Dependability, power, and performance trade-off on a multicore processor

Abstract

As deep submicron technologies are advanced, we face new challenges, such as power consumption and soft errors. A naive technique, which utilizes emerging multicore processors and relies upon thread-level redundancy to detect soft errors, is power hungry. It consumes at least two times larger power than the conventional single-threaded processor does. This paper investigates a trade-off between dependability and power on a multicore processor, which is named multiple clustered core processor (MCCP). It is proposed to adapt processor resources according to the requested performance. A new metric to evaluate a trade-off between dependability, power, and performance is proposed. It is the product of soft error rate and the popular energy-delay product. We name it energy, delay, and upset rate product (ED UP). Detailed simulations show that the MCCP exploiting the adaptable technique improves the EDUP by up to 21% when it is compared with the one exploiting the naive technique.