The University of Texas System

Arizona State University

Carnegie Mellon University

The University of Arizona

Anish Krishnakumar

Daniel W Bliss

Joshua Mack

Chaitali Chakrabarti

Ahmet Goksoy

Nirmal Kumbhare

Radu Marculescu

Ali Akoglu

Samet Egemen Arda

Umit Ogras

Anderson Sartor

Sumit Mandal

Hierarchical and lightweight imitation learning (IL) for power management of embedded systems-on-chip (SoCs), also referred to herein as HiLITE, is provided. Modern SoCs use dynamic power management (DPM) techniques to improve energy efficiency. However, existing techniques are unable to efficiently adapt the runtime decisions considering multiple objectives (e.g., energy and real-time requirements) simultaneously on heterogeneous platforms. To address this need, embodiments described herein propose HiLITE, a hierarchical IL framework that maximizes energy efficiency while satisfying soft real-time constraints on embedded SoCs. This approach first trains DPM policies using IL; then, it applies a regression policy at runtime to minimize deadline misses. HiLITE improves the energy-delay product by 40% on average, and reduces deadline misses by up to 76%, compared to state-of-the-art approaches. In addition, the trained policies not only achieve high accuracy, but also have negligible prediction time overhead and small memory footprint.

HiLITE: hierarchical and lightweight imitation learning for power management of embedded SoCs

Growing community of inventors

Madison, WI, United States of America

Anish Krishnakumar