Efficient Parallelization of Unstructured Reductions on Shared Memory Parallel Architectures

Authors:
Siegfried Benkner;Thomas Brandes
Affiliations:
-;-
Venue:
IPDPS '00 Proceedings of the 15 IPDPS 2000 Workshops on Parallel and Distributed Processing
Year:
2000

Citing 8
Cited 1

Run-time scheduling and execution of loops on message passing machines

Journal of Parallel and Distributed Computing - Special issue: algorithms for hypercube computers
Runtime compilation techniques for data partitioning and communication schedule reuse

Proceedings of the 1993 ACM/IEEE conference on Supercomputing
Parallel Programming with Polaris

Computer
Maximizing Multiprocessor Performance with the SUIF Compiler

Computer
Optimizing Irregular HPF Applications using Halos

Proceedings of the 11 IPPS/SPDP'99 Workshops Held in Conjunction with the 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing
A Tracing Protocol for Optimizing Data Parallel Irregular Computations

Euro-Par '98 Proceedings of the 4th International Euro-Par Conference on Parallel Processing
On Automatic Parallelization of Irregular Reductions on Scalable Shared Memory Systems

Euro-Par '99 Proceedings of the 5th International Euro-Par Conference on Parallel Processing
High Performance Fortran: Language Specification (PART II)

ACM SIGPLAN Fortran Forum - Special issue: high performance Fortran language specification, part 2

Exploiting Data Locality on Scalable Shared Memory Machines with Data Parallel Programs

Euro-Par '00 Proceedings from the 6th International Euro-Par Conference on Parallel Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new parallelization method for an efficient implementation of unstructured array reductions on shared memory parallel machines with OpenMP. This method is strongly related to parallelization techniques for irregular reductions on distributed memory machines as employed in the context of High Performance Fortran. By exploiting data locality, synchronization is minimized without introducing severe memory or computational overheads as observed with most existing shared memory parallelization techniques.