An Energy-aware Online Learning Framework for Resource Management in Heterogeneous Platforms
Abstract
Mobile platforms must satisfy the contradictory requirements of fast response time and minimum energy consumption as a function of dynamically changing applications. To address this need, systems-on-chip (SoC) that are at the heart of these devices provide a variety of control knobs, such as the number of active cores and their voltage/frequency levels. Controlling these knobs optimally at runtime is challenging for two reasons. First, the large configuration space prohibits exhaustive solutions. Second, control policies designed offline are at best sub-optimal, since many potential new applications are unknown at design-time. We address these challenges by proposing an online imitation learning approach. Our key idea is to construct an offline policy and adapt it online to new applications to optimize a given metric (e.g., energy). The proposed methodology leverages the supervision enabled by power-performance models learned at runtime. We demonstrate its effectiveness on a commercial mobile platform with 16 diverse benchmarks. Our approach successfully adapts the control policy to an unknown application after executing less than 25% of its instructions.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- May 13, 2020
- Source ID
- 10.1145/3386359
Entities
People
- Ganapati Bhat
- Janardhan Rao Doppa
- Partha Pratim Pande
- Sumit K. Mandal
- Umit Y. Ogras
Organizations
- Arizona State University
- Army Research Office
- National Science Foundation
- Semiconductor Research Corporation
- Washington State University