One step toward bridging the gap between theory and practice in moldable task scheduling with precedence constraints

Hunold, Sascha

doi:10.1002/cpe.3372

Cited by 15 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combining all these parameters, we obtain a dataset of 108 DAGs. This dataset has already been used to model workflows in the scheduling literature [35,36]. We split it in two parts in the representations: the sparse DAGGEN dataset contains the DAGs with a density of 0.2 and the dense DAGGEN dataset contains the DAGs with a density of 0.8.…”

Section: Simulation Resultsmentioning

confidence: 99%

Limiting the memory footprint when dynamically scheduling DAGs on shared-memory platforms

Marchal

Simon

Vivien

2019

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Scientific workflows are frequently modeled as Directed Acyclic Graphs (DAGs) of tasks, which represent computational modules and their dependences in the form of data produced by a task and used by another one. This formulation allows the use of runtime systems which dynamically allocate tasks onto the resources of increasingly complex computing platforms. However, for some workflows, such a dynamic schedule may run out of memory by processing too many tasks simultaneously. This paper focuses on the problem of transforming such a DAG to prevent memory shortage, and concentrates on shared memory platforms. We first propose a simple model of DAGs which is expressive enough to emulate complex memory behaviors. We then exhibit a polynomial-time algorithm that computes the maximum peak memory of a DAG, that is, the maximum memory needed by any parallel schedule. We consider the problem of reducing this maximum peak memory to make it smaller than a given bound. Our solution consists in adding new fictitious edges, while trying to minimize the critical path of the graph. After proving that this problem is NP-complete, we provide an ILP solution as well as several heuristic strategies that are thoroughly compared by simulation on synthetic DAGs modeling actual computational workflows. We show that on most instances we are able to decrease the maximum peak memory at the cost of a small increase in the critical path, thus with little impact on the quality of the final parallel schedule.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Limiting the memory footprint when dynamically scheduling DAGs on shared-memory platforms

Marchal

Simon

Vivien

2019

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

show abstract

“…Combining all these parameters, we obtain a dataset of 108 DAGs. This dataset has already been used to model workflows in the scheduling literature [15,9]. We split it in two parts in the representations: the sparse DAGGEN dataset contains the DAGs with a density of 0.2 and the dense DAGGEN dataset contains the DAGs with a density of 0.8.…”

Section: Simulation Resultsmentioning

confidence: 99%

Parallel Scheduling of DAGs under Memory Constraints

Marchal

Nagy

Simon

et al. 2018

2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS)

View full text Add to dashboard Cite

Scientific workflows are frequently modeled as Directed Acyclic Graphs (DAG) of tasks, which represent computational modules and their dependencies in the form of data produced by a task and used by another one. This formulation allows the use of runtime systems which dynamically allocate tasks onto the resources of increasingly complex computing platforms. However, for some workflows, such a dynamic schedule may run out of memory by exposing too much parallelism. This paper focuses on the problem of transforming such a DAG to prevent memory shortage, and concentrates on shared memory platforms. We first propose a simple model of DAGs which is expressive enough to emulate complex memory behaviors. We then exhibit a polynomial-time algorithm that computes the maximum peak memory of a DAG, that is, the maximum memory needed by any parallel schedule. We consider the problem of reducing this maximum peak memory to make it smaller than a given bound by adding new fictitious edges, while trying to minimize the critical path of the graph. After proving this problem NP-complete, we provide an ILP solution as well as several heuristic strategies that are thoroughly compared by simulation on synthetic DAGs modeling actual computational workflows. We show that on most instances we are able to decrease the maximum peak memory at the cost of a small increase in the critical path, thus with little impact on quality of the final parallel schedule. Key-words: Ordonnancement parallèle de DAGs sous contraintes mémoireRésumé : Les applications de calcul scientifique sont souvent modélisées par des graphes de tâches orientés acycliques (DAG), qui représentent les tâches de calcul et leurs dépendances, sous la forme de données produites par une tâche et utilisées par une autre. Cette formulation permet l'utilisation d'API qui allouent dynamiquement les tâches sur les ressources de plateformes de calcul hétérogènes de plus en plus complexes. Cependant, pour certaines applications, un tel ordonnancement dynamique peut manquer de mémoire en exploitant trop de parallélisme. Cet article porte sur le problème consistant à transformer un tel DAG pour empêcher toute pénurie de mémoire, en se concentrant sur les plateformes à mémoire partagée. On propose tout d'abord un modèle simple de graphe qui est assez expressif pour émuler des comportements mémoires complexes. On expose ensuite un algorithme polynomial qui calcule le pic mémoire maximum d'un DAG, qui représente la mémoire maximale requise par tout ordonnancement parallèle. On considère ensuite le problème consistant à réduire ce pic mémoire maximal pour qu'il devienne plus petit qu'une borne donnée en rajoutant des arêtes fictives, tout en essayant de minimiser le chemin critique du graphe. Après avoir prouvé ce problème NPcomplet, on fournit un programme linéaire en nombres entiers le résolvant, ainsi que plusieurs stratégies heuristiques qui sont minitieusement comparées-sur des graphes synthétiques modélisant des applications de calcul réelles. On montre que sur la plupar...

show abstract

“…Off-and on-line heuristics with performance guarantees are often developed for multiprocessor task scheduling problems, see, for example, Wang and Cheng [62,61], Choundhary et al [18], Srinivasa Prasanna and Musicus [53], Blazewicz et al [11], Blazewicz et al [9], Dutot et al [25] and Hunold [31].…”

Section: Problem F Easible(q)mentioning

confidence: 99%

Optimal workforce assignment to operations of a paced assembly line

Dolgui

Kovalev

Kovalyov

et al. 2018

European Journal of Operational Research

View full text Add to dashboard Cite

To cite this version:Alexandre Dolgui, Sergey Kovalev, Mikhail Kovalyov, Sergey Malyutin, Ameur Soukhal. Optimal workforce assignment to operations of a paced assembly line. European Journal of Operational Research, Elsevier, 2018, 264 (1), pp.200-211. 10.1016/j.ejor.2017 Optimal workforce assignment to operations of a paced assembly line AbstractWe study a paced assembly line intended for manufacturing different products. Workers with identical skills perform non-preemptable operations whose assignment to stations is known. Operations assigned to the same station are executed sequentially, and they should follow the given precedence relations. Operations assigned to different stations can be performed in parallel.The operation's processing time depends on the number of workers performing this operation.The problem consists in assigning workers to operations such that the maximal number of workers employed simultaneously in the assembly line is minimized, the line cycle time is not exceeded and the box constraints specifying the possible number of workers for each operation are not violated. We show that the general problem is NP-hard in the strong sense, develop conventional and randomized heuristics, propose a reduction to a series of feasibility problems, present a MILP model for the feasibility problem, show relation of the feasibility problem to multi-mode project scheduling and multiprocessor scheduling, establish computational complexity of several special cases based on this relation and provide computer experiments with real and simulated data.

show abstract

One step toward bridging the gap between theory and practice in moldable task scheduling with precedence constraints

Cited by 15 publications

References 23 publications

Limiting the memory footprint when dynamically scheduling DAGs on shared-memory platforms

Limiting the memory footprint when dynamically scheduling DAGs on shared-memory platforms

Parallel Scheduling of DAGs under Memory Constraints

Optimal workforce assignment to operations of a paced assembly line

Contact Info

Product

Resources

About