Hybrid scheduling for the parallel solution of linear systems

نویسندگان

  • Patrick Amestoy
  • Abdou Guermouche
  • Jean-Yves L'Excellent
  • Stéphane Pralet
چکیده

In this paper, we consider the problem of designing a dynamic scheduling strategy that takes into account both workload and memory information in the context of the parallel multifrontal factorization. The originality of our approach is that we base our estimations (work and memory) on a static optimistic scenario during the analysis phase. This scenario is then used during the factorization phase to constrain the dynamic decisions. The task scheduler has been redesigned to take into account these new features. Moreover performance have been improved because the new constraints allow the new scheduler to make optimal decisions that were forbidden or too dangerous in unconstrained formulations. Performance analysis show that the memory estimation becomes much closer to the memory effectively used and that even in a constrained memory environment we decrease the factorization time with respect to the initial approach. Key-words: sparse matrices, parallel multifrontal method, dynamic scheduling, memory. This text is also available as a research report of the Laboratoire de l’Informatique du Parallélisme http://www.ens-lyon.fr/LIP and as a technical report from ENSEEIHT-IRIT. Stratégies d’ordonnancement hybrides pour la résolution parallèle de systèmes linéaires Résumé : Nous proposons des stratégies d’ordonnancement bi-critères, qui s’intéressent à la fois à la performance et à la consommation mémoire d’un algorithme parallèle de factorisation de matrices creuses, basé sur la méthode multifrontale. L’originalité de notre approche est que nous basons nos estimations mémoire sur un scénario optimiste (simulation lors de la phase d’analyse), qui est ensuite utilisé lors de la factorisation pour contraindre les décisions dynamiques d’ordonnancement. Un nouvel ordonnanceur a été implanté, qui prend en compte ces nouvelles contraintes. De plus, la performance a été améliorée parce que notre nouvelle approche permet à l’ordonnanceur de prendre des décisions meilleures, qui étaient interdites ou trop dangereuses auparavant. Une analyse de performance montre que les estimations mémoire sont beaucoup plus proches de la mémoire effectivement utilisée, et que le temps de factorisation est amélioré de façon significative par rapport à l’approche initiale. Mots-clés : matrices creuses, méthode multifrontale, ordonnancement dynamique, mémoire Hybrid Scheduling for the Parallel Solution of Linear Systems 3

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Hybrid algorithms for Job shop Scheduling Problem with Lot streaming and A Parallel Assembly Stage

In this paper, a Job shop scheduling problem with a parallel assembly stage and Lot Streaming (LS) is considered for the first time in both machining and assembly stages. Lot Streaming technique is a process of splitting jobs into smaller sub-jobs such that successive operations can be overlapped. Hence, to solve job shop scheduling problem with a parallel assembly stage and lot streaming, deci...

متن کامل

Heuristic approach to solve hybrid flow shop scheduling problem with unrelated parallel machines

In hybrid flow shop scheduling problem (HFS) with unrelated parallel machines, a set of n jobs are processed on k machines. A mixed integer linear programming (MILP) model for the HFS scheduling problems with unrelated parallel machines has been proposed to minimize the maximum completion time (makespan). Since the problem is shown to be NP-complete, it is necessary to use heuristic methods to ...

متن کامل

Simultaneous production planning and scheduling in a hybrid flow shop with time periods and work shifts

Simultaneous production planning and scheduling has been identified as one of the most important factors that affect the efficient implementation of planning and scheduling operations for the production systems. In this paper, simultaneous production planning and scheduling is applied in a hybrid flow shop environment, which has numerous applications in real industrial settings. In this problem...

متن کامل

Generalized Cyclic Open Shop Scheduling and a Hybrid Algorithm

In this paper, we first introduce a generalized version of open shop scheduling (OSS), called generalized cyclic open shop scheduling (GCOSS) and then develop a hybrid method of metaheuristic to solve this problem. Open shop scheduling is concerned with processing n jobs on m machines, where each job has exactly m operations and operation i of each job has to be processed on machine i . However...

متن کامل

Design of a Hybrid Genetic Algorithm for Parallel Machines Scheduling to Minimize Job Tardiness and Machine Deteriorating Costs with Deteriorating Jobs in a Batched Delivery System

This paper studies the parallel machine scheduling problem subject to machine and job deterioration in a batched delivery system. By the machine deterioration effect, we mean that each machine deteriorates over time, at a different rate. Moreover, job processing times are increasing functions of their starting times and follow a simple linear deterioration. The objective functions are minimizin...

متن کامل

A New Hybrid Meta-Heuristics Approach to Solve the Parallel Machine Scheduling Problem Considering Human Resiliency Engineering

This paper proposes a mixed integer programming model to solve a non-identical parallel machine (NIPM) scheduling with sequence-dependent set-up times and human resiliency engineering. The presented mathematical model is formulated to consider human factors including Learning, Teamwork and Awareness. Moreover, processing time of jobs are assumed to be non-deterministic and dependent to their st...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Parallel Computing

دوره 32  شماره 

صفحات  -

تاریخ انتشار 2006