A variable group block distribution strategy for dense factorizations on networks of heterogeneous computers

Authors:
Alexey Lastovetsky;Ravi Reddy
Affiliations:
Department of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland;Department of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland
Venue:
PPAM'05 Proceedings of the 6th international conference on Parallel Processing and Applied Mathematics
Year:
2005

Citing 8
Cited 0

ScaLAPACK user's guide

ScaLAPACK user's guide
A Proposal for a Heterogeneous Cluster ScaLAPACK (Dense Linear Solvers)

IEEE Transactions on Computers
Heterogeneous Distribution of Computations While Solving Linear Algebra Problems on Networks of Heterogeneous Computers

HPCN Europe '99 Proceedings of the 7th International Conference on High-Performance Computing and Networking
Experiments with mpC: Efficient Solving Regular Problems on Heterogeneous Networks of Computers via Irregulation

IRREGULAR '98 Proceedings of the 5th International Symposium on Solving Irregularly Structured Problems in Parallel
Linear Algebra Algorithms in Heterogeneous Cluster of Personal Computers

HCW '00 Proceedings of the 9th Heterogeneous Computing Workshop
Simulation of Data Distribution Strategies for LU Factorization on Heterogeneous Machines

IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Data Partitioning with a Realistic Performance Model of Networks of Heterogeneous Computers with Task Size Limits

ISPDC '04 Proceedings of the Third International Symposium on Parallel and Distributed Computing/Third International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks
Design and Implementation of the ScaLAPACK LU, QR, and Cholesky Factorization Routines

Scientific Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a static data distribution strategy called Variable Group Block distribution to optimize the execution of factorization of a dense matrix on a network of heterogeneous computers. The distribution is based on a functional performance model of computers, which tries to capture different aspects of heterogeneity of the computers including the (multi-level) memory structure and paging effects.