EECS – Prelim: Machine Learning for Dynamic Resource Management in Manycore Systems, Gaurav Narang

About the event

Student: Gaurav Narang

Advisor: Dr. Partha Pande and Dr. Jana Doppa

Degree: Electrical and Computer Engineering Ph.D.

Title: Machine Learning for Dynamic Resource Managemetn in Manycore Systems

Abstract: The complexity of manycore System-on-chips (SoCs) is growing faster than our ability to manage them to reduce the overall energy consumption. Further, as SoC design moves towards 3D-architectures, the core’s power density increases leading to unacceptable high peak chip temperatures. We consider the optimization problem of dynamic power management (DPM) in manycore SoCs for an allowable performance penalty and admissible peak chip temperature. We employ a machine learning (ML) based DPM policy, which selects the voltage/frequency (V/F) levels for different cluster of cores as a function of the application workload features such as core computation and inter-core traffic etc. We propose a novel learning-to-search (L2S) framework to automatically identify an optimized sequence of DPM decisions from a large combinatorial space for joint energy-thermal optimization for one or more given applications.
Further, we consider the problem of dynamic power management (DPM) for unseen applications at runtime. We propose a novel uncertainty-aware online learning framework to learn the DPM policy, which can adapt to unseen applications at runtime. It relies on two key ideas. First, an entropy-based uncertainty measure is used to distinguish between seen and unseen system states. Second, we employ conformal prediction to compute uncertain V/F sets for unseen system states. We perform bounded-search over the uncertain V/F configurations using power/performance models to identify the best V/F configurations to minimize the energy-delay product (EDP) and create supervised examples for online learning.