At IDF last year Intel's Justin Rattner demonstrated a 32nm test chip based on Intel's original Pentium architecture that could operate near its threshold voltage. The power consumption of the test chip was so low that the demo was powered by a small solar panel. A transistor's threshold voltage is the minimum voltage applied to the gate for current to flow. The logical on state is typically mapped to a voltage much higher than the threshold voltage to ensure reliable and predictable operation. The non-linear relationship between power and voltage makes operating at lower voltages, especially those near the threshold very interesting.

At this year's ISSCC Intel is presenting details of a number of NTV (near threshold voltage) research projects. For starters, Intel is sharing more details on Claremont - the 32nm NTV Pentium processor demonstrated at IDF. At 3MHz Claremont can operate at 280mV and scale up to 1.2V at 915MHz. Minimum power for Claremont is a meager 2mW.

Intel is also sharing details of a 22nm NTV SIMD engine for use in processor graphics. Given Intel's new focus on improving processor graphics performance, the fact that we're seeing more Intel driven research around GPU technologies isn't surprising. It's also important to point out that Intel needs the experience in building NTV circuits for both CPUs and GPUs if this technology is ever to make it into an actual product. NTV operation grants much better power efficiency where possible, making eventual productization very desirable.

Comments Locked

10 Comments

View All Comments

  • Arnulf - Monday, February 20, 2012 - link

    Isn't 1.2V a bit excessive, given that my 5 year old Core2 runs perfectly fine at 2.13 GHz with Vcc clamped to 1.1V ? I would imagine this improved chip runs at much lower voltage given the huge difference in operating frequency, heat buildup (which causes dissipation to go up as resistance increases with temperature) and manufacturing process (32 nm versus 65 nm) ...
  • Hulk - Monday, February 20, 2012 - link

    I could be wrong but I think the point is not just the voltage but the lower power levels and the huge swing in voltage (and frequency and power) that this chip is running. While 3MHz is a very low frequency, 2mW is an insanely small amount of power. I have a feeling the power usage at 915MHz/1.2V would also be very low but we're not provided with that information.
  • negativentropy - Monday, February 20, 2012 - link

    2 mW is about equivalent to your average lemon-based battery...
  • Klimax - Tuesday, February 21, 2012 - link

    PotatOS?
  • dasgetier - Tuesday, February 21, 2012 - link

    GLaDOS would run on it
  • Couponsva - Tuesday, July 13, 2021 - link

    Great article! I recently wrote a research paper on cybernetics. It was a very interesting study, but unfortunately I didn't have much time to study the material. So I decided to contact the service https://couponsva.com/
  • Henk Poley - Wednesday, February 22, 2012 - link

    Are they saying they never properly researched the boundary properties of the building blocks they use to make their machines?
  • JKflipflop98 - Wednesday, February 22, 2012 - link

    Yes, the most advanced and cutting edge team of scientists and engineers in the entire industry just didn't do their homework.

    You're a bright one, aren't you?
  • martinroberto - Tuesday, June 22, 2021 - link

    Don’t you guys think that 1.2v is a bit more for a Pentium core? I work as an academic writer in an assignment help service, and yes, people ask us if they can -based from us at cheap rates all the time.

Log in

Don't have an account? Sign up now