Reliable energy-aware application mapping and voltage–frequency island partitioning for GALS-based NoC

Mahabadi, Aminollah; Zahedi, Sakineh; Khonsari, Ahmad

doi:10.1016/j.jcss.2012.09.006

Cited by 13 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mapping problem of a real-time application with stochastic execution times onto multicore systems is formulated in [102]. The tasks are scheduled on the processors and also allocate the voltage frequency stages for Processing Elements (PEs) with Mixed Integer Linear Programming (MILP) in the GALS-based NoC.…”

Section: Energy-aware Schemesmentioning

confidence: 99%

Towards Task Mapping Approaches in Network on Chips: A Comprehensive Survey

Màsdàrí

2023

Preprint

View full text Add to dashboard Cite

One of the main stages of Network on Chip (NoC) is task mapping where the application tasks are mapped to the processing resources. Task mapping decisions have a direct impact on the NoC performance and can be classified as static or dynamic mapping methods. In this paper, we carry out a comprehensive systematic study of task mapping schemes in various NoCs. For this purpose, firstly, an overview of the task mapping's main concepts is presented. Then, a taxonomy of the mapping schemes regarding their objectives and applied mapping factors is presented and the studied schemes are categorized into fault-tolerant schemes, congestion-aware schemes, communication-aware approaches, temperature-aware methods, and energy-aware schemes. Afterward, their main contributions, provided services, and drawbacks of the proposed studies in the literature are illustrated. Moreover, a comprehensive discussion of various features of the investigated mapping methods is presented and issues such as the applied algorithms, simulators, datasets, and evaluation metrics are discussed. Finally, the concluding issues and open research areas are highlighted.

show abstract

Section: Energy-aware Schemesmentioning

confidence: 99%

Towards Task Mapping Approaches in Network on Chips: A Comprehensive Survey

Màsdàrí

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Several investigations have also been conducted into developing energy-aware task scheduling algorithms to optimize energy consumption by applying Dynamic Voltage Scaling (DVS) technique [13][14][15][16]. In these works, the authors determined task-slack time by considering critical and non-critical paths in job DAGs.…”

Section: Related Workmentioning

confidence: 99%

“…Meanwhile, there is a considerable amount of research work that focuses on reducing power consumption in their proposed bi-objective task scheduling models by minimizing the value of their developed predefined power consumption objective functions for multi-core processors and cloud environment [11,12]. In addition, several studies have been undertaken in the area of energy-aware task scheduling by applying the Dynamic Voltage Frequency Scaling (DVFS) technique [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Evolutionary algorithm-based multi-objective task scheduling optimization model in cloud environments

Ramezani

Taheri

et al. 2015

World Wide Web

View full text Add to dashboard Cite

Optimizing task scheduling in a distributed heterogeneous computing environment, which is a nonlinear multi-objective NP-hard problem, plays a critical role in decreasing service response time and cost, and boosting Quality of Service (QoS). This paper, considers four conflicting objectives, namely minimizing task transfer time, task execution cost, power consumption, and task queue length, to develop a comprehensive multi-objective optimization model for task scheduling. This model reduces costs from both the customer and provider perspectives by considering execution and power cost. We evaluate our model by applying two multi-objective evolutionary algorithms, namely Multi-Objective Particle Swarm Optimization (MOPSO) and Multi-Objective Genetic Algorithm (MOGA). To implement the proposed model, we extend the Cloudsim toolkit by using MOPSO and MOGA as its task scheduling algorithms which determine the optimal task arrangement among VMs. The simulation results show that the proposed multi-objective model finds optimal trade-off solutions amongst the four conflicting objectives, which significantly reduces the job response time and makespan. This model not only increases QoS but also decreases the cost to providers. From our experimentation results, we find that MOPSO is a faster and more accurate evolutionary algorithm than MOGA for solving such problems.

show abstract

“…The VFI based NoC-MPSoC (VFI-NoC-HMPSoC) is an ideal choice for data extensive applications due to its higher throughput, lower complexity, and superior energyefficiency Lackey et al (2002). VFI-MPSoCs require lower number of multiple clock first-in-first-out (MCFIFO) and voltage level converters (VLCs) Mahabadi et al (2013). Green computing in modern embedded systems is a challenging facet because higher energy consumption reduces the lifetime of an edge-device in IoT and causes an increased carbon dioxide CO 2 emission i.e.…”

Section: Introductionmentioning

confidence: 99%

Energy-efficient scheduling of streaming applications in VFI-NoC-HMPSoC based edge devices

Tariq

Ali

Liu

et al. 2020

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Energy-aware high-performance computing is becoming a challenging facet for streaming applications at edge devices in Internet-of-Things (IoT) due to the high computational complexity involved. Therefore, the number of processors has increased significantly on the multiprocessor system subsequently, Voltage Frequency Island (VFI) recently adopted for an effective energy management mechanism in the large scale multiprocessor chip designs. In this paper, energy-aware scheduling of real-time streaming applications on edge-devices is investigated. First, an innovative re-timing based technique is developed to transform the dependent workload into an independent task model to avail resources and the wasted slack in the processors with a possible minimal prologue. Moreover, unlike the existing population-based optimization algorithms, a novel population-based algorithm, ARSH-FATI is proposed that can dynamically switch between explorative and exploitative search modes at run-time for performance trade-off. Finally, a communication contention-aware Earliest Edge Consistent Deadline First (EECDF) scheduling algorithm is presented. Our static scheduler ARHS-FATI collectively performs task mapping and ordering. Consequently, its performance is superior to the existing state-of-the-art approach proposed for homogeneous VFI based MPSoCs.

show abstract

Reliable energy-aware application mapping and voltage–frequency island partitioning for GALS-based NoC

Cited by 13 publications

References 39 publications

Towards Task Mapping Approaches in Network on Chips: A Comprehensive Survey

Towards Task Mapping Approaches in Network on Chips: A Comprehensive Survey

Evolutionary algorithm-based multi-objective task scheduling optimization model in cloud environments

Energy-efficient scheduling of streaming applications in VFI-NoC-HMPSoC based edge devices

Contact Info

Product

Resources

About