A lightweight task graph scheduler for distributed high-performance scientific computing

Authors:
Josef Weinbub;Karl Rupp;Siegfried Selberherr
Affiliations:
Institute for Microelectronics, TU Wien, Austria;Institute for Microelectronics, TU Wien, Austria,Institute for Analysis and Scientific Computing, TU Wien, Vienna, Austria;Institute for Microelectronics, TU Wien, Austria
Venue:
PARA'12 Proceedings of the 11th international conference on Applied Parallel and Scientific Computing
Year:
2012

Citing 5
Cited 0

Why functional programming matters

The Computer Journal - Special issue on Lazy functional programming
Static scheduling algorithms for allocating directed task graphs to multiprocessors

ACM Computing Surveys (CSUR)
Scheduling Parallel Task Graphs on (Almost) Homogeneous Multicluster Platforms

IEEE Transactions on Parallel and Distributed Systems
Introduction to Algorithms, Third Edition

Introduction to Algorithms, Third Edition
The task graph pattern

Proceedings of the 2010 Workshop on Parallel Programming Patterns

Quantified Score

Hi-index	0.00

Visualization

Abstract

The continually growing demand for increased simulation complexity introduces the need for scientific software frameworks to parallelize simulation tasks. We present our approach for a task graph scheduler based on modern programming techniques. The scheduler utilizes the Message Passing Interface to distribute the tasks among distributed computing nodes. We show that our approach does not only offer a concise user-level code but also provides a high degree of scalability.