Sun Working to Eliminate Circuit Boards 349
lokedhs writes "Sun Microsystems is coming out with new chips without connectors. According to the article, this will have a lot of advantages: 'Performance, for instance, could greatly escalate because the speed of transferring data among chips and the number of channels for the transfers would increase. Energy consumption could also decline. Just as important, overall costs could fall, because defective chips could be removed like Scrabble tiles.' This technology will also lead to new CPU's without cache: 'The technique could also allow designers to remove the cache--the large pool of memory currently found on the processor--and put it on a separate chip. Caches were integrated onto processors to amplify bandwidth. Adding cache, however, bumps up manufacturing costs, as it greatly increases the number of transistors. With the bandwidth constraint gone, caches could once again be made independent without it having an impact on performance.'"
Heat... (Score:4, Informative)
Interesting technology, thought.
Re:Heat... (Score:5, Insightful)
The great thing about circuit boards is that they're cheap and easy to replace, so the maintenance gains they're talking about are not as great as they claim. It's also a VERY well understood tech; Sun takes a substantial risk by going in a totally different direction. It will be interesting to see how it plays out.
Re:Heat... (Score:5, Interesting)
FYI: The power issue is only going to get worse at smaller geometries.
Roughtly: Power = Switching Power + Leakage Power + Others.
The two we are interested in here is the Switching Power and the Leakage power. Up until now Switching power has been the greedy party, but when geometries shrink down to 90nm and below, leakage power really kicks in.
IBM and AMD have done some nifty stuff with strained silicon and silicon on insolutor to try and reduce the leakage power (and therefore the heat).
So heat really will not be solved by just taking it away faster - because there's a whole lot more of it lurking around the corner, to fix the heat issue, you have to fix the cause not the symptom.
Re:Heat... (Score:2)
Re:Heat... (Score:3, Informative)
Re:Heat... (Score:4, Interesting)
Interlocking chips (Score:5, Funny)
Re:Heat... (Score:2)
It's still a 2-D plane (I think), so it's nothing that a long heatsink and case fans can't handle.
Oversimplified (Score:2, Interesting)
Re:Oversimplified (Score:5, Interesting)
If cost effective, and if they can get past the alignment issues, this is spectacular.
Re:Oversimplified (Score:5, Funny)
Wow, were back to my old 386 PC!
Re:Oversimplified (Score:4, Insightful)
Wireless Communcation (Score:4, Interesting)
Re:Wireless Communcation (Score:2, Insightful)
Re:Wireless Communcation (Score:2)
Imagine you have a 32bit data bus - in every single clock cycle, each of the 32 pins can change their state. If you receive a 0 from one pin, and a 1 from the other, how do you tell them apart?
You can solve the problem by putting the data into a frame, building a checksum and discarding the frame - but that only helps if frame collisions are rare, if every single frame has
Re:Wireless Communcation (Score:3, Informative)
Didn't say to get rid of circuit boards (Score:4, Informative)
Re:Didn't say to get rid of circuit boards (Score:2, Funny)
"There is a huge need for higher-bandwidth kind of chips," Robert Drost, a senior researcher at Sun Labs, said at an open house last week. "Rather than have the chips soldered onto a printed circuit board, the printed circuit board is taken out of the system."
Re:Didn't say to get rid of circuit boards (Score:5, Insightful)
Ha! That's the funniest mis-use of electronics terms I've seen in quite a while.
Yeah I know this is OT/FB but what the hell.
-nB
Re:Didn't say to get rid of circuit boards (Score:4, Insightful)
An indutcotor, is like a heavy train, it takes time to get it moving, but when it is moving it takes time to change it. So it is very good at blocking AC signals (they try to move back and forward at high speed, ie constantly changing) but passing DC.
A capacitor is like a condom, you can fill it, and empty it but you cannot go through it, however it is possible to pass an alternating signal to your partner though it during sex. So they are good at passing AC signals and blocking DC.
God, I hope thats the right way round.
Sun developed something? (Score:5, Funny)
Love,
Zaq
Re:Sun developed something? (Score:3, Funny)
Re:Sun developed something? (Score:2, Informative)
Re:Sun developed something? (Score:3, Interesting)
Anyone watch Stargate? (Score:2, Funny)
Either way, I'm thrilled and spooked.
Um...who repairs motherboards anymore? (Score:3, Insightful)
If there's a high-end application for this technology, great, but getting rid of high-end hardware is one of the biggest reasons people are also getting rid of Sun...
Re:Um...who repairs motherboards anymore? (Score:3, Insightful)
Space (Score:4, Interesting)
Re:Space (Score:3, Insightful)
That is why this kind of technology [atmel.com] is used in embeded systems for years. Stack EEPROM and RAM on eachother in one housing to save space.
10-pt tiles? (Score:5, Funny)
With my luck I'll get a dead Pentium Z or Q that I just can't get rid of.
Prime Intellect? (Score:4, Interesting)
Re:Prime Intellect? (Score:3, Funny)
kuro5hin link on slashdot? Go fark yourself.
Power (Score:4, Insightful)
Most likely, the capacitive coupling of signals is only targeting chip to chip data signals, not the supply of power to the chips.
Re:Power (Score:3, Insightful)
Also, there are EMI issues with the specific arrangement you mentioned (side by side pads) relating to something called inductive loops. The skin effect would basically say that all of your highfrequency currents would return along the edges of your big pads, leaving a big loop
Even better! (Score:5, Funny)
Re:Even better! (Score:2)
Observations from a prototype lab... (Score:2, Interesting)
Heat transfer is also a pro
Heat? Naw. Here's some better problems. (Score:5, Insightful)
And a more interesting topic is their consistent mentioning of taking the cache of the chip. That's a nice dream and all, but where the hell are you going to put it then? Hardwired onto the motherboard? That's going to dramatically increase the cost of mobo's (so they are simply shifting who gets to eat the high sticker price on their products). And what if I buy a quad capable mobo, but only put 2 processors on it, I'm effectively wasting 2 sets of cache, rather than simply wasting 2 cpu sockets, and the sockets are a hell of a lot cheaper than the cache. I suppose you could fix this by going back to COAST (cache on a stick, yeah i know you remember that nasty stuff). But that brings in a whole new problem: These days, cache is only fast because it's so close to the cpu. If they move it off the die, it's just going to be put back on in 2 years because we can't access the cache fast enough ever since we moved it off the die.
I'm no super computer engineer, but these guys better have an entire family of rabbits they plan on pulling out of their asses or this fucker's gonna flop.
Re:Heat? Naw. Here's some better problems. (Score:3, Insightful)
For example, they might be able to tune a process to give higher yields on the cache and have a second process for the logic. Less broken chips, more stuff to se
Re:Heat? Naw. Here's some better problems. (Score:2)
Re:Heat? Naw. Here's some better problems. (Score:3, Interesting)
Re:Heat? Naw. Here's some better problems. (Score:5, Interesting)
Well, if they invent a very good self-aligning mounting socket, dirt can be dealt with just by being very careful and using one of those air-in-a-can dusters. This technology would be very expensive, initially, so you could even get one of Sun's guys to come out and do it for you.
That's a nice dream and all, but where the hell are you going to put it then?
I'd bet they put it nowhere. L2 and L3 caches are a kludge, and, if they really achieve huge chip-to-chip bandwidth, they just might not need the cache hierarchy. This is reminiscent of old CPUs, where the system RAM ran at an acceptably large fraction of the speed of the CPU, so there was no L2 cache at all.
Re:Heat? Naw. Here's some better problems. (Score:3, Insightful)
To me, it would seem like some sort of cache would still be needed. As I understand things, even if a slow bus was eliminated, it still takes the RAM much longer to look up data than the CPU is c
Re:Heat? Naw. Here's some better problems. (Score:4, Insightful)
It's called a clean room dude, and it's distinctly Old Tech. Granted, this will cut into the vision of pushing this out into the hands of field engineers, but I suspect that Sun is visualizing a "processor assembly" that will plug into an otherwise conventional motherboard. Perhaps in the distant future, that might change, but not now. What this ends up meaning is that they have two separate fabs making smaller chips rather than one fab making gigantic chips. It is much easier to make three or four small chips without errors than one huge chip, so they get higher yields for their processors. This means that they can produce a "processor assembly" with some ridiculous amount of cache and 8 cores for a much lower price than would be possible with conventional tech.
The whole point of this tech is to directly connect the cache to the processor without putting it on chip. No, it won't be on the MoBo. Instead, it will be on the "processor" - but the "processor" will have multiple chips in it.
I'm partially speculating here, but I bet that's what's on their mind.
Dupe (Score:5, Informative)
http://slashdot.org/articles/03/09/22/1055244.sht
jdb2
And if you're too lazy to use Google... (Score:3, Informative)
http://research.sun.com/async/Publications/KPDisc
jdb2
Same speed need? (Score:3, Interesting)
If designed, however, this could allow admins to assign quickie chips to the OLTP (or DSS batch loads @ night) systems, and the slower CPUs to the less intensive tasks (like sys admin).
Security (Score:3, Insightful)
Re:Security (Score:2)
> drop a survailiance device in it, or near it
And how are you going to interpret the signals? Humm?
The idea is to replace the physical pins with capacitive coupling in order to _increase_ the desity. Ok, so we are already talking about several hundred pins on a modern CPU. If this technology works, that will jump up to a solid thousand. Then you start stacking them.
So, even if your radio could detect a signal designed to be picked up by an adjacent
Lasers? (Score:2)
Seems like all that capacitive coupling would cause heat and e/m interference problems. Why couldn't you use LED lasers and sensors built onto the chips to optically couple adjacent chips through a simple optical connection? Each side of a square package could have a laser transmitter and a receiver so it could communicate with up to four adjacent chips. Dust in the sensors would be a problem. So would misaligned components. But, that would do the same thing, no?
Just wondering 'cause, you know, I got no
Re:Lasers? (Score:2, Insightful)
[OFFTOPIC] Explanation of 503s? Post here (Score:4, Interesting)
Does anyone have any idea what's going on here? I can't be the only one who wishes for a front-page story explaining why Slashdot is so amazingly unreliable and broken lately--especially for subscribers who are paying $ for this service.
Re:[OFFTOPIC] Explanation of 503s? Post here (Score:3, Informative)
However, it's probably not a place to discuss it unless you have something to contribute to resolving it.
Re:[OFFTOPIC] Explanation of 503s? Post here (Score:5, Funny)
More than one or two chips (Score:2, Interesting)
"Sun Invents Positronic Brain" (Score:5, Funny)
Re:"Sun Invents Positronic Brain" (Score:2)
They are getting out of hardware, buying a software house. What's next is getting rid of all the engineers (everything can be "outsourced"), and hiring a bunch of IP lawyers. We've seen this scenario, right?
Re:"Sun Invents Positronic Brain" (Score:2, Funny)
Yes, but it will be tied to their stock price, for very hard to explain technical reasons, so some days it will be called a negatronic brain. For the Trekkies out there, Data and Lore are really the same android, just in positronic and negatronic modes. Those scenes where they stand side-by-side...well, a wizard did it.
Important info (Score:5, Informative)
Alignment (Score:2)
Re:Alignment (Score:2)
If you've ever seen a chip bonded to the carrier you'll know that the distance between pads is very very small - aligning these chips by hand would be impossible. (Also moving an actual chip die manually is difficult -
Practical Wafer-Scale Integration (Score:2)
What about clusters? (Score:2)
this kind of flexibility would be the only point going down this path imo.
OT: why is slashdot's uptime now a matter of hours?
Sounds interesting, but they need not manufacture (Score:2, Interesting)
As an aside, I guess I'll have to stop Gaff Taping [webring.com] my CPU into the socket.
Advances in Artificial Organs... (Score:2)
Oh, wait, they did. Sorry, Darl.
Just like Legos (Score:3, Interesting)
Sun should get some priorities. (Score:4, Insightful)
Could have many benefits (Score:4, Informative)
As for the technique of capacitive coupling, that is how signals used to pass through low voltage amps virtually since the triode tube. The technique has been used for isolation amplifiers for many years. The signal on one side of the voltage barrier is digitised in some way (perhaps just PCM) and transmitted across a voltage barrier using very small capacitors, to where it is decoded. In some cases, power for the input side is also transmitted by capacitive coupling across the barrier.
Because the transmitting and receiving side of the capacitors is so tiny and the electric field therefore so constrained, it is not going to be possible to read the signals with an external aerial.
I believe Philips, among others, earlier suggested using LEDs and photodiodes along the edges of packages, but appart from requiring power they could only be unidirectional. Capacitive coupling itself absorbs begligible power and can be fully bidirectional.
have fun at it, sun (Score:2)
isn't the market moving in the opposite direction, towards demanding cheap commodity solutions?
just asking....
write-only memory? (Score:2)
Benefits beyond computers (Score:4, Interesting)
BTM
Re:Benefits beyond computers (Score:3, Informative)
Nerve cells already work this way. There is no physical contact between the axons and dendrites. They come very, very close to each other. A potential wave (electric pulse) travels from the nerve soma down the axon, where it causes a huge number of neurotransmitter-filled vacuoles
Read the technical paper and patent (Score:3, Interesting)
Sun is not "coming out with new chips without connectors". Sun has demonstrated a new kind of interconnect in a lab. They might use it in a DoD funded supercomputer project. Maybe.
You're not going to "stack chips like Scrabble tiles". The unpackaged chips have to be aligned within a few microns and held in position. That's going to be done in an IC packaging facility. The result will be a multi-chip module, a single package containing several chips.
Multi-chip modules have been around for a long time. The Pentium Pro, for example, was a multi-chip module. There's a multi-chip module Linux computer in a single package [axis.com] from ETRAX. Multi-chip modules are expensive and hard to manufacture, and they're generally used only when you need to combine chips that couldn't be manufactured on the same substrate, like a fast CPU and flash memory. They usually cost more than the chips packaged individually. That's why this isn't a mainstream technology.
This new approach might revive the multi-chip module market. Might. This has to become a cheap process before it will be used outside the supercomputer world. A whole generation of automated assembly machinery has to be developed to assemble and align chips in multi-chip modules before this is more than a demo technology. But this looks more promising than the way multi-chip modules are currently made. If it becomes cheaper to put two chips in one package than to put two chips in two packages, this is a significant development. Otherwise, not.
For everyone bitching about OSS and (Score:3, Interesting)
OSS is bringing down the overall value of computing, which is a good thing for all of us. The increased competition means the big players must begin to really innovate of die slow. The stuff we use everyday should be cheap. Intel did its job on the hardware side of things, OSS is working hard on the Software side.
This is the Sun I am used to seeing. I have said before, their value is in their people --nice to see them putting it to use.
Sun's research paper about this (Score:3, Informative)
They actually have a bunch of interesting papers in the parent directory here [sun.com], mostly covering stuff about asynchronous/clockless computing.
Good for hobbyists (Score:3, Interesting)
In manufacturing, the trend is still to integrate more and more on a single die. The cache will still be on the CPU but in addition, so will the system memory, graphics chip, and power supply. One day the 120V AC power cord will plug directly into the CPU.
Nothing to do with printed circuit boards (Score:3, Informative)
What this will let chip makers do is to manufacture the cpu and cache on separate silicon wafers, then stack them together and package them as a unit. The researchers claim a speed of 21.6 Gigabits/second using a 4x4 matrix of transmitters. Perhaps we'll see processors being sold with X Gig of memory on-board, with X being the amount of memory that can be manufactured in the same space as the CPU. Perhaps additional processors could be stacked together as well. Imagine putting 4 CPU's and 4 Gig of memory into a spot on a motherboard that takes 1 CPU today. You will still need a printed circuit board to connect to the circuitry that handles the external devices, ports, slots, etc.
Re:eh? (Score:5, Funny)
They should get together with Pringles [pringles.com] or Lays [laysstax.com] -- they've both been doing this for a while...
Re:eh? (Score:2, Funny)
As long as they don't bring olestra into the mix.
Re:eh? (Score:2, Informative)
Re:eh? (Score:2)
You need cooling and shielding (Score:5, Informative)
The problem with capacitive connections is that you are, for all intents and purposes, using small radio links. This causes several issues to come to the fore:
- Your immunity to cross-talk goes down. Misalignment will exacerbate these problems.
- Capacitive receivers will also be able to pick up local RF fields. The computer will be much more vulnerable to external interference than it was before.
- The computer will also radiate much more than it did before, creating more RFI and leaking information that might be crucial (like crypto keys).
Making the chips the meat in a sandwich with metal sheets for the bread would help this a lot, because tightly coupled ground planes attenuate both radiation and reception. As long as you're putting a ground plane on top of the assembly it might as well do double duty as a cooling device, though I wonder what effect the heat-transfer compounds would have on transmission and crosstalk.Re:You need cooling and shielding (Score:4, Interesting)
Instead of screwball stuff I think it'd be more helpful to simply find ways to drastically reduce the number of pins required. Most of these chips are huge because of the 128 signal wide memory/data busses, N control/configuration pins, big address busses etc. Much of this can be replaced with comparatively fewer high speed links.
What I'd rather see is parallel busses being replaced by very high speed serial links (all patented to hell and back of course), perhaps one link per expected peripheral (memory, adjunct processor, i/o bus, video bus, etc.). One could build a very cheap PCB that could almost be hand assembled. The problem is that each peripheral would also have to be compatible with the link. No one builds DDRs with SERDES links for example...
80% of the boards I've designed have been pratically identical in terms of core functionality, but they've been completely different in implementation because of the differing interfaces.
Serial links? (Score:4, Insightful)
You'd need optical links, and not very long ones. It probably wouldn't reduce the cost of the motherboard, anyway.
Comment removed (Score:4, Interesting)
Re:eh? (Score:5, Informative)
Re-read article. It's not a stack. They make reference to scrabble tiles as a comparison.
Even if it were a stack liquid cooling built directly into the stack, ala the internal combustion engine, could handle the heat effectively. Probably more effectively then our current heat sink technology.
TW
Re:eh? (Score:4, Insightful)
They have 5-6 years to work on this whole idea. Every once in a while, people have to go into completely different directions. The engineers at sun are not idiots. Do the people on here actually believe that they're not going to deal with these types of problems that are mentioned here?
Re:Without connectors? (Score:5, Informative)
Sounds clever to me. Electrical engineers have been constantly fighting unwanted interference in their circuits. Now they will be listening for it.
Re:Without connectors? (Score:2, Funny)
...as will your friendly neighborhood competitor, spy organization, etc. And you thought the Tempest effect was bad.
Re:Without connectors? (Score:4, Funny)
Re:Without connectors? (Score:5, Informative)
Re:Without connectors? (Score:3, Informative)
Multiple communications channels between chips can be used. Each channel uses an individual pad slightly embedded in each chip, and the pads in each chip have to be physically aligned to some extent. This has two advantages... because the pads are done on-die and not outside the chip, the pads can be two orders of magnitude smaller than external pins. Also, the pins are protected from electrostatic discharge. The summary at the end of the article says:
Re:Wrong (Score:5, Informative)
CMOS-FET = Complementary Metal Oxide Semiconductor - Field Effect Transistor
That's semiconductors separated by oxide (oxidized silicone or glass) to allow fields derived from differing voltages on either side of the glass to affect conductivity and thereby provide actuatable signals. All this new system does is replace the Oxide with something else; namely the walls of the outside of the chip and the unavoidable air-gap.
Obviously this alternate medium is not as efficient as normal hyper-thin glass, BUT it's more efficient than transferring physical electrons from silicon to copper and amplifying it such that you can induce a measurable current down the coppy wire several centimeters away. More-over, it's more practical to etch micro-wire paths on the edge of a chip than to manually pin-punch chips like we do today. We can make such signal points smaller and more articulate.
The ONLY problem (as outlined in the article) is keeping these micro-signals aligned.. If you're off by even half a capacitive cell, then you're fields aren't going to be strong enough, and depending on cell-spacing, you're likely to generate noise to adjacent cells.
Alignment (Score:3, Interesting)
Pretty much the same way one aligns a glass fibre in it's termination point...
--dave
Re:Wrong (Score:3, Informative)
Re:They'll revert to wires because... (Score:4, Insightful)
Seriously, I keep clicking the 'read comments' button hoping to read something interesting. Instead, I see a dozen posts by people who read the headline, think 'well that won't work!', and post about it. If you came up with it in half a second, do you think you're the first person to have that very original thought? Come on.
"They think airplanes will be faster? Ha. They've completely forgotten to take headwinds into account. "
Re:They'll revert to wires because... (Score:2)
"Experts" of often wrong. Look at how he was quoted in the article. They acknowlege that they don't have a clue if it'll work or not.
use the enemy and win. (Score:5, Interesting)
This is a very cool idea and it's the kind of thing I expect from Sun. Once it's stated, the solution almost looks obvious. While there's lots of work needed to make the idea practical, I admire the way they took a big noise problem and used it to propagate signal. It's too bad they are run by someone who thinks that they are going to make their money by licensing software instead of selling chips and licenses to very cool and real inventions.
Re:They'll revert to wires because... (Score:2)
Where will the signal decoder go on the CPU? It would essentially be a co-processor CPU fanning out to all the inputs on the main CPU and would likely introduce its own latencies and bottlenecks.
Re:Capacitive coupling (Score:2)