Slashdot Mirror

← Back to Stories (view on slashdot.org)

Intel Shrinks Transistor Size By 30%

Posted by Hemos on from the how-long-until-market dept.

pinkUZI writes "Intel will announce that it has crammed 500 million transistors on to a single memory chip, shrinking them in size by 30%. " The tech details are sadly lacking in the article - but I'm sure those will follow. Indeed, the Yahoo piece gives the details that "...has created a fully functional 70 megabit memory chip with transistor switches measuring just 35 nanometers."

16 of 258 comments (clear)

  1. Heat by shfted! · · Score: 5, Insightful

    I'm waiting for Intel to reduce heat output by 30%. 130 watts for a top end P4 is pretty insane, when a top end Opteron is only 100 watts. I don't care how small it is.

    --
    He who laughs last is stuck in a time dilation bubble.
    1. Re:Heat by rsmith-mac · · Score: 2, Insightful
      This means that if they were to make a current chip using the new 30% smaller technology, the result would probably produce about 30% less heat and use that much less power.

      Up until the latest process shrink(90nm), I would agree with you, but the laws of physics are starting to catch up with silicon chips. Intel, as has everyone else at 90nm, has had a major problem with current leakage with the process, which is causing any power savings to dissapear due to the excess leakage(and results in the infamous 100wt CPU). Without a special technology(like strained silicon) to go along with further process shrinks, you're looking at breaking even at best, and needing more energy at worst.

    2. Re:Heat by darkmeridian · · Score: 2, Insightful

      I have a Pentium IV E 3.0 Ghz. I need a huge Thermaltake solid copper heatsink and an extraordinarily loud fan and many case fans to cool the sucker off when playing DOOM III.

      If it dissipated less heat, my computer would dissipate less sound. = )

      Will

      --
      A NYC lawyer blogs. http://www.chuangblog.com/
    3. Re:Heat by 10Ghz · · Score: 2, Insightful

      Opterons generate less than 100 watts. AFAIK the 100 watt figure is the absolute maximum amount of heat the chip-family will produce, _including upcoming, yet to be announced models_! Actual wattage right now for top-end Opteron is considerably below 100 W

      --
      Lesbian Nazi Hookers Abducted by UFOs and Forced Into Weight Loss Programs - -all next week on Town Talk.
  2. This is news? by Anonymous Coward · · Score: 5, Insightful

    I work for Intel, and I gotta say--we do this every couple of years, and this wasn't a particularly stunning or unexpected part of our roadmap. If you wanted a more sensationalist headline for a pretty expected bit of news you might try the old "Intel Proves Moore's Law Not Dead Yet"

  3. Heat issues by Biotech9 · · Score: 4, Insightful
    The company also developed so-called sleep transistors that shut off the electrical current to areas of a chip that aren't being used. As a result, power consumption drops -- something that will decrease heat generation and help battery-powered devices last longer between charges.

    This sounds like a great way to tackle heat and power problems with laptops (and PCs, it's not like modern PCs don't have heating trouble too). I'd lay a bet though, that it'll still run hotter than the P4s, it seems there should be an addenium to Moores law.

    The number of transistors on an integrated circuit would double every 18 months, and that integrated circuit will get pretty damn shit hot
  4. Re:In related news... by addaon · · Score: 5, Insightful

    It's for a memory chip... when was the last time you had a memory chip that produced a noticeable amount of heat? (Hint: Rambus.) When was the last time you had a memory chip that produced an unacceptable amount of heat? (Well, if you're stretching, some of the SRAM's that HP used for caches in the PA-RISC boxes...)

    --

    I've had this sig for three days.
  5. Half way there. by Chess_the_cat · · Score: 5, Insightful

    Moore predicted his Law would run out in 2012 when 1 billion transistors are fit on a chip. Looks like we're ahead of schedule.

    --
    Support the First Amendment. Read at -1
  6. Details by StevenHenderson · · Score: 1, Insightful

    From the article:

    For its next generation chips, Intel said it incorporated new materials and other technologies to work around the problems.

    Wow, what a helpful and descriptive statement. The quality of this article is disgusting. Why even post it?

  7. Re:In related news... by brejc8 · · Score: 5, Insightful

    They could just say "Clock gating".
    I love it when a technical group has to talk to non technical jurnalists who report to other technical groups. Something gets lost in the middle step.

    --
    Mouse powered Chips, Open source Processors and Lego
  8. Re:In related news... by swordboy · · Score: 5, Insightful

    This is Intel's 65 nanometer process announcement. Right now, they are at 90 nanometers. They always test the process using SRAM cells. This doesn't mean that Intel won't use the process for CPUs and what not.

    But as a rule of thumb, the closer you bunch up the transistors, the higher the electrical leakage. This is why the current chips are consuming more power than ever. At 65 nanometers, we'll be 30 percent smaller but also leak 30 percent more. This leakage causes heat.

    Intel's paperwork shows that they believe that practical transistors will stop shrinking at approximately 320 watts/cm^2 which is nearing the heat density of a nuclear reactor (500w/cm^2). This will take place at the 45nm level in 2007.

    --

    Life is the leading cause of death in America.
  9. Intel by JerryLs · · Score: 4, Insightful

    May I ask why, every time they shrink the size of components, they feel a need to put more on the chip? I realize more can be done, but with all the heat/power problems with increased density, why not use the space with chip power you already have? The result would be a cooler, lower power device.

    --
    Ad Astra Per Asper
  10. Re:In related news... by dslbrian · · Score: 4, Insightful

    Narrower gates are less good at being the perfect insulators they should be. The thinner dielectric allows more leakage current, and can even break completely if the voltage is too high

    I think your describing the wrong mechanism - deep submicron device leakage is dominated by drain-source subthreshold currents (hot-electron effects and whatnot), not by gate-source currents.

  11. Producing it in the Lab by Anonymous Coward · · Score: 2, Insightful

    is one thing. Producing it on the Production Line is another.

    This is why there are Chemical Engineers, as opposed to Chemists. Or Mechanical Engineers, as opposed to Physicists. You can produce a single one at a cost of $10,000 in the lab, and that is an achievement.

    But there's another step, and it very quickly leaves the realm of a controlled environment...

  12. Re:EE Times article by GigsVT · · Score: 2, Insightful

    What a bold move, predicting the end of Moore's law.

    Yawn.

    --
    I've had enough abrasive sigs. Kittens are cute and fuzzy.
  13. In other news.... by MemoryDragon · · Score: 2, Insightful

    Intel shrinks the number of commands of the x86 architecture by 30% thus resulting in less heat and a global saving of energy of multiple gigawatts per month.