Heterogeneous multicore processors (HMPs), consisting of cores with different performance/power characteris- tics, have been proposed to deliver higher energy effi- ciency than symmetric multicores. This paper investi- gates the opportunities and limitations in using HMPs to gain energy-efficiency. Unlike previous work focused on server systems, we focus on the client workloads typi- cally seen in modern end-user devices. Further, beyond considering core power usage, we also consider the ‘un- core’ subsystem shared by all cores, which in modern platforms, is an increasingly important contributor to to- tal SoC power. Experimental evaluations use client ap- plications and usage scenarios seen on mobile devices and a unique testbed comprised of heterogeneous cores, with results that highlight the need for uncore-awareness and uncore scalability to maximize intended efficiency gains from heterogeneous cores.
- Georgia Tech: Vishal Gupta, Karsten Schwan
- Intel Labs: Paul Brett, David Koufaty, Dheeraj Reddy, Scott Hahn
- Intel Corporation: Ganapati Srinivasa