Scheduling Moldable BSP Tasks

Dutot, Pierre-François; Netto, Marco A. S.; Goldman, Alfredo; Kon, Fábio

doi:10.1007/11605300_8

Cited by 15 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This number can be optimized but cannot be changed after the execution started. For moldable jobs, we consider the model defined in . Let r e q t i m e i be the execution time of job J i , which requires at most r e q p r o c i PEs.…”

Section: Frameworkmentioning

confidence: 99%

Using a sparse promoting method in linear programming approximations to schedule parallel jobs

Chrétien¹,

Nicod

Philippe

et al. 2014

Concurrency and Computation

View full text Add to dashboard Cite

Summary In this paper, we tackle the well‐known problem of scheduling a collection of parallel jobs on a set of processors either in a cluster or in a multiprocessor computer. For the makespan objective, that is, the completion time of the last job, this problem has been shown to be NP‐hard, and several heuristics have already been proposed to minimize the execution time. In this paper, we consider both rigid and moldable jobs. Our main contribution is the introduction of a new approach to the scheduling problem, based on the recent discoveries in the field of compressed sensing. In the proposed approach, all possible positions and shapes of the jobs are encoded into a matrix, and the scheduling is performed by selecting the best columns under natural constraints. Thus, the solution to the new scheduling formulation is naturally sparse, and we may use appropriate relaxations to achieve the optimization task in the quickest possible way. Among many possible relaxation strategies, we choose to minimize the ℓp‐quasi‐norm for p∈(0,1). Minimization of the ℓp‐quasi‐norm is implemented via a successive linear programming approximation heuristic. We propose several new algorithms based on this approach, and we assess their efficiency through simulations. The experiments show that the scheme outperforms the classic Largest Task First list based algorithm for scheduling small to medium instances but needs improvements to compete on larger numbers of jobs. Copyright © 2014 John Wiley & Sons, Ltd.

show abstract

Section: Frameworkmentioning

confidence: 99%

Using a sparse promoting method in linear programming approximations to schedule parallel jobs

Chrétien¹,

Nicod

Philippe

et al. 2014

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…The considered moldable jobs respect the model defined in [10]. Let reqtime i be the duration of job i which requires at most reqproc i PEs.…”

Section: Frameworkmentioning

confidence: 99%

“…In [2] static scheduling of rigid parallel jobs for minimizing the makespan is studied and in [1] for minimizing the sum of the completion time of each job. In [10], Dutot et al consider the problem of scheduling moldable jobs with the objective of minimizing the makespan. The authors present experimental results where the well-known Largest Task First (LTF) algorithm is the best for the makespan objective.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Job Scheduling Using Successive Linear Programming Approximations of a Sparse Model

Chretien

Nicod

Philippe

et al. 2012

Euro-Par 2012 Parallel Processing

View full text Add to dashboard Cite

In this paper we tackle the well-known problem of scheduling a collection of parallel jobs on a set of processors either in a cluster or in a multiprocessor computer. For the makespan objective, i.e., the completion time of the last job, this problem has been shown to be NP-Hard and several heuristics have already been proposed to minimize the execution time. We introduce a novel approach based on successive linear programming (LP) approximations of a sparse model. The idea is to relax an integer linear program and use ℓp norm-based operators to force the solver to find almost-integer solutions that can be assimilated to an integer solution. We consider the case where jobs are either rigid or moldable. A rigid parallel job is performed with a predefined number of processors while a moldable job can define the number of processors that it is using just before it starts its execution. We compare the scheduling approach with the classic Largest Task First list based algorithm and we show that our approach provides good results for small instances of the problem. The contributions of this paper are both the integration of mathematical methods in the scheduling world and the design of a promising approach which gives good results for scheduling problems with less than a hundred processors.

show abstract

“…It is offered as a function of system management software and is called a scheduler. There are many studies in these days [2] [3]. There are some schedulers commercially available.…”

Section: Introductionmentioning

confidence: 99%

Parameter Optimization of Job Scheduler Based on NQS Simulator

Ito

2008

2008 3rd International Conference on Innovative Computing Information and Control

View full text Add to dashboard Cite

We propose a scientific approach to optimize the system usage with parameter configuration, mainly by developing simulator software for NQS with which the system usage pattern could be virtually simulated with various parameter configurations, consequently makes us possible to see how optimally the system is used with the current configuration. Furthermore this scientific approach is useful to investigate a property of each parameter.

show abstract

Scheduling Moldable BSP Tasks

Abstract: Abstract

Cited by 15 publications

References 19 publications

Using a sparse promoting method in linear programming approximations to schedule parallel jobs

Using a sparse promoting method in linear programming approximations to schedule parallel jobs

Job Scheduling Using Successive Linear Programming Approximations of a Sparse Model

Parameter Optimization of Job Scheduler Based on NQS Simulator

Contact Info

Product

Resources

About