Become a fan of Slashdot on Facebook

 



Forgot your password?
typodupeerror
Sun Microsystems Wireless Networking Hardware Technology

Sun Working to Obsolete Motherboards 228

Posted by CowboyNeal
from the look-ma-no-solder dept.
perl_camel_jockey writes "Sun is developing a new technology that promises to increase computing power by eliminating the need for physical, soldered chip-to-chip connections on the motherboard. Called 'proximity communications', it portends the ability for chips to talk to one another wirelessly just by being next to each other. Potential applications in computer design abound. Apparently this is part of Sun's Hero program, recipient of a $50 million grant from DARPA's High Productivity Computing Systems program to rejuvenate supercomputing in the US and regain the lead lost to Japan, in particular to NEC's Earth Simulator, ranked as the most powerful supercomputer in the world."
This discussion has been archived. No new comments can be posted.

Sun Working to Obsolete Motherboards

Comments Filter:
  • by physicsphairy (720718) on Friday August 06, 2004 @02:52AM (#9897372) Homepage
    "it portends the ability for chips to talk to one another wirelessly just by being next to each other."

    Well, unless each chip comes equipped with its own miniaturized nuclear reactor, aren't they still all going to have to have leads running to the powersupply?

    I don't mean to be a heckler, but are you really "doing away" with the motherboard or just reducing it to a voltage bus with transmitters and receivers replacing some of the input and output pins?

  • Worried... (Score:4, Interesting)

    by rpbailey1642 (766298) <robert.b.prattNO@SPAMgmail.com> on Friday August 06, 2004 @02:58AM (#9897388)
    I might just be horribly ignorant, so please inform me...security? Even though all it is transferring is system calls and such, I am certain that there are ways to back-engineer what the computer is doing at that time by reading the (very faint, I'm sure) wireless signals. Again, I do not know, so will someone please enlighten me? What exactly is going on, what are the security ramifications?
  • Re:Deja vu (Score:4, Interesting)

    by maxwell demon (590494) on Friday August 06, 2004 @03:17AM (#9897440) Journal
    Why should the moderators read the postings? After all, most are dupes anyway, where they will not learn anything new. :-)
  • Re:DUPE (Score:5, Interesting)

    by johnhennessy (94737) on Friday August 06, 2004 @03:23AM (#9897458)

    How about allowing subscribers to moderate stories before they hit the main site.

    People who are really busy could browse at +5 "Don't do anything else until you read this !!!" while people with loads of time (or in college) could browse at normal levels.

    Oh, and as a plus, you would eliminate dupes as well.
  • WTF? (Score:1, Interesting)

    by Anonymous Coward on Friday August 06, 2004 @03:28AM (#9897470)
    It was pointed out yesterday, when this article was duped first the first time, that this had been posted sometime last year. Seriously, WTF? How out of touch are the slashdot moderators?
  • C=64 Reminder (Score:3, Interesting)

    by incog8723 (579923) on Friday August 06, 2004 @04:30AM (#9897611)
    This reminds me of an issue with a C=64 I used to have that I had removed the aluminum foil casing from (inside the case). The 6502 processor wirelessly queried the SID chip for reassurance and understanding.

    Sincerely,
    Ass-embly Language
  • Chip Issues (Score:3, Interesting)

    by drakyri (727902) on Friday August 06, 2004 @05:14AM (#9897684)
    One of the issues we run into where I work (we make oscillators) is that chips behave differently over their specified temperature operating range. Commercial parts are rated from 0 to 70 Celsius (Industrial : -40/+85, Military : -55/+125). Commercial range is pretty decent for most applications; the average user wouldn't expect their computer innards to be heating up past 150 Farenheit. Anyhow, the simpler chips we make operate differently at different temperatures (the part I'm working on now is rated +- 100 parts per million).

    A more complicated way of making these is to make what's called an Oven-Controlled model - you basically create a little oven that responds to the temperature of the chip, keeping it at a certain optimal temperature. These parts are much more stable and accurate; they vary in parts per billion. Dust is a big concern during manufacture; they're pretty sensitive, but once they're sealed, they're more or less set to go.

    On a completely seperate note, I have to wonder what kind of issues Sun will be having with crosstalk on their new mobo's.
  • by Anonymous Coward on Friday August 06, 2004 @05:22AM (#9897697)
    This technology is only for interconnecting the different dies together. Currently you can buy flash & SRAM stack chips on a single package (for the cell phone market). This is done with stackchip technology using die to die connection.

    This technology is useless at the system level because of tight mechanical alignment issues. Think optic bench experiments - heavy table, stabilized and 3D alignment to line chips together to form a big system. Oh yes, power, misc signals etc.

    PCB will still be used for doing medium/low bandwidth connections because currently all available parts are designed for PCB assembly. PCB is the cheapest & most efficient technology to do this for years to come.

    They still need to solve heat issue when you now have the heat of all the stack chips in a single physical package to dissipate.
  • Prime Intellect (Score:3, Interesting)

    by skinfitz (564041) on Friday August 06, 2004 @06:54AM (#9897854) Journal
    This idea reminds me of the free online novel Prime Intellect [kuro5hin.org] which I can strongly recommend.
  • Re:DUPE (Score:3, Interesting)

    by Karma Farmer (595141) on Friday August 06, 2004 @07:51AM (#9898101)
    People who are really busy could browse at +5 "Don't do anything else until you read this !!!"

    It would be awesome if Slashdot moderation worked like that at all. But, it doesn't. Moderators don't decide "this post is worth a 3, while that one is worth a 5, and that one is worth a -1." Moderators are only given three choices for a post: +1, 0, and -1. Slashdot uses an insanely boneheaded algorithm to map those three moderation choices to seven different thresholds: -1, 0, +1, +2, +3, +4, and +5.

    Assume 100% of the people reading a post find it very informative. If only one of those readers moderates, that post is going to get a 0, 1, 2, or 3 (depending on the person who submitted the post).

    Conversely, assume 60% of the readers find a post mildly informative, and 40% of the moderators believe a post is horribly misinformed. If 30 of those readers moderate, that post is going to always get a 5.

    In other words, browsing at +5 doesn't mean "show me the best posts." Slashdot is designed so that browsing at +5 means "show me the posts that have been seen by the largest number of readers with mod points." Articles, because they are seen by so many readers, will always be at +5 or -1, and almost never anything in between.

    Psychologists who design casinos for a living could probably explain the reward system in play -- why is such an obviously non-useful system paradoxically so successful? Probably for the same reason people throw away money on slot machines. Allowing the moderation of articles would be like a slot machine that just simply gave back 75 cents every time you put in a dollar and pulled the lever. A lot more efficient, but much less appealing.
  • by Baldrson (78598) on Friday August 06, 2004 @08:06AM (#9898206) Homepage Journal
    DARPA's history of supercomputing initiatives isn't quite as bad as NASA running the Shuttle program but its up there.

    If you want fast computers developed in the US, buy them from the US market and try to mould your tax incentives so that they simulate, as closely as possible, a net asset tax as described in "A Net Asset Tax Based On The Net Present Value Calculation [geocities.com]".

    The reason Cray Computer Corporation's gallium arsenide fab went out of business wasn't for lack of funding -- it was for a lack domestic market for the end product, supercomputers, in the wake of the end of the cold war. One could also chalk it up to Cray's fixation on supercomputers since the output of the GaAs fab line could have been altered to serve high speed telecom markets, but if DARPA wants fast supercomputers, there was help available from private capital sources.

    Its never a good idea for government to compete with private capital sources in high technology.

  • Re:Pride (Score:3, Interesting)

    by Archibald Buttle (536586) <steve_sims7@@@yahoo...co...uk> on Friday August 06, 2004 @09:03AM (#9898653)
    Maybe I'm being stupid, but I don't see how this work obseletes the Von Neumann architecture.

    Sure, there's no wires connecting the chips together, but the basic ingredients of a Von Neumann machine are still there, i.e. memory and processor.

    As somebody has already said it's not going to be just one chip, however even single-chip computers still follow the model. Yes, the processor and memory reside on the same chip, but they're still logically separate units. Indeed most modern processor chips are Von Neumann machines containing CPU and cache in a single unit.

    Will this wipe out motherboards? You still need to put these chips somewhere, and I would speculate that they wouldn't be very tolerant of being moved about relative to each other whilst operational. They also need power.
  • by Animats (122034) on Friday August 06, 2004 @12:57PM (#9900926) Homepage
    This isn't a "3D" stacking technology. The chips that communicate have to be mounted face to face. See the illustration in Sun's technical paper. [sun.com]

    For an example of true 3D chip stacking, see Infineon's SOLID technology [lightreading.com]. Infineon announced that in 2002. Intel and Sharp have also played around with similar approaches.

    The Infineon approach is interesting because it puts a layer of copper between the chips. Getting heat out of the middle of the stack is a major problem with all stacking schemes. Infineon claims to address this, but it's not clear how well. You're probably not going to stack up a pile of 50 watt CPUs with this technology. RAM, maybe. Low-duty-cycle flash memory, no problem. Music players are the obvious application.

    Not much seems to have come from that technology since the 2002 announcement. So far, none of these stacking schemes have been useful. They're smaller, but not cheaper.

Be careful when a loop exits to the same place from side and bottom.

Working...