Filters








51,042 Hits in 3.4 sec

Effective distributed scheduling of parallel workloads

Andrea C. Dusseau, Remzi H. Arpaci, David E. Culler
1996 Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems - SIGMETRICS '96  
For these reasons, we are motivated to investigate whether or not local schedulers can be used to effectively schedule parallel workloads.  ...  We present a distributed algorithm for time-sharing parallel workloads that is competitive with coscheduling. lrnphcit scheduling allows each local scheduler in the system to make independent decisions  ... 
doi:10.1145/233013.233020 dblp:conf/sigmetrics/Arpaci-DusseauAC96 fatcat:w4xtgqhnibd77be6t5gorf6mse

Effective distributed scheduling of parallel workloads

Andrea C. Dusseau, Remzi H. Arpaci, David E. Culler
1996 Performance Evaluation Review  
For these reasons, we are motivated to investigate whether or not local schedulers can be used to effectively schedule parallel workloads.  ...  We present a distributed algorithm for time-sharing parallel workloads that is competitive with coscheduling. lrnphcit scheduling allows each local scheduler in the system to make independent decisions  ... 
doi:10.1145/233008.233020 fatcat:4263wilhlrhclhuymxn3msgmj4

The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers

S. Bani-Mohammad, M. Ould-Khaoua, Lewis M. Mackenzie, I. Ababneh, J. D. Ferguson
2008 Proceedings, International Parallel and Distributed Processing Symposium (IPDPS)  
2008) The effect of real workloads and stochastic workloads on the performance of allocation and scheduling algorithms in 2D mesh multicomputers.  ...  In this paper, we evaluate the performance of several well-known processor allocation and job scheduling strategies based on a real workload trace and compare the results against those obtained from using  ...  Dror Feitelson, School of Computer Science and Engineering, Hebrew University, who provided us workload traces and information regarding the traces. Also, we would like to thank Dr.  ... 
doi:10.1109/ipdps.2008.4536492 dblp:conf/ipps/Bani-MohammadOMAF08 fatcat:ri3to5urkjejhgtq3z5e23r5r4

Pitfalls in Parallel Job Scheduling Evaluation [chapter]

Eitan Frachtenberg, Dror G. Feitelson
2005 Lecture Notes in Computer Science  
There are many choices to make when evaluating the performance of a complex system. In the context of parallel job scheduling, one must decide what workload to use and what measurements to take.  ...  In this paper we document numerous pitfalls one may fall into, with the hope of providing at least some help in avoiding them.  ...  Workload Structure Workload issues span all methods of parallel job scheduling evaluation.  ... 
doi:10.1007/11605300_13 fatcat:sub42wkz6vfpljbk7n4hzouoeu

Efficient Inter-Device Task Scheduling Schemes for Multi-Device Co-Processing of Data-Parallel Kernels on Heterogeneous Systems

Lanjun Wan, Weihua Zheng, Xinpan Yuan
2021 IEEE Access  
which is more suitable for data-parallel kernels whose computation and data are uniformly distributed. • An asynchronous-based dynamic and elastic task scheduling scheme is designed to effectively partition  ...  work across an arbitrary set of devices, which is more suitable for data-parallel kernels whose computation and data are non-uniformly distributed. • Experiments are conducted to verify the effectiveness  ... 
doi:10.1109/access.2021.3073955 fatcat:hp2cg7nf4ff23paxtegyh6ndli

Adaptively scheduling parallel loops in distributed shared-memory systems

Yong Yan, Canming Jin, Xiaodong Zhang
1997 IEEE Transactions on Parallel and Distributed Systems  
that match the real workload distributions at runtime.  ...  Our results show that using runtime information to adaptively adjust scheduling granularity is an effective way to handle loops with a wide range of load distributions when no prior knowledge of the execution  ...  ACKNOWLEDGMENTS We appreciate Neal Wagner's and Samir Das' careful reading of the manuscript and constructive comments.  ... 
doi:10.1109/71.569656 fatcat:pmfuc7jl5ff5harpbfnafr42fi

User group-based workload analysis and modelling

B. Song, C. Ernemann, R. Yahyapour
2005 CCGrid 2005. IEEE International Symposium on Cluster Computing and the Grid, 2005.  
Knowledge about the workload is an important aspect for scheduling of resources as parallel computers or Grid components.  ...  However, job scheduling for single parallel installations as well as for Grid systems started to focus more on the quality of service for specific user groups.  ...  We denote the estimated combined distribution function for a user group k as G k . However the G k distribution function set does not address the power of 2 effect for the parallelism.  ... 
doi:10.1109/ccgrid.2005.1558664 dblp:conf/ccgrid/SongEY05 fatcat:nhslxjkxwnfevbbety54qnog6y

Efficiency Measurement for Effective Stress Management in Heterogeneous 2-D Mesh Processor

Arashdeep Singh, Sunny Behal, Ankit Arora
2013 International Journal of Computer Applications  
Such types of distributed cluster along with heterogeneous behavior will requires vast amount of scheduling efforts.  ...  Complexity increases as scheduler has to detect dynamic characteristics of the processors. Parallel schedulers are implemented in cluster technology for job assignment and placement.  ...  An efficient scheduling mechanisms will provides an effective utilization of multiprocessor hardware with major aim is to exploit the machine efficiency.  ... 
doi:10.5120/14066-2330 fatcat:ca4fmkpao5ee5g4fp27yeahqhu

A case for conservative workload modeling: Parallel job scheduling with daily cycles of activity

D.G. Feitelson, E. Shmueli
2009 2009 IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems  
Using parallel job scheduling as a case study, and daily cycles of activity as the attribute in dispute, we present two schedulers whose simulated performance seems identical without cycles, but then becomes  ...  of running and waiting jobs as sampled at different times of the day, with the CREASY and EASY schedulers (250 users).  ...  Our workload data is based on traces from the Parallel Workloads Archive, and we thank all those who have made this data available.  ... 
doi:10.1109/mascot.2009.5366139 dblp:conf/mascots/FeitelsonS09 fatcat:itghdufncbh27mfezmd5ghqwg4

Job scheduling strategies for networks of workstations [chapter]

B. B. Zhou, R. P. Brent, D. Walsh, K. Suzaki
1998 Lecture Notes in Computer Science  
In this paper we first introduce the concepts of utilisation ratio and effective speedup and their relations to the system performance.  ...  workloads.  ...  A new system based on these ideas is currently under construction on a distributed memory parallel machine, the Fujitsu AP1000+, at the Australian National University.  ... 
doi:10.1007/bfb0053985 fatcat:odl2shhspngzfdfvy2jtlup7xe

Parallel Job Scheduling in Cloud with Lookahead and Workload Consolidation

Swathi S, Thushara A, Shabi Kamal
2014 International Journal of Computer Applications  
Many of these applications may be complex which requires parallel processing capabilities. Parallel job scheduling techniques mainly focus on improving responsiveness and utilization.  ...  For a data center that deals with parallel jobs, it is important to devise an optimal schedule which results in maximal utilization of available node capacity.  ...  Many parallel job scheduling strategies have been proposed for scheduling parallel jobs in distributed environment.  ... 
doi:10.5120/17483-8386 fatcat:io2zi7aksfgnrczp34oeh236xi

An evaluation of parallel job scheduling for ASCI Blue-Pacific

H. Franke, J. Jann, J. E. Moreira, P. Pattnaik, M. A. Jette
1999 Proceedings of the 1999 ACM/IEEE conference on Supercomputing (CDROM) - Supercomputing '99  
Starting with a real workload obtained from job logs of one of the ASCI machines, we generate a statistical model of this workload using Hyper Erlang distributions.  ...  We then vary the parameters of those distributions to generate various workloads, representative of different operating points of the machine.  ...  Parallel workloads often are over-dispersive.  ... 
doi:10.1145/331532.331577 dblp:conf/sc/FrankeJMPJ99 fatcat:wio6bwidl5a3nhyvp5xmdjiqo4

A Probabilistic Machine Learning Approach to Scheduling Parallel Loops with Bayesian Optimization

Khu-rai Kim, Youngjae Kim, Sungyong Park
2020 IEEE Transactions on Parallel and Distributed Systems  
This paper proposes Bayesian optimization augmented factoring self-scheduling (BO FSS), a new parallel loop scheduling strategy.  ...  By accurately modeling the temporal locality effect, our locality-aware GP model accelerates the convergence of BO.  ...  Myoung Suk Kim for his insightful comments about our statistical analysis and Rover Root for his helpful comments about the scientific workloads considered in this work.  ... 
doi:10.1109/tpds.2020.3046461 fatcat:fxc4d32wrba2pgoank5nep6s5a

Designing parallel loop self-scheduling schemes using the hybrid MPI and OpenMP programming model for multi-core grid systems

Chao-Chin Wu, Chao-Tung Yang, Kuan-Chou Lai, Po-Hsun Chiu
2010 Journal of Supercomputing  
of them were aimed at parallel loop self-scheduling.  ...  Loop scheduling on parallel and distributed systems has been thoroughly investigated in the past.  ...  We also propose to use a parameter, SWR, to alleviate the effect of irregular workload.  ... 
doi:10.1007/s11227-010-0418-y fatcat:3phn3gjn7zgkzbv2qo4zwzdpny

A Parallel Boundary Element Method for the Electromagnetic Analysis of Large Structures With Lossy Conductors [article]

Damian Marek, Shashwat Sharma, Piero Triverio
2021 arXiv   pre-print
We propose a parallelization strategy that distributes these two workloads evenly over thousands of processing cores.  ...  Unlike existing parallel BEM solvers, we use a formulation that rigorously models the skin effect, which results in two coupled computational workloads.  ...  In fact, distributing a set of discrete parallel computational tasks over an arbitrary number of identical processing units is a variant of the multiprocessor scheduling problem [32] .  ... 
arXiv:2108.03991v1 fatcat:jkhdynqf4jduddrkrjclj3zqcm
« Previous Showing results 1 — 15 out of 51,042 results