Publications

Results 51–57 of 57
Skip to search filters

Finding strongly connected components in distributed graphs

Journal of Parallel and Distributed Computing

McLendon, William; Hendrickson, Bruce A.; Plimpton, Steven J.; Rauchwerger, Lawrence

The traditional, serial, algorithm for finding the strongly connected components in a graph is based on depth first search and has complexity which is linear in the size of the graph. Depth first search is difficult to parallelize, which creates a need for a different parallel algorithm for this problem. We describe the implementation of a recently proposed parallel algorithm that finds strongly connected components in distributed graphs, and discuss how it is used in a radiation transport solver. © 2005 Elsevier Inc. All rights reserved.

More Details

Solving elliptic finite element systems in near-linear time with support preconditioners

Proposed for publication in SIAM Journal of Matrix Analysis.

Boman, Erik G.; Hendrickson, Bruce A.

We consider linear systems arising from the use of the finite element method for solving scalar linear elliptic problems. Our main result is that these linear systems, which are symmetric and positive semidefinite, are well approximated by symmetric diagonally dominant matrices. Our framework for defining matrix approximation is support theory. Significant graph theoretic work has already been developed in the support framework for preconditioners in the diagonally dominant case, and in particular it is known that such systems can be solved with iterative methods in nearly linear time. Thus, our approximation result implies that these graph theoretic techniques can also solve a class of finite element problems in nearly linear time. We show that the support number bounds, which control the number of iterations in the preconditioned iterative solver, depend on mesh quality measures but not on the problem size or shape of the domain.

More Details

LDRD report : parallel repartitioning for optimal solver performance

Devine, Karen D.; Boman, Erik G.; Devine, Karen D.; Heaphy, Robert T.; Hendrickson, Bruce A.; Heroux, Michael A.

We have developed infrastructure, utilities and partitioning methods to improve data partitioning in linear solvers and preconditioners. Our efforts included incorporation of data repartitioning capabilities from the Zoltan toolkit into the Trilinos solver framework, (allowing dynamic repartitioning of Trilinos matrices); implementation of efficient distributed data directories and unstructured communication utilities in Zoltan and Trilinos; development of a new multi-constraint geometric partitioning algorithm (which can generate one decomposition that is good with respect to multiple criteria); and research into hypergraph partitioning algorithms (which provide up to 56% reduction of communication volume compared to graph partitioning for a number of emerging applications). This report includes descriptions of the infrastructure and algorithms developed, along with results demonstrating the effectiveness of our approaches.

More Details

Load balancing fictions, falsehoods and fallacies

Applied Mathematical Modeling

Hendrickson, Bruce A.

Effective use of a parallel computer requires that a calculation be carefully divided among the processors. This load balancing problem appears in many guises and has been a fervent area of research for the past decade or more. Although great progress has been made, and useful software tools developed, a number of challenges remain. It is the conviction of the author that these challenges will be easier to address if programmers first come to terms with some significant shortcomings in their current perspectives. This paper tries to identify several areas in which the prevailing point of view is either mistaken or insufficient. The goal is to motivate new ideas and directions for this important field.

More Details

Interprocessor communication with memory constraints

Hendrickson, Bruce A.; Hendrickson, Bruce A.

Many parallel applications require periodic redistribution of workloads and associated data. In a distributed memory computer, this redistribution can be difficult if limited memory is available for receiving messages. The authors propose a model for optimizing the exchange of messages under such circumstances which they call the minimum phase remapping problem. They first show that the problem is NP-Complete, and then analyze several methodologies for addressing it. First, they show how the problem can be phrased as an instance of multi-commodity flow. Next, they study a continuous approximation to the problem. They show that this continuous approximation has a solution which requires at most two more phases than the optimal discrete solution, but the question of how to consistently obtain a good discrete solution from the continuous problem remains open. Finally, they devise a simple and practical approximation algorithm for the problem with a bound of 1.5 times the optimal number of phases.

More Details

Design of dynamic load-balancing tools for parallel applications

Devine, Karen D.; Hendrickson, Bruce A.; Boman, Erik G.; Vaughan, Courtenay T.

The design of general-purpose dynamic load-balancing tools for parallel applications is more challenging than the design of static partitioning tools. Both algorithmic and software engineering issues arise. The authors have addressed many of these issues in the design of the Zoltan dynamic load-balancing library. Zoltan has an object-oriented interface that makes it easy to use and provides separation between the application and the load-balancing algorithms. It contains a suite of dynamic load-balancing algorithms, including both geometric and graph-based algorithms. Its design makes it valuable both as a partitioning tool for a variety of applications and as a research test-bed for new algorithmic development. In this paper, the authors describe Zoltan's design and demonstrate its use in an unstructured-mesh finite element application.

More Details
Results 51–57 of 57
Results 51–57 of 57