(Enter summary)
Abstract: This paper provides a novel insight into this tradeoff
by providing analytical equations that can serve as quantitative guidelines for optimizing
this tradeoff for parallel finite element applications. These equations include the following
machine and problem parameters: the number of elements in the global domain (N ), the
number of processors to be used for execution (P ), the ratio of message startup time to
network bandwidth for the target machine (ff=fi), and the number of bytes per shared ... (Update)
Context of citations to this paper: More
...focus should be on reducing the total message size or number of shared nodes. Analytical guidelines for making this choice can be found in [15]. As noted above, the performance of the local and wide area networks is considered in terms of latency and bandwidth. Another factor...
Cited by: More
A Decomposition Method for Efficient Use of.. - Taylor, Chen.. (1996)
(Correct)
Active bibliography (related documents): More All
0.8: Practical Issues of 2-D Parallel Finite Element Analysis - Hribar, Taylor (1994)
(Correct)
0.6: A Study of the Factorization Fill-In for a Parallel.. - Valerie Taylor (1994)
(Correct)
0.3: Parallel Methods for Solving Nonlinear Block Bordered.. - Zhang, Byrd, Schnabel
(Correct)
Similar documents based on text: More All
0.2: Balancing Load versus Decreasing Communication: Exploring the .. - Valerie Taylor (1996)
(Correct)
0.2: Balancing Load versus Decreasing Communication.. - Valerie Taylor (1996)
(Correct)
0.1: Termination Detection for Parallel Shortest Path Algorithms - Hribar, Taylor, Boyce
(Correct)
BibTeX entry: (Update)
E. Schwabe, V. E. Taylor, and M. Hribar. An in-depth analysis of the communication costs of parallel finite element applications. Technical Report CSE-95-005, Northwestern University, EECS Department, 1995. http://citeseer.ist.psu.edu/schwabe95depth.html More
@misc{ schwabe95depth,
author = "E. Schwabe and V. Taylor and M. Hribar",
title = "depth analysis of the communication costs of parallel finite element applications",
text = "E. Schwabe, V. E. Taylor, and M. Hribar. An in-depth analysis of the communication
costs of parallel finite element applications. Technical Report CSE-95-005,
Northwestern University, EECS Department, 1995.",
year = "1995",
url = "citeseer.ist.psu.edu/schwabe95depth.html" }
Citations (may not include all citations):
219
Partitioning of Unstructured Problems for Parallel Processin..
- Simon - 1991
108
Finite Element Procedure in Engineering Analysis (context) - Bathe - 1982
80
Machine Multicomputer: An Architectural Evaluation (context) - Noakes, Wallach et al. - 1993
63
Automatic Partitioning of Unstructured Meshes for the Parall.. (context) - Farhat, Lesoinne - 1993
43
Solving Finite Element Equations on Concurrent Computers (context) - Nour-Omid, Raefsky et al. - 1987
39
Solution of Partial Differential Equation on Vector and Para.. (context) - Ortega, Voigt - 1985
31
Architecture and Implementation of Vulcan (context) - Stunkel - 1994
21
A Retrofit Based Methodology for the Fast Generation and Opt.. (context) - Vanderstraeten, Farhat et al. - 1994
10
Sandia National Laboratory (context) - Hendrickson, Leland et al. - 1993
8
Communication Overhead on CM5: An Experimental Performance E.. (context) - Ponnusamy, Choudhary et al. - 1992
5
Complexity of Parallel Implementation of Domain Decompositio.. (context) - Gropp, Keyes - 1988
4
Computational Fluid Dynamics on Parallel Processors (context) - Gropp, Smith - 1990
4
McGraw-Hill Book Company (context) - Kardestuncer, Element - 1987
3
Parallelization of a Finite Element Application Program on a.. (context) - Aykanat, Ozguner et al. - 1987
3
Solving Structural Mechanics Problems on the Caltech Hypercu.. (context) - Nour-Omid, Park - 1987
2
A Study of Interprocessor Communication Schemes for Parallel (context) - Seitz - 1992
1
WHAMSD Project Progres Report (context) - Gao, Project et al. - 1991
1
High Performance Using a Hypercube Architecture for Parallel.. (context) - Malone - 1989
1
Argonne National Laborabory Technical Report MCS-P (context) - Gropp, Domain - 1991
Documents on the same site (http://www.ece.nwu.edu/~michelle/papers.html): More
Choosing a Shortest Path Algorithm - Hribar, Taylor (1995)
(Correct)
Performance Study of Parallel Shortest Path Algorithms.. - Hribar, Taylor (1997)
(Correct)
Modeling Processor Wait Time for 2-D Parallel Finite Element.. - Hribar, Taylor
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC