Imitation Learning for Dynamic VFI Control in Large-Scale Manycore Systems
Open Access
- 26 May 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 25 (9) , 2458-2471
Abstract
Manycore chips are widely employed in high-performance computing and large-scale data analysis. However, the design of high-performance manycore chips is dominated by power and thermal constraints. In this respect, voltage-frequency island (VFI) is a promising design paradigm to create scalable energy-efficient platforms. By dynamically tailoring the voltage and frequency of each island, we can further improve the energy savings within given performance constraints. Inspired by the recent success of imitation learning (IL) in many application domains and its significant advantages over reinforcement learning (RL), we propose the first architecture-independent IL-based methodology for dynamic VFI (DVFI) control in manycore systems. Due to its popularity in the EDA community, we consider an RL-based DVFI control methodology as a strong baseline. Our experimental results demonstrate that IL is able to obtain higher quality policies than RL (on average, 5% less energy with the same level of performance) with significantly less computation time and hardware area overheads (3.1X and 8.8X, respectively).Keywords
Funding Information
- U.S. National Science Foundation (CCF 1514269, CCF 1162202, CCF 1314876, CNS 1564022, CCF 1514206)
This publication has 34 references indexed in Scilit:
- Data-Driven Activity Prediction2015
- Wireless NoC for VFI-Enabled Multicore Chip Design: Performance Evaluation and Design Trade-OffsIEEE Transactions on Computers, 2015
- A Probabilistic Graphical Model-based Approach for Minimizing Energy Under Performance Constraints2015
- Distributed Reinforcement Learning for Power Limited Many-Core System Performance Optimization2015
- Performance Evaluation of Congestion-Aware Routing with DVFS on a Millimeter-Wave Small-World Wireless NoCACM Journal on Emerging Technologies in Computing Systems, 2014
- DVFS Pruning for Wireless NoC ArchitecturesIEEE Design & Test, 2014
- Pack & Cap2011
- The gem5 simulatorACM SIGARCH Computer Architecture News, 2011
- Algorithms for Reinforcement LearningSynthesis Lectures on Artificial Intelligence and Machine Learning, 2010
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009