RAM, you are probably savvy enough to have ext3, Reiser, etc.)

I don't know. I give up. It's a valid question, but I don't think it's a troll. But the answer is most definately, 100% "it depends".

fiber on motherboard

[NaturePhotog]

I already have fiber on my motherboard. Well, OK, technically it's cat fur sucked in through the vents, but that's got a lot of fiber. And it uses absolutely *no* power. The heat retention is a problem, though.

About buses

[petis]

The reason that buses that uses photons as the data carriers are coming up is quite interesting. The good thing with light (photons) are that photons are 'bosons', which amongst other things means that they do not interact with other photons. Good for transporting data, since noise is not a problem.

Electrons, on the other hand are 'fermions', which means that they interact strongly with other electrons. That is good for logic (since the whole point is to interact..), but is a problem for transports. (Cross talk etc)

From a power consumption point of view, using currents/voltage in a wire to send a logic one ore zero has some really severe problems. The wire itself introduces a resistance, capacitance and inductance which are non neglectible, at least not for long wires (buses) or high frequencies. IIRC, R ~ sqrt(f) for high frequencies, which leads to signal distortion, power loss, and ultimately an upper limit to the data rate. This is probably one of the reasons that research and development is going on in this area.

Re:I wonder

[Chundra]

Someone, quick, moderate this either:

+1 Enteresting or
+1 Enformative

;-)

Interesting combinations of technology

[Mordain]

The use of fiber on motherboards and similar devices has some huge advantages. First board density would quadruple. With DWDM whole busses from chip to chip would be replaced with single fiber lines. This would increase the number of components drasticly and also reduce electrical feedback from bus crossovers. Imagine building boards where the only consideration is where to place things asthetically?

The downsides are of course that every chip will have to have fiber PHY built in? or at least have on for every chip. This could be an even worse problem in the long run.

Re:Not a troll

[gorilla]

I don't know about this specific instance, but in general, optical is better than electrical because it's not vunerable to electromagnetic interference causing noise on the signal. I also know that modern CPUs and other high speed components generate a lot of noise - ever tried to use an AM radio next to a computer, it's not easy. This noise both consumes power, and makes it difficult to route connections, if they are too close then they will interfere with each other and not work. If the route is too long, then it won't work either. Using optical connections could mean that the layout of boards could be simplified, and therefore use less power.

SCSI, optical

[sigwinch]

This would put SCSI on the skids. Right now SCSI is the only really fast interface commonly available between devices, but it's cost has kept it from becoming the standard. But if you could just plug in a fiber connection, you'd be rocking.

SCSI is rather physical layer agnostic. It already runs on at least four totally different electrical layers: high-volvage single-ended, high-voltage differential, low-voltage differential, fibre channel (which can be copper, despite the name). Optical SCSI would be just another physical layer. The real value of SCSI is that it is very nicely tailored to mass storage devices.

Another problem is that we'd still have the silicon-to-light translation bottleneck. i.e. and electrical signal from a pin on a chip needs to be converted to laserlight somehow. To make this truly work, you'd need a chip that reponds via light, ...

Yup, that's the real challenge. Speaking from personal experience with optical chip modules, getting fiber/light to the chip is major pain in the ass. The mechanical design challenges are significant and obnoxious.

Re:Fibre on-board

[Boulder Geek]

Seems to me that ability to attain high motherboard speeds isn't as much of an issues as getting one that is reasonably priced.

I think you're nuts. High motherboard and I/O speeds are exactly what's needed. With reasonably fast (by today's standards) mobos based on the SiS735 available at ~$60 street, I don't see why we need cheaper mobos. Fiber interconnects to main memory (provided they keep the latency down!) could make a real difference. Imagine if main memory behaved more like cache. I'd be willing to pay more for that, at least for a database and compute servers.

Re:Not a troll

[foobar104]

how much of a bottleneck is the bus right now?

This info is a little out of date-- it comes from Practical Unix Programming by Robbins and Robbins, published in '96.

It's a table of access times, scaled so 10 ns is equal to 1 second.

Processor cycle: 1 second
Cache access: 3 seconds
Memory access: 20 seconds
Context switch: 166 minutes
Disk access: 11 days

Notice that this table doesn't discuss bus bandwidths. The reason is simple: latency is more important than bus bandwidth for these kinds of comparisons. It doesn't matter if you can suck in 800 MB per second from RAM to CPU if getting that first byte still takes many nanoseconds.

In short, for normal server or desktop tasks, bus bandwidth isn't a serious bottleneck at all. But for traditional HPC applications, where a processor takes a huge chunk of data (measured at least in 10s of megabytes) and operates on it serially, from front to back, your bus and memory bottlenecks start to show through.

It's kind of analogous to having a car with a top speed of 250 MPH and a 0-60 time of four minutes. On the highway, once you get up to speed, you'll cruise along nicely. (Think of that as big serial computations.) But in stop-and-go traffic in the city, you're sucking. (Typical branching programs that depend on user input.)