Task scheduling on heterogeneous multiprocessor systems through coherent data allocation

Deng, Zexi; Shen, Hong; Cao, Dun-Qian; Yan, Zihan; Huang, Huimin

doi:10.1002/cpe.6183

Cited by 6 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Static scheduling on HMS has been studied extensively. The proposed algorithms can be divided into list-based, cluster-based, replication-based and guided random search [13]. List-based algorithms involve task priority list construction and task mapping.…”

Section: Related Workmentioning

confidence: 99%

Research and optimization of task schedulingalgorithm based on heterogeneous multi-coreprocessor

Liu,

Ding

2024

Preprint

View full text Add to dashboard Cite

Heterogeneous multi-core processor has the ability to switch between differenttypes of cores to perform tasks, which provides more space and possibility forrealizing efficient operation of computer system and improving computer computing power. Current research focuses on heterogeneous multiprocessor systemswith high performance or low power consumption to reduce system energy consumption. However, some studies have shown that excessive voltage reductionmay lead to an increase in transient failure rates, reducing system reliability. Inorder to solve this problem, this paper studies the energy optimal schedulingproblem of HMSS with DVFS under the constraints of minimum time and reliability, and proposes an improved wild horse optimization algorithm (OIWHO),which improves the efficiency of heterogeneous task scheduling and shortens thetask completion time. The algorithm uses the learning and chaos perturbationstrategies based on opposition and crossover strategies to balance the search andutilization capabilities, and can further improve the performance of OIWHO.Compared with previous work, our proposed algorithm has more advantagesthan existing algorithms. Experimental results show that the average computingtime of OIWHO algorithm is 13.38%, 10.90%, 6.97%, 2.39% and 3.21% fasterthan QHA, PSO, GWO, LFD and OIWOA, respectively. Especially when solvinglarge-scale problems, our algorithm takes less time than other algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Research and optimization of task schedulingalgorithm based on heterogeneous multi-coreprocessor

Liu,

Ding

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Third, another goal of task scheduling is to maintain the load balance among machines. However, task scheduling problem with resource constraints in HCE has been proven to be NP‐complete 2–4 . Hence the task scheduling problem in cross‐domain HCE is still faced with great challenges.…”

Section: Introductionmentioning

confidence: 99%

“…However, task scheduling problem with resource constraints in HCE has been proven to be NP-complete. [2][3][4] Hence the task scheduling problem in cross-domain HCE is still faced with great challenges.…”

Section: Introductionmentioning

confidence: 99%

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Sun

Yang

Lei

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Task scheduling and load balancing problem of heterogeneous computing environment (HCE) is getting more and more attention these days and has become a research hotspot in this field. The task scheduling and load balancing problem of heterogeneous environment, which refers to assigning a set of tasks to a specific set of machines with different hardware and different computing performance with the goal of minimizing task processing time and keeping load balance among machines, has been proved to be an NP-complete problem. The development of artificial intelligence provides new ideas to solve this problem. In this paper, we propose a novel task scheduling and load balancing method based on optimized deep reinforcement learning in HCE. First, we formulate task scheduling problem as a Markov decision process and then adopt a dueling double deep Q-learning network to search the optimal task allocation solution. Then we use two well-known large-scale cluster data sets Google Cloud Jobs data set and Alibaba Cluster Trace data set to validate our approach. The experimental results show that compared with other existing solutions, our proposed method can achieve much shorter task response time and better load balancing effect.

show abstract

Reliability-aware task scheduling for energy efficiency on heterogeneous multiprocessor systems

et al. 2021

View full text Add to dashboard Cite

Task scheduling on heterogeneous multiprocessor systems through coherent data allocation

Cited by 6 publications

References 66 publications

Research and optimization of task schedulingalgorithm based on heterogeneous multi-coreprocessor

Research and optimization of task schedulingalgorithm based on heterogeneous multi-coreprocessor

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Reliability-aware task scheduling for energy efficiency on heterogeneous multiprocessor systems

Contact Info

Product

Resources

About