skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Using the GA and TAO Toolkits for Solving Large-Scale Optimization Problems on Parallel Computers

Abstract

Challenges in the scalable solution of large-scale optimization problems include the development of innovative algorithms as well as efficient tools for parallel data manipulation. This paper discusses the combined use of two complementary toolkits from the collection of Advanced CompuTational Software (ACTS), namely Global Arrays (GA) for parallel data management and the Toolkit for Advanced Optimization (TAO). TAO uses abstractions for vectors and matrices, so that optimization algorithms can easily interface to the external linear algebra support provided by the GA library. The GA/TAO interfaces are available both in the traditional library mode and as components compliant with the Common Component Architecture (CCA). We highlight the design of each toolkit, describe the interfaces between them, and evaluate performance for model problems involving bound-constrained optimization.

Authors:
; ; ; ;
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
915684
Report Number(s):
PNNL-SA-39636
KJ0101030; TRN: US200816%%25
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Journal Article
Journal Name:
ACM Transactions on Mathematical Software, 33(2):Article 11
Additional Journal Information:
Journal Volume: 33; Journal Issue: 2
Country of Publication:
United States
Language:
English
Subject:
97; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; ALGORITHMS; COMPUTER CALCULATIONS; MEMORY MANAGEMENT; PERFORMANCE; PARALLEL PROCESSING; G CODES; T CODES

Citation Formats

Benson, S, Krishnan, Manoj Kumar, McInnes, L, Nieplocha, Jarek, and Sarich, J. Using the GA and TAO Toolkits for Solving Large-Scale Optimization Problems on Parallel Computers. United States: N. p., 2007. Web. doi:10.1145/1236463.1236466.
Benson, S, Krishnan, Manoj Kumar, McInnes, L, Nieplocha, Jarek, & Sarich, J. Using the GA and TAO Toolkits for Solving Large-Scale Optimization Problems on Parallel Computers. United States. https://doi.org/10.1145/1236463.1236466
Benson, S, Krishnan, Manoj Kumar, McInnes, L, Nieplocha, Jarek, and Sarich, J. 2007. "Using the GA and TAO Toolkits for Solving Large-Scale Optimization Problems on Parallel Computers". United States. https://doi.org/10.1145/1236463.1236466.
@article{osti_915684,
title = {Using the GA and TAO Toolkits for Solving Large-Scale Optimization Problems on Parallel Computers},
author = {Benson, S and Krishnan, Manoj Kumar and McInnes, L and Nieplocha, Jarek and Sarich, J},
abstractNote = {Challenges in the scalable solution of large-scale optimization problems include the development of innovative algorithms as well as efficient tools for parallel data manipulation. This paper discusses the combined use of two complementary toolkits from the collection of Advanced CompuTational Software (ACTS), namely Global Arrays (GA) for parallel data management and the Toolkit for Advanced Optimization (TAO). TAO uses abstractions for vectors and matrices, so that optimization algorithms can easily interface to the external linear algebra support provided by the GA library. The GA/TAO interfaces are available both in the traditional library mode and as components compliant with the Common Component Architecture (CCA). We highlight the design of each toolkit, describe the interfaces between them, and evaluate performance for model problems involving bound-constrained optimization.},
doi = {10.1145/1236463.1236466},
url = {https://www.osti.gov/biblio/915684}, journal = {ACM Transactions on Mathematical Software, 33(2):Article 11},
number = 2,
volume = 33,
place = {United States},
year = {Fri Jun 01 00:00:00 EDT 2007},
month = {Fri Jun 01 00:00:00 EDT 2007}
}