Enhanced Phase-Driven $Q$ -Learning-Based DRM for Multicore Processors
Authors:
- 19 October 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 38 (11) , 2022-2031
Abstract
In this paper, we propose a new dynamic reliability management (DRM) technique for multi-core processors using phase-driven Q-learning based method. Our technique considers a wide range of long-term reliability issues and maximizes the throughput of the processor subject to the reliability constraint. We employ ON/OFF switching actions and dynamic voltage and frequency scaling (DVFS) as control knobs (i.e. working modes) to tune the state of cores of the processor. In order to achieve this, our technique detects program phases and adaptively determines the optimal working modes for each phase using the Q-learning based method. By integrating the phase detection into the Q-learning based management, our technique can provide efficient management for the programs with highly diverse phases. We also propose three additional modules to improve the management efficiency of our technique. In order to evaluate our technique, we use it to manage a 3D CPU with high-diver programs. Several failure mechanisms are considered in this case study. Our proposed technique is compared with two existing Q-learning based techniques Das:learning, Kim:learning. The experimental results demonstrate that when the number of phases is smaller than the number of working modes, our technique can achieve more than 1.36x improvement in performance with 60% memory space savings.Keywords
This publication has 36 references indexed in Scilit:
- Distributed Reinforcement Learning for Power Limited Many-Core System Performance Optimization2015
- Electromigration Study for Multiscale Power/Ground Vias in TSV-Based 3-D ICsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2014
- Architectural Reliability: Lifetime Reliability Characterization and Management ofMany-Core ProcessorsIEEE Computer Architecture Letters, 2014
- Multi2Sim2012
- Dynamic thermal management for multimedia applications using machine learning2011
- Prediction of room temperature and relative humidity by autoregressive linear and nonlinear neural network models for an open officeEnergy and Buildings, 2011
- Maestro: Orchestrating Lifetime Reliability in Chip Multiprocessors2010
- Bridging the Processor-Memory Performance Gapwith 3D IC TechnologyIEEE Design & Test of Computers, 2005
- Lifetime Reliability: Toward an Architectural SolutionIEEE Micro, 2005
- Discovering and exploiting program phasesIEEE Micro, 2003