On-line Optimization of Power Efficiency in 3D Multicore Processors
| Autor: | Sudhakar Yalamanchili, X. Chen, He Xiao, Yorai Wardi |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
020203 distributed computing
Multi-core processor Computer science 02 engineering and technology Parallel computing Stochastic approximation 020202 computer hardware & architecture Power (physics) Control and Systems Engineering Line (geometry) 0202 electrical engineering electronic engineering information engineering Point (geometry) Sensitivity (control systems) Throughput (business) Electrical efficiency |
| Zdroj: | IFAC-PapersOnLine. 51:127-132 |
| ISSN: | 2405-8963 |
| DOI: | 10.1016/j.ifacol.2018.06.290 |
| Popis: | This paper considers the problem of maximizing power efficiency in multi-core processors by dynamic voltage frequency scaling. We formulate the problem in an on-line setting and apply to it a gradient-based stochastic approximation algorithm. We use a cycle-level, full-system simulation platform capable of realistic modeling of state-of-the-art microarchitectures executing industry-standard benchmarks (Splash 2). The optimization algorithm computes the gradients by the Infinitesimal Perturbation Analysis (IPA) sample-based sensitivity analysis technique. Despite the fact that the system’s characteristics vary widely with time and hence the optimum point varies as well, the simulation experiments exhibit a tracking of the optimal values. To our knowledge this is the first application of IPA to co-optimizing throughput performance and power in computer processors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|