View in EDS

An Application-Level Scheduling with Task Bundling Approach for Many-Task Computing in Heterogeneous Environments

Saved in:
Bibliographic Details
Title: An Application-Level Scheduling with Task Bundling Approach for Many-Task Computing in Heterogeneous Environments
Authors: Xiao, Jian, Zhang, Yu, Chen, Shuwei, Yu, Huashan
Contributors: Peking University Beijing, James J. Park, Albert Zomaya, Sang-Soo Yeo, Sartaj Sahni, TC 10, WG 10.3
Source: Lecture Notes in Computer Science ; 9th International Conference on Network and Parallel Computing (NPC) ; https://inria.hal.science/hal-01551355 ; 9th International Conference on Network and Parallel Computing (NPC), Sep 2012, Gwangju, South Korea. pp.1-13, ⟨10.1007/978-3-642-35606-3_1⟩
Publisher Information: CCSD
Springer
Publication Year: 2012
Subject Terms: application-level scheduling, many task computing, task bundling, traditional scheduling heuristics, [INFO]Computer Science [cs]
Subject Geographic: Gwangju, South Korea
Description: Part 1: Algorithms, Scheduling, Analysis, and Data Mining ; International audience ; Many-Task Computing (MTC) is a widely used computing paradigm for large-scale task-parallel processing. One of the key issues in MTC is to schedule a large number of independent tasks onto heterogeneous resources. Traditional task-level scheduling heuristics, like Min-Min, Sufferage and MaxStd, cannot readily be applied in this scenario. As most of MTC tasks are usually fine-grained, the resource management overhead would be prominent and the multi-core nodes might become hard to be fully utilized. In this paper we propose an application-level scheduling with task bundling approach that utilizes the knowledge of both applications and tasks to overcome these difficulties. Furthermore we adapt the traditional task-level heuristics to our model for MTC scheduling. Experimental results show that these application-level scheduling approaches, when equipped with task bundling, can deliver good performance for Many-Task Computing in terms of both Makespan and Flowtime.
Document Type: conference object
Language: English
DOI: 10.1007/978-3-642-35606-3_1
Availability: https://inria.hal.science/hal-01551355
https://inria.hal.science/hal-01551355v1/document
https://inria.hal.science/hal-01551355v1/file/978-3-642-35606-3_1_Chapter.pdf
https://doi.org/10.1007/978-3-642-35606-3_1
Rights: http://creativecommons.org/licenses/by/ ; info:eu-repo/semantics/OpenAccess
Accession Number: edsbas.2079CE7
Database: BASE
Description
Abstract:Part 1: Algorithms, Scheduling, Analysis, and Data Mining ; International audience ; Many-Task Computing (MTC) is a widely used computing paradigm for large-scale task-parallel processing. One of the key issues in MTC is to schedule a large number of independent tasks onto heterogeneous resources. Traditional task-level scheduling heuristics, like Min-Min, Sufferage and MaxStd, cannot readily be applied in this scenario. As most of MTC tasks are usually fine-grained, the resource management overhead would be prominent and the multi-core nodes might become hard to be fully utilized. In this paper we propose an application-level scheduling with task bundling approach that utilizes the knowledge of both applications and tasks to overcome these difficulties. Furthermore we adapt the traditional task-level heuristics to our model for MTC scheduling. Experimental results show that these application-level scheduling approaches, when equipped with task bundling, can deliver good performance for Many-Task Computing in terms of both Makespan and Flowtime.
DOI:10.1007/978-3-642-35606-3_1