Exploiting Unused Time Slots in List Scheduling Considering Communication Contention

Authors:
Oliver Sinnen;Leonel Sousa
Affiliations:
-;-
Venue:
Euro-Par '01 Proceedings of the 7th International Euro-Par Conference Manchester on Parallel Processing
Year:
2001

Citing 7
Cited 2

Parallel Algorithms and Architectures

Parallel Algorithms and Architectures
A Compile-Time Scheduling Heuristic for Interconnection-Constrained Heterogeneous Processor Architectures

IEEE Transactions on Parallel and Distributed Systems
Scheduling Task Graphs on Arbitrary Processor Architectures Considering Contention

HPCN Europe 2001 Proceedings of the 9th International Conference on High-Performance Computing and Networking
Bubble scheduling: A quasi dynamic algorithm for static allocation of tasks to parallel architectures

SPDP '95 Proceedings of the 7th IEEE Symposium on Parallel and Distributeed Processing
A Performance Evaluation of CP List Scheduling Heuristics for Communication Intensive Task Graphs

IPPS '98 Proceedings of the 12th. International Parallel Processing Symposium on International Parallel Processing Symposium
Benchmarking the Task Graph Scheduling Algorithms

IPPS '98 Proceedings of the 12th. International Parallel Processing Symposium on International Parallel Processing Symposium
Comparison of Contention Aware List Scheduling Heuristics for Cluster Computing

ICPPW '01 Proceedings of the 2001 International Conference on Parallel Processing Workshops

A Realistic Model and an Efficient Heuristic for Scheduling with Heterogeneous Processors

IPDPS '02 Proceedings of the 16th International Parallel and Distributed Processing Symposium
A dynamic communication contention awareness list scheduling algorithm for arbitrary heterogeneous system

ODBASE'06/OTM'06 Proceedings of the 2006 Confederated international conference on On the Move to Meaningful Internet Systems: CoopIS, DOA, GADA, and ODBASE - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Static scheduling is the temporal and spatial mapping of a program to the resources of a parallel system. Scheduling algorithms use the Directed Acyclic Graph (DAG) to represent the sub-tasks and the precedence-constraints of the program to be parallelised. This article proposes an extention to the classical list scheduling heuristic that allows to schedule DAGs to arbitrary processor architectures considering link contention. In this extension, communication links are treated as shared resources likewise the processors and we improve the extended algorithm by exploiting unused time slots on the resources. The algorithm is experimentally compared to the existing heuristics BSA and DLS.