Patent · US Active

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

US12332707B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignees

Inventors

Key dates

Filing dateOct 22, 2021
Grant dateJun 17, 2025
Priority date
Expiry dateJan 9, 2042

Classification

  • Technology area (CPC Y)Emerging Cross-Sectional Technologies
  • CPC primaryY02D10/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.