Scheduling Malleable Task Trees

نویسندگان

  • Bertrand Simon
  • Loris Marchal
  • Frédéric Vivien
  • ENS Lyon
چکیده

Solving sparse linear systems can lead to processing tree workflows on a platform of processors. In this study, we use the model of malleable tasks motivated in [1, 9] in order to study tree workflow schedules under two contradictory objectives: makespan minimization and memory minization. First, we give a simpler proof of the result of [8] which allows to compute a makespan-optimal schedule for tree workflows. Then, we study a more realistic speedup function and show that the previous schedules are not optimal in this context. Finally, we give complexity results concerning the objective of minimizing both makespan and memory. Key-words: Scheduling, Malleable tasks, Task trees, Makespan Minimization, Memory minimization ∗ Bertrand SIMON is with ENS de Lyon, France. E-mail: [email protected] † Loris MARCHAL is with CNRS, France. E-mail: [email protected] ‡ Frédéric VIVIEN is with Inria, France. E-mail: [email protected] Ordonnancement de tâches malléables Résumé : Résoudre des systèmes linéaires creux peut nécessiter le traitement d’arbres de tâches sur une plate-forme de processeurs. Dans cette étude, nous utilisons le modèle de tâches malléables motivé dans [1, 9] pour étudier l’ordonnancement d’arbre de tâches sous plusieurs perspectives. Tout d’abord, nous proposons une preuve plus simple d’un résultat de [8] qui permet de calculer simplement un ordonnancement optimal d’un arbre de tâches malléables pour le temps de complétion. Nous étudions également un modèle de fonction d’accélération plus réaliste, et montrons que l’ordonnancement précédent n’est plus optimal dans ce contexte. Enfin, nous proposons ensuite des résultats de complexité pour le problème de la minimisation simultanée du temps de complétion et de la mémoire. Mots-clés : Ordonnancement, Tâches malléables, Arbre de tâches, Minimisation du makespan, Minimisation de la mémoire Scheduling malleable task trees 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

The Power of Choice in Scheduling Parallel Tasks

A malleable parallel task is one that can be executed on any number of processors, with its execution time being a function of the number of processors allotted to it. A nonmalleable parallel task is one that requires a speciic number of processors. Given n independent parallel tasks and m identical processors, we consider the problem of scheduling these tasks to minimize average completion tim...

متن کامل

An approximation algorithm for scheduling trees of malleable tasks

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau...

متن کامل

Scheduling and Packing Malleable Tasks with Precedence Constraints of Bounded Width

We study two related problems in non-preemptive scheduling and packing of malleable tasks with precedence constraints to minimize the makespan. We distinguish the scheduling variant, in which we allow the free choice of processors, and the packing variant, in which a task must be assigned to a contiguous subset of processors. For precedence constraints of bounded width, we completely resolve th...

متن کامل

Scheduling Trees of Malleable Tasks for Sparse Linear Algebra

Scientific workloads are often described as directed acyclic task graphs. In this paper, we focus on the multifrontal factorization of sparse matrices, whose task graph is structured as a tree of parallel tasks. Among the existing models for parallel tasks, the concept of malleable tasks is especially powerful as it allows each task to be processed on a time-varying number of processors. Follow...

متن کامل

Multiresource Malleable Task Scheduling

We present a technique for generalizing previously known results for single resource task systems to multiresource malleable task systems: Assuming a system with s resources, we apply a transformation which maps the system into a single resource task system. For a large class of heuristics it is shown, that given a heuristic H which achieves a suboptimality bound of c H with respect to the opti...

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:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014