9,234 Hits in 3.4 sec

Fair Resource Sharing for Dynamic Scheduling of Workflows on Heterogeneous Systems [chapter]

Hamid Arabnejad, Jorge G. Barbosa, Frédéric Suter
2014 High-Performance Computing on Complex Environments  
We would like also to thank the support given by the European Cost Action IC0805 Open Network for High-Performance  ...  CONCURRENT WORKFLOW SCHEDULING Recently, several algorithms have been proposed for concurrent workflow scheduling to improve the execution time of several applications in an HCS system.  ...  and tools for mapping and executing applications onto distributed and heterogeneous systems.  ... 
doi:10.1002/9781118711897.ch9 fatcat:wfkx7m5cbfg3fcuzfbrzvt2laq

Network-Aware HEFT Scheduling for Grid

Muhammad Murtaza Yousaf, Michael Welzl
2014 The Scientific World Journal  
It is shown how misleading a schedule can be if the impact of parallel data transfers that share a bottleneck is ignored. A network-aware HEFT can be used to yield a benefit for Grid applications.  ...  In the proposed mechanism, such data transfers are stretched to their realistic completion time. A HEFT schedule with stretched data transfers exhibits the realisticmakespanof the schedule.  ...  Real-Time Processing Applications. Many highly data intensive applications today require a real-time or near real-time response from the execution system [5] .  ... 
doi:10.1155/2014/317284 pmid:24587719 pmcid:PMC3919093 fatcat:3bvwxaiplveh7aksuybvguw3by

Batch queue resource scheduling for workflow applications

Yang Zhang, Charles Koelbel, Keith Cooper
2009 2009 IEEE International Conference on Cluster Computing and Workshops  
This paper introduces a scheduling technique that aggregates a workflow application into several subcomponents.  ...  Workflow computations have become a major programming paradigm for scientific applications.  ...  This work was supported in part by the Shared University Grid at Rice funded by NSF under Grant EIA-0216467, and a partnership between Rice University, Sun Microsystems, and Sigma Solutions, Inc.  ... 
doi:10.1109/clustr.2009.5289186 dblp:conf/cluster/ZhangKC09 fatcat:dsi3y6ml25frfcpeaj3sje4jnq

Shared recovery for energy efficiency and reliability enhancements in real-time applications with precedence constraints

Baoxian Zhao, Hakan Aydin, Dakai Zhu
2013 ACM Transactions on Design Automation of Electronic Systems  
Shared recovery for energy efficiency and reliability enhancements in real-time applications with precedence constraints.  ...  Then, we propose a shared recovery based frequency assignment technique (namely SHR-DAG) and prove its optimality to minimize energy consumption while preserving the system reliability.  ...  SYSTEM MODELS Application Model In this work, we consider a real-time application consisting of n frame-based dependent tasks running on a single-processor system.  ... 
doi:10.1145/2442087.2442094 fatcat:ictkr7pfi5cr5jlrufnyy3nfhy

The Proceedings of First Work-in-Progress Session of The CSI International Symposium on Real-Time and Embedded Systems and Technologies [article]

Ali Behnoudfar, Seyyed Hossein Hosseini Zahani, Mojtaba Hatami, Mahmoud Naghibzadeh, Boshra Taheri, Fathieh Faghih, Mehdi Kargahi
2019 arXiv   pre-print
The topics of interest in RTEST WiP span over all theoretical and application-oriented aspects, reporting design, analysis, implementation, evaluation, and empirical results, of real-time and embedded  ...  systems, internet-of-things, and cyber-physical systems.  ...  techniques for multicore scheduling on these systems [4] .  ... 
arXiv:1904.06995v1 fatcat:7lvriwiw5fd55njqithwclrxru

MXDAG: A Hybrid Abstraction for Cluster Applications [article]

Weitao Wang, Sushovan Das, Xinyu Crystal Wu, Zhuang Wang, Ang Chen, T. S. Eugene Ng
2021 arXiv   pre-print
In contrast, Coflow abstraction collectively schedules network flows among compute tasks but lacks the end-to-end view of the application DAG.  ...  DAG-based abstraction primarily targets compute tasks and has no explicit network-level scheduling.  ...  For the DAG with asymmetric topology, The optimal solution delays the start time for f 4 and avoid resource sharing on the source NIC on the host C.  ... 
arXiv:2107.07442v1 fatcat:iqahcvjwufelfi4jwywrh6mf6y

WorkStealing Algorithm for Load Balancing in Grid Computing

Hadeer S. Hossam, Hala Abdel-Galil, Mohamed Belal
2021 International Journal of Advanced Computer Science and Applications  
Grid computing is a computer network in which many resources and services are shared for performing a specific task.  ...  In this paper, we propose WorkStealing-Grid Cost Dependency Matrix (WS-GCDM) which schedule DAG tasks according to their data transfer cost, dependency between tasks and load of the available resources  ...  Fig. 4 .Fig. 5 . 45 Resource Busy Time Percentage for GCDM Algorithm on Random DAG with 40 Tasks. Resource Busy Time Percentage for WS-GCDM Algorithm on Random DAG with 40 Tasks.  ... 
doi:10.14569/ijacsa.2021.0120711 fatcat:zre3veetbrdkpiddoh5ynlkm3y

Towards efficient processing of latency-sensitive serverless DAGs at the edge

Xiaosu Lyu, Ludmila Cherkasova, Robert Aitken, Gabriel Parmer, Timothy Wood
2022 Proceedings of the 5th International Workshop on Edge Systems, Analytics and Networking  
CCS CONCEPTS • Computing methodologies → Distributed computing methodologies; • Computer systems organization → Real-time system architecture.  ...  Many emerging novel applications expect "near real-time" processing and responses, which can not be guaranteed by today's Cloud and would require processing at the Edge.  ...  In our future work, we are continuing to expand Sledge with support for more complex DAG functions and exploring how the scheduling and admission control systems can be improved to provide stronger deadline  ... 
doi:10.1145/3517206.3526274 fatcat:45p6zzdng5bspeea2h4dxvpcfi

Minimizing response times of automotive dataflows on multicore

Glenn A. Elliott, Namhoon AKim, Jeremy P. Erickson, Cong Liu, James H. Andersony
2014 2014 IEEE 20th International Conference on Embedded and Real-Time Computing Systems and Applications  
We implement these techniques in PGM RT , a portable middleware framework for managing real-time dataflow applications on multicore platforms.  ...  Results for our test platform show that cache-aware clustered scheduling outperforms naïve partitioned and global approaches in terms of schedulability and end-to-end response times of dataflows. *  ...  Shige Wang of General Motors for his helpful comments on drafts of this paper.  ... 
doi:10.1109/rtcsa.2014.6910527 dblp:conf/rtcsa/ElliottAELA14 fatcat:t57zg2tz3vftxp5bunjfcj4enu

Dynamic scheduling for workflow applications over virtualized optical networks

Jingyu Ding, Yan Wang, Jiajin Le, Yaohui Jin
2011 2011 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)  
Joint scheduling of both computation and communication resources for workflow based distributed computing application over optical networks has been studied recently.  ...  In this paper, we propose to employ shared virtualized optical network (VON) for the task scheduling problem.  ...  When the traffic load is high (>350), there is less shared bandwidth to utilize for the application scheduler, which results in deduction of rescheduling times.  ... 
doi:10.1109/infcomw.2011.5928793 fatcat:y7ihbiletffhvaehwmob2afiau

EasyPDP: An Efficient Parallel Dynamic Programming Runtime System for Computational Biology

Shanjiang Tang, Ce Yu, Jizhou Sun, Bu-Sung Lee, Tao Zhang, Zhen Xu, Huabei Wu
2012 IEEE Transactions on Parallel and Distributed Systems  
The experimental results illustrate that EasyPDP system is fine and provides an efficient infrastructure for dynamic programming algorithms.  ...  Based on the model, EasyPDP runtime system is designed and implemented. It automatically handles thread creation, dynamic data task allocation and scheduling, data partitioning, and fault tolerance.  ...  ACKNOWLEDGMENTS The authors would like to thank the editor, all the reviewers, Chao Sun, Jun Du, Liya Fan, Libo Sun, and Tingxu Yan for the help in improving this paper.  ... 
doi:10.1109/tpds.2011.218 fatcat:dql74n6t4repje7n3zk4hsjj5q

Scheduling Task-parallel Applications in Dynamically Asymmetric Environments [article]

Jing Chen, Pirah Noor Soomro, Mustafa Abduljabbar, Madhavan Manivannan, Miquel Pericas
2020 arXiv   pre-print
to handle scenarios in which system performance is not only unknown but also changing over time.  ...  Shared resource interference is observed by applications as dynamic performance asymmetry.  ...  Applications sharing system resources will observe a performance (i.e. execution time) variability during such interfering events.  ... 
arXiv:2009.00915v2 fatcat:xspjxhx6hrhajkzxpvypa6kmyu

Dynamic Task Distribution Model for On-Chip Reconfigurable High Speed Computing System

Mahendra Vucha, Arvind Rajawat
2015 International Journal of Reconfigurable Computing  
Some benchmark applications are represented as DAG and are distributed to the resources of RHSCS based on DTD-MLF model.  ...  The DTD-MLF methodology takes the advantage of runtime design parameters of an application represented as DAG and considers the attributes of tasks in DAG and computing resources to distribute the tasks  ...  An efficient multitask scheduler [14] proposed for runtime reconfigurable system introduced a new parameter called Time-Improvement as cost function for compiler assisted scheduling models.  ... 
doi:10.1155/2015/783237 fatcat:kozszwtk4jbl3dvaqqnipeq6ji


Quan Chen, Minyi Guo, Zhiyi Huang
2012 Proceedings of the 26th ACM international conference on Supercomputing - ICS '12  
CATS adopts an online DAG partitioner based on the profiling information to ensure tasks with shared data can efficiently utilize the shared cache.  ...  To address the problem, this paper proposes a Cache Aware Task-Stealing (CATS) scheduler, which uses the shared cache efficiently with an online profiling method and schedules tasks with shared data to  ...  Acknowledgment This work was partially supported by Shanghai Excellent Academic Leaders Plan(No. 11XD1402900), 863 program 2011AA01A202, NSFC (Grant No. 60725208, 61003012) and National Science Fund for  ... 
doi:10.1145/2304576.2304599 dblp:conf/ics/ChenGH12 fatcat:l5hy5yt33nfcdni5ktz7ssiaoe

Resource Management in the Multi-Tenant Cloud Environment

Piwal Priya, Mandre B.
2017 International Journal of Computer Applications  
The simulation results shows that the scheduling algorithm improves the performance of scientific workflows and helps in minimization of workflow completion time, tardiness, execution cost and use of idle  ...  The aim of the system is to handle resource management by executing scientific workflows.  ...  The WorkflowSim depends on CloudSim for providing accurate and suitable task level execution model, such as time-shared and space-shared model.  ... 
doi:10.5120/ijca2017915064 fatcat:yzhi74iamnfdfhn2xa5cbe5y6q
« Previous Showing results 1 — 15 out of 9,234 results