HiLITE: Hierarchical and Lightweight Imitation Learning for Power Management of Embedded SoCs

Sartor, Anderson L.; Krishnakumar, Anish; Arda, Samet E.; Ogras, Ümit Y.; Mărculescu, Radu

doi:10.1109/lca.2020.2992182

Cited by 12 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent work also propose the use of power management systems to help reduce the power and energy consumption of the real-time systemsusing machine learning techniques [44], [36]. HetSched can work in conjunction with these schedulers to further reduce energy along with the efficient utilization of resources to meet real-time deadlines and power constraints.…”

Section: Related Workmentioning

confidence: 99%

Heterogeneity-Aware Scheduling on SoCs for Autonomous Vehicles

Amarnath

Pal

Kassa

et al. 2021

IEEE Comput. Arch. Lett.

View full text Add to dashboard Cite

Systems-on-Chips (SoCs) that power autonomous vehicles (AVs) must meet stringent performance and safety requirements prior to deployment. With increasing complexity in AV applications, the system needs to meet stringent real-time demands of multiple safety-critical applications simultaneously. A typical AV-SoC is a heterogeneous multiprocessor consisting of accelerators supported by general-purpose cores. Such heterogeneity, while needed for power-performance efficiency, complicates the art of task (process) scheduling.In this paper, we demonstrate that hardware heterogeneity impacts the scheduler's effectiveness and that optimizing for only the real-time aspect of applications is not sufficient in AVs. Therefore, a more holistic approach is required -one that considers global Quality-of-Mission (QoM) metrics, as defined in the paper. We then propose HetSched, a multi-step scheduler that leverages dynamic runtime information about the underlying heterogeneous hardware platform, along with the applications' real-time constraints and the task traffic in the system to optimize overall mission performance. HetSched proposes two scheduling policies: M Sstat and M S dyn and scheduling optimizations like task pruning, hybrid heterogeneous ranking and rank update. HetSched improves overall mission performance on average by 4.6×, 2.6× and 2.6× when compared against CPATH, ADS and 2lvl-EDF (state-of-the-art real-time schedulers built for heterogeneous systems), respectively, and achieves an average of 53.3% higher hardware utilization, while meeting 100% critical deadlines for real-world applications of autonomous driving and aerial vehicles. Furthermore, when used as part of an SoC design space exploration loop, in comparison to the prior schedulers, HetSched reduces the number of processing elements required by an SoC to safely complete AV's missions by 35% on average while achieving 2.7× lower energy-mission time product.

show abstract

Section: Related Workmentioning

confidence: 99%

Heterogeneity-Aware Scheduling on SoCs for Autonomous Vehicles

Amarnath

Pal

Kassa

et al. 2021

IEEE Comput. Arch. Lett.

View full text Add to dashboard Cite

show abstract

“…However, utilization alone does not provide sufficient information about the characteristics of applications running on the system. To address this drawback, recent approaches have used performance counters to make DRM decisions [1,17,19,20]. The performance counters give fine-grained information about the system state, thus allowing DRM policies to make more intelligent decisions.…”

Section: Related Workmentioning

confidence: 99%

“…The performance counters give fine-grained information about the system state, thus allowing DRM policies to make more intelligent decisions. Machine learning approaches, such as decision trees [17], RL [2], and IL [10,12,20] have also been used to create DRM policies for mobile platforms. While these approaches are able to improve upon prior DRM methods, they still optimize for a single objective function, such as energy or execution time or PPW.…”

Section: Related Workmentioning

confidence: 99%

“…Imitation learning (IL). IL methods create an Oracle policy to optimize a given objective and then learn a policy to mimic its behavior [12,20]. We employ the IL approach and Oracle policies for energy and PPW objectives from a recent work [12], which showed good results for optimizing energy with small or no performance penalty (i.e., very specific trade-offs).…”

Section: B Parmis and Baseline Drm Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Learning Pareto-Frontier Resource Management Policies for Heterogeneous SoCs: An Information-Theoretic Approach

Deshwal

Belakaria

Bhat

et al. 2021

2021 58th ACM/IEEE Design Automation Conference (DAC)

View full text Add to dashboard Cite

Mobile system-on-chips (SoCs) are growing in their complexity and heterogeneity (e.g., Arm's Big-Little architecture) to meet the needs of emerging applications, including games and artificial intelligence. This makes it very challenging to optimally manage the resources (e.g., controlling the number and frequency of different types of cores) at runtime to meet the desired trade-offs among multiple objectives such as performance and energy. This paper proposes a novel informationtheoretic framework referred to as PaRMIS to create Pareto-optimal resource management policies for given target applications and design objectives. PaRMIS specifies parametric policies to manage resources and learns statistical models from candidate policy evaluation data in the form of target design objective values. The key idea is to select a candidate policy for evaluation in each iteration guided by statistical models that maximize the information gain about the true Pareto front. Experiments on a commercial heterogeneous SoC show that PaRMIS achieves better Pareto fronts and is easily usable to optimize complex objectives (e.g., performance per Watt) when compared to prior methods.

show abstract

“…Since runtime task scheduling is a sequential decision-making problem, supervised learning methodologies, such as linear regression and regression tree, may not generalize for unseen states at runtime. Reinforcement learning (RL) and imitation learning (IL) are more effective for sequential decisionmaking problems [19,29,31]. Indeed, RL has shown promise when applied to the scheduling problem [20,21,37], but it suffers from slow convergence and sensitivity of the reward function [15,18].…”

Section: Introductionmentioning

confidence: 99%

Runtime Task Scheduling Using Imitation Learning for Heterogeneous Many-Core Systems

Krishnakumar

Arda

Goksoy

et al. 2020

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

Self Cite

View full text Add to dashboard Cite

Domain-specific systems-on-chip, a class of heterogeneous many-core systems, are recognized as a key approach to narrow down the performance and energy-efficiency gap between custom hardware accelerators and programmable processors. Reaching the full potential of these architectures depends critically on optimally scheduling the applications to available resources at runtime. Existing optimization-based techniques cannot achieve this objective at runtime due to the combinatorial nature of the task scheduling problem. As the main theoretical contribution, this paper poses scheduling as a classification problem and proposes a hierarchical imitation learning (IL)-based scheduler that learns from an Oracle to maximize the performance of multiple domainspecific applications. Extensive evaluations with six streaming applications from wireless communications and radar domains show that the proposed IL-based scheduler approximates an offline Oracle policy with more than 99% accuracy for performance-and energy-based optimization objectives. Furthermore, it achieves almost identical performance to the Oracle with a low runtime overhead and successfully adapts to new applications, many-core system configurations, and runtime variations in application characteristics.

show abstract

HiLITE: Hierarchical and Lightweight Imitation Learning for Power Management of Embedded SoCs

Cited by 12 publications

References 9 publications

Heterogeneity-Aware Scheduling on SoCs for Autonomous Vehicles

Heterogeneity-Aware Scheduling on SoCs for Autonomous Vehicles

Learning Pareto-Frontier Resource Management Policies for Heterogeneous SoCs: An Information-Theoretic Approach

Runtime Task Scheduling Using Imitation Learning for Heterogeneous Many-Core Systems

Contact Info

Product

Resources

About