Energy-aware scheduling of multi-version tasks on heterogeneous real-time systems

Roeder, Julius; Rouxel, Benjamin; Altmeyer, Sebastian; Grelck, Clemens

doi:10.1145/3412841.3441930

Cited by 19 publications

(9 citation statements)

References 27 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The energy aware scheduling of dependent AC tasks were considered in some prior works [36], [37] that employed DVFS at the cores. Most of the prior energy/thermal management mechanisms [14], [17], [28] control the dynamic power of the cores in CMPs either by employing DVFS [41], [42] or by migrating tasks [13], [19], [20]. Recently, Roeder et al [42] showed the effectiveness of DVFS, planned offline, for a heterogeneous real-time system with multi-version based taskmodel, but energy efficiency can be enhanced dynamically based on the runtime tasks' as well as system's characteristics.…”

Section: State-of-the-artmentioning

confidence: 99%

“…Most of the prior energy/thermal management mechanisms [14], [17], [28] control the dynamic power of the cores in CMPs either by employing DVFS [41], [42] or by migrating tasks [13], [19], [20]. Recently, Roeder et al [42] showed the effectiveness of DVFS, planned offline, for a heterogeneous real-time system with multi-version based taskmodel, but energy efficiency can be enhanced dynamically based on the runtime tasks' as well as system's characteristics. Donald and Martonosi [14] have shown the efficacy of different DVFS techniques along with task migration policies to control temperature, where distributed DVFS applied with task migration are claimed to be the best.…”

Section: State-of-the-artmentioning

confidence: 99%

See 1 more Smart Citation

DELICIOUS: Deadline-Aware Approximate Computing in Cache-Conscious Multicore

Saha

Chakraborty

Agarwal

et al. 2023

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Enhancing result-accuracy in approximate computing (AC) based real-time systems, without violating power constraints of the underlying hardware, is a challenging problem. Execution of such AC real-time applications can be split into two parts: (i) the mandatory part, execution of which provides a result of acceptable quality, followed by (ii) the optional part, that can be executed partially or fully to refine the initially obtained result in order to increase the result-accuracy, without violating the time-constraint. This paper introduces DELICIOUS, a novel hybrid offline-online scheduling strategy for AC real-time dependent tasks. By employing an efficient heuristic algorithm, DELICIOUS first generates a schedule for a task-set with an objective to maximize the results-accuracy, while respecting system-wide constraints. During execution, DELICIOUS then introduces a prudential cache resizing that reduces temperature of the adjacent cores, by generating thermal buffers at the turned off cache ways. DELICIOUS further trades off this thermal benefits by enhancing the processing speed of the cores for a stipulated duration, called V/F Spiking, without violating the power budget of the core, to shorten the execution length of the tasks. This reduced runtime is exploited either to enhance result-accuracy by dynamically adjusting the optional part, or to reduce temperature by enabling sleep mode at the cores. While surpassing the prior art, DELICIOUS offers 80% result-accuracy with its scheduling strategy, which is further enhanced by 8.3% in online, while reducing runtime peak temperature by 5.8 °C on average, as shown by benchmark based evaluation on a 4-core based multicore.

show abstract

Section: State-of-the-artmentioning

confidence: 99%

Section: State-of-the-artmentioning

confidence: 99%

DELICIOUS: Deadline-Aware Approximate Computing in Cache-Conscious Multicore

Saha

Chakraborty

Agarwal

et al. 2023

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…Approaches exist without applying a fault tolerance policy, e.g., the task mapping problem is decomposed into a sub-problem that satisfies the reliability constraint and another that minimizes resources [5] and a whale optimization algorithm is proposed [6]. In [7], the scheduling algorithm for dependent multi-version tasks is studied based on Forward List Scheduling with the goal of minimizing the total energy consumption under real-time constraint. Approaches execute a recovery task, e.g., individual [8] or shared [2,9], or both [10], with maximum frequency, exploring available time slack to meet the reliability constraint.…”

Section: Related Work and Motivationmentioning

confidence: 99%

Near-optimal energy-efficient partial-duplication task mapping of real-time parallel applications

Cui

Kritikakou

et al. 2023

Journal of Systems Architecture

View full text Add to dashboard Cite

“…Roeder et al,. [20] have experimented to reduce total energy usage, this paper provides an off-line scheduling approach based on forward list scheduling for dependent multi version tasks. Our heuristic allows apps to dynamically adjust voltage and frequency while they were running since it takes into consideration Dynamic Voltage and Frequency Scaling (DVFS).…”

Section: Literature Reviewmentioning

confidence: 99%

Multiobjective Approach to Schedule DAG Tasks on Voltage Frequency Islands

Sanchit

Singh

2023

IEEE Access

View full text Add to dashboard Cite

Scheduling a Directed Acyclic Graph (DAG) on voltage frequency islands involves dividing the available processing units into multiple islands with varying voltage and frequency levels, and then mapping the tasks of the DAG to the islands while minimizing the makespan and overall energy consumption. In this research work, a novel DAG task scheduling model is introduced with the assistance acquired from the deep learning paradigm. The proposed model includes four major phases: (a) DAG modelling, (b) Voltage frequency island partitioning, (c) core temperature prediction and (d) scheduling optimization. Initially, the Directed Acyclic Graph (DAG) model is designed. The nodes of DAG represent tasks and the edges represent dependencies between tasks. Then, in the Voltage frequency island partitioning, the available processing units into multiple voltage frequency islands. This can be done based on the power consumption of each unit, and the task requirements. Subsequently, the Recurrent Neural Network (RERNN) is trained to predict the core temperature of each voltage frequency island based on the multi-objectives like execution time, makespan, overall energy consumption. Then, the scheduling of the DAG on the voltage frequency islands is optimized using the Self-Improved Pelican Optimization Algorithm (SI-POA). The proposed SI-POA model is an extended version of the standard POA model. The SI-POA model is inspired by the behavior by the natural behavior of pelicans during hunting. In the scheduling optimization phase, the SI-POA algorithm to optimize the scheduling of the DAG on the voltage frequency islands while taking into account the predicted core temperature of each island based on the Recalling-enhanced recurrent neural network (RERNN) model. The goal is to minimize the makespan and overall energy consumption of the DAG while keeping the core temperature of each island within safe limits.

show abstract

Energy-aware scheduling of multi-version tasks on heterogeneous real-time systems

Cited by 19 publications

References 27 publications

DELICIOUS: Deadline-Aware Approximate Computing in Cache-Conscious Multicore

DELICIOUS: Deadline-Aware Approximate Computing in Cache-Conscious Multicore

Near-optimal energy-efficient partial-duplication task mapping of real-time parallel applications

Multiobjective Approach to Schedule DAG Tasks on Voltage Frequency Islands

Contact Info

Product

Resources

About