Performance-Energy Trade-off in Modern CMPs
- 30 December 2020
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 18 (1), 1-26
- https://doi.org/10.1145/3427092
Abstract
Chip multiprocessors (CMPs) are ubiquitous in all computing systems ranging from high-end servers to mobile devices. In these systems, energy consumption is a critical design constraint as it constitutes the most significant operating cost for computing clouds. Analogous to this, longer battery life continues to be an essential user concern in mobile devices. To optimize on power consumption, modern processors are designed with Dynamic Voltage and Frequency Scaling (DVFS) support at the individual core as well as the uncore level. This allows fine-grained control of performance and energy. For an n core processor with m core and uncore frequency choices, the total DVFS configuration space is now m(n+1) (with the uncore accounting for the + 1). In addition to that, in CMPs, the performance-energy trade-off due to core/uncore frequency scaling concerning a single application cannot be determined independently as cores share critical resources like the last level cache (LLC) and the memory. Thus, unlike the uni-processor environment, the energy consumption of an application running on a CMP depends not only on its characteristics but also on those of its co-runners (applications running on other cores). The key objective of our work is to select a suitable core and uncore frequency that minimizes power consumption while limiting application performance degradation within certain pre-defined limits (can be termed as QoS requirements). The key contribution of our work is a learning-based model that is able to capture the interference due to shared cache, bus bandwidth, and memory bandwidth between applications running on multiple cores and predict near-optimal frequencies for core and uncore.Keywords
This publication has 17 references indexed in Scilit:
- Modular reinforcement learning for self-adaptive energy efficiency optimization in multicore systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Reliability and energy efficiency in cloud computing systems: Survey and taxonomyJournal of Network and Computer Applications, 2016
- Adaptive energy minimization of embedded heterogeneous systems using regression-based learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Controlling Free Riding Using Extended Point Based Incentive Mechanism in Peer-to-Peer NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Power-aware performance increase via core/uncore reinforcement control for chip-multiprocessorsPublished by Association for Computing Machinery (ACM) ,2012
- vGreenACM Transactions on Design Automation of Electronic Systems, 2010
- Cloud computing and emerging IT platforms: Vision, hype, and reality for delivering computing as the 5th utilityFuture Generation Computer Systems, 2009
- Power provisioning for a warehouse-sized computerPublished by Association for Computing Machinery (ACM) ,2007
- Compile-time dynamic voltage scaling settingsPublished by Association for Computing Machinery (ACM) ,2003
- Random ForestsMachine Learning, 2001