Hwisung Jung

Stochastic modeling of a thermally-managed multi-core system

Achieving high performance under a peak temperature limit is a first-order concern for VLSI designers. This paper presents a new abstract model of a thermally-managed system, where a stochastic process model is employed to capture the system performance and thermal behavior. We formulate the problem of dynamic thermal management (DTM) as the problem of minimizing the energy cost of the system for a given level of performance under a peak temperature constraint by using a controllable Markovian decision process (MDP) model. The key rationale for utilizing MDP for solving the DTM problem is to manage the stochastic behavior of the temperature states of the system under online re-configuration of its micro-architecture and/or dynamic voltage-frequency scaling. Experimental results demonstrate the effectiveness of the modeling framework and the proposed DTM technique.

Dynamic power management under uncertain information

This paper tackles the problem of dynamic power management (DPM) in nanoscale CMOS design technologies that are typically affected by increasing levels of process, voltage, and temperature (PVT) variations and fluctuations. This uncertainty significantly undermines the accuracy and effectiveness of traditional DPM approaches. More specifically, a stochastic framework was propose to improve the accuracy of decision making in power management, while considering the manufacturing process and/or design induced uncertainties. A key characteristic of the framework is that uncertainties are effectively captured by a partially observable semi-Markov decision process. As a result, the proposed framework brings the underlying probabilistic PVT effects to the forefront of power management policy determination. Experimental results with a RISC processor demonstrate the effectiveness of the technique and show that the proposed variability-aware power management technique ensures robust system-wide energy savings under probabilistic variations

Continuous Frequency Adjustment Technique Based on Dynamic Workload Prediction

Real-time embedded systems increasingly rely on dynamic power management to balance between power and performance goals. In this paper, we present a technique for continuous frequency adjustment (CFA) which enables one to adjust the frequency values of various functional blocks in the system at very low granularity so as to minimize energy while meeting a performance constraint. A key feature of the proposed technique is that the workload characteristics for functional blocks are effectively captured at runtime to generate a frequency value that is continuously adjusted, thereby eliminating the delay and energy penalties incurred by transitions between power-saving modes. The workload prediction is accomplished by solving an initial value problem (IVP). Applying CFA to a real-time system in 65 nm CMOS technology, we demonstrate the effectiveness of the proposed technique by reporting 13.6% energy saving under a performance constraint.

Stochastic Dynamic Thermal Management: A Markovian Decision-based Approach

This paper proposes a stochastic dynamic thermal management (DTM) technique in high-performance VLSI system with especial attention to the uncertainty in temperature observation. More specifically, we propose a stochastic thermal management framework to improve the accuracy of decision making in DTM, which performs dynamic voltage and frequency scaling to minimize total power dissipation and on-chip temperature. A key characteristic of the framework is that thermal states are controlled by stochastic processes, i.e., partially observable semi-Markov decision processes. Collaborative optimization is considered with mathematical programming formulations to reduce operating temperature by using multi-objective design optimization methods. Experimental results with 32-bit embedded RISC processor demonstrate the effectiveness of the technique and show that the proposed algorithm ensures thermal safety under performance constraints.

Improving the Efficiency of Power Management Techniques by Using Bayesian Classification

This paper presents a supervised learning based dynamic power management (DPM) framework for a multicore processor, where a power manager (PM) learns to predict the system performance state from some readily available input features (such as the state of service queue occupancy and the task arrival rate) and then uses this predicted state to look up the optimal power management action from a pre-computed policy lookup table. The motivation for utilizing supervised learning in the form of a Bayesian classifier is to reduce overhead of the PM which has to recurrently determine and issue voltage-frequency setting commands to each processor core in the system. Experimental results reveal that the proposed Bayesian classification based DPM technique ensures system-wide energy savings under rapidly and widely varying workloads.

A stochastic local hot spot alerting technique

With the increasing levels of variability in the behavior of manufactured nano-scale devices and dramatic changes in the power density on a chip, timely identification of hot spots on a chip has become a challenging task. This paper addresses the questions of how and when to identify and issue a hot spot alert. There are important questions since temperature reports by thermal sensors may be erroneous, noisy, or arrive too late to enable effective application of thermal management mechanisms to avoid chip failure. This paper thus presents a stochastic technique for identifying and reporting local hot spots under probabilistic conditions induced by uncertainty in the chip junction temperature and the system power state. More specifically, it introduces a stochastic framework for estimating the chip temperature and the power state of the system based on a combination of Kalman filtering (KF) and Markovian decision process (MDP) model. Experimental results demonstrate the effectiveness of the framework and show that the proposed technique alerts about thermal threats accurately and in a timely fashion in spite of noisy or sometimes erroneous readings by the temperature sensor.

Predictive-Flow-Queue-Based Energy Optimization for Gigabit Ethernet Controllers

This paper presents energy-efficient packet interface architecture and a power management technique for gigabit Ethernet controllers, where low-latency and high-bandwidth are required to meet the pressing demands of very high frame-rate data. More specifically, a predictive-flow-queue (PFQ)-based packet interface architecture is presented, which adjusts the operating frequency of different functional blocks at a fine granularity so as to minimize the total system energy dissipation while attaining performance goals. A key feature of the proposed architecture is the implementation of a runtime workload prediction method for the network traffic along with a continuous frequency adjustment mechanism, which enables one to eliminate the latency and energy penalties associated with discrete power mode transitions. Furthermore, a stochastic modeling framework based on Markovian decision processes and queuing models is employed, which make it possible to adopt a precise mathematical programming formulation for the energy optimization under performance constraints. Experimental results with a designed 65-nm Gb Ethernet controller show that the proposed interface architecture and continuous frequency scaling result in system-wide energy savings while meeting performance specifications.

Uncertainty-Aware Dynamic Power Management in Partially Observable Domains

This paper tackles the problem of dynamic power management (DPM) in nanoscale CMOS design technologies that are typically affected by increasing levels of process and temperature variations and fluctuations due to the randomness in the behavior of silicon structure. This uncertainty undermines the accuracy and effectiveness of traditional DPM approaches. This paper presents a stochastic framework to improve the accuracy of decision making during dynamic power management, while considering manufacturing process and/or environment induced uncertainties. More precisely, variability and uncertainty at the system level are captured by a partially observable semi-Markov decision process with interval-based definition of states while the policy optimization problem is formulated as a mathematical program based on this model. Experimental results with a RISC processor in 65-nm technology demonstrate the effectiveness of the technique and show that the proposed uncertainty-aware power management technique ensures system-wide energy savings under statistical circuit parameter variations.

Resilient dynamic power management under uncertainty

With the increasing levels of variability and randomness in the characteristics and behavior of manufactured nanoscale structures and devices, achieving performance optimization under process, voltage, and temperature (PVT) variations as well as current, voltage, and thermal (CVT) stress has become a daunting, yet vital, task. In this paper, we present a stochastic dynamic power management (DPM) framework to improve the accuracy of decision making under probabilistic conditions induced by PVT variations and/or stress. More precisely, we propose a resilient power management technique that guarantees to select an optimal policy under sources of uncertainty. A key characteristic of the proposed technique is that the effects of uncertainties due to variability and stress are captured by stochastic processes which control a self- improving power manager. Simulation results with a 65 nm processor design show that, compared to the worst-case PVT conditions, the proposed DPM technique ensures energy efficiency, while reducing the uncertain behaviors of the system.

Optimizing the power delivery network in dynamically voltage scaled systems with uncertain power mode transition times

With the increasing demand for energy-efficient power delivery network (PDN) in todays electronic systems, configuring an optimal PDN that supports power management techniques, e.g., dynamic voltage scaling (DVS), has become a daunting, yet vital task. This paper describes how to model and configure such a PDN so as to minimize the total energy dissipation in DVS-enabled systems, while satisfying total PDN cost and/or power conversion efficiency constraints. The problem of configuring an energy-efficient PDN under various constraints is subsequently formulated by using a controllable Markovian decision process (MDP) model and solved optimally as a policy optimization problem. The key rationale for utilizing MDP for solving the PDN configuration problem is to manage stochastic behavior of the power mode transition times of DVS-enabled systems. Simulation results demonstrate that the proposed technique ensures energy savings, while satisfying design goals in terms of total PDN cost and its power efficiency.1