Near threshold computing research

A post at Phsyorg.com this week reviews research by University of Michigan researchers into electronic devices that operate a much lower voltages than today’s silicon

In a recent study, a team of researchers, Ronald Dreslinski, et al., from the University of Michigan, have investigated a solution to the power problem by using a method called near-threshold computing (NTC). In the NTC method, electronic devices operate at lower voltages than normal, which reduces energy consumption. The researchers predict that NTC could enable future computer systems to reduce energy requirements by 10 to 100 times or more, by optimizing them for low-voltage operation. Unfortunately, low-voltage operation also involves performance trade-offs: specifically, performance loss, performance variation, and memory and logic failures.

…“NTC is an enabling technology that allows for continued scaling of CMOS-based devices, while significantly improving energy efficiency,” Dreslinski told PhysOrg.com. “The major impact of the work is that, for a fixed battery lifetime, significantly more transistors can be used, allowing for greater functionality. Particularly, [NTC allows] the full use of all transistors offered by technology scaling, eliminating ‘Dark Silicon’ that occurs as we scale to future technology nodes beyond 22 nm where ’more transistors can be placed on chip, but will be unable to be turned on concurrently.’”

The “threshold” in near threshold computing is the voltage at which a transistor is turned on and able to work its magic (see the Wikipedia for a more precise discussion). Typically we operate at voltages significantly higher than the threshold voltage to eliminate any confusion about whether the transistor is supposed to be on or off — as you lower the voltage applied to the transistor such that it becomes close to the threshold, the more chance there is of an unintentional state transition due to noise in the system.

In discussions of the exascale future, near threshold chips usually come up. However, there are significant challenges to overcome

Operating at near-threshold rather than subthreshold voltages could provide a compromise, enabling devices to require less energy while minimizing the energy leakage. This improved trade-off could potentially open up low-voltage design to mainstream semiconductor products. However, near-threshold computing still faces the other three challenges mentioned earlier: a 10 times performance loss, five times increase in performance variation, and an increase in functional failure rate of five orders of magnitude. These challenges have not been widely addressed so far, but the Michigan researchers spend the bulk of their analysis reviewing the current research to overcome these barriers.

More in the article, which I commend to your weekend reading list.