Two-level parallelization for finite-element based design optimization via case studies

Subramaniam Rajan, A. D. Belegundu, A. S. Damle, D. Lau

Research output: Contribution to journalArticle

Abstract

Computing clusters created with commodity chips are gaining popularity owing to relative ease of assembly and maintenance compared to a supercomputer. Such clusters are able to solve much larger problems owing to increased memory and reduced compute time. The challenge, however, is to develop new algorithms and software that can exploit multiple processors. In this paper we discuss the parallel processing options and their implementations in a gradient-based design optimization software system. The main objectives are as follows-(a) implement a design optimization methodology for sizing, shape and topology optimization using two-level parallelism and (b) provide a benchmark in the area of FEA-based design optimization for studying speedups with increasing number of processors to speed development of effective parallel algorithms. The two-level parallelism is implemented using nested parallel gradient calculations in conjunction with parallel FEA, and parallel line search with parallel FEA. Two case studies involving topology and shape optimization are studied in detail and they include three-dimensional finite element meshes with about 160∈000 hexahedral elements and about 175∈000 nodes. Furthermore, the case studies have been implemented using a workbench where the topology and shape optimization have an interface with a commercial CAD package, permitting a solid model representation of both the initial and the final optimized part.

Original languageEnglish (US)
Pages (from-to)69-93
Number of pages25
JournalOptimization and Engineering
Volume9
Issue number1
DOIs
StatePublished - Mar 2008

Fingerprint

Shape optimization
Parallelization
Topology Optimization
Shape Optimization
Finite Element
Parallelism
Gradient
Finite element method
Cluster Computing
Solid Model
Line Search
Supercomputer
Parallel Processing
Parallel Algorithms
Software System
Cluster computing
Maintenance
Chip
Supercomputers
Mesh

Keywords

  • Cluster computing
  • Design optimization
  • Finite element analysis
  • MPI
  • Parallel processing
  • Shape optimization
  • Topology optimization

ASJC Scopus subject areas

  • Control and Optimization
  • Electrical and Electronic Engineering
  • Software
  • Mechanical Engineering
  • Civil and Structural Engineering
  • Aerospace Engineering

Cite this

Two-level parallelization for finite-element based design optimization via case studies. / Rajan, Subramaniam; Belegundu, A. D.; Damle, A. S.; Lau, D.

In: Optimization and Engineering, Vol. 9, No. 1, 03.2008, p. 69-93.

Research output: Contribution to journalArticle

@article{10e854c7ccd84fb28188228c942279bf,
title = "Two-level parallelization for finite-element based design optimization via case studies",
abstract = "Computing clusters created with commodity chips are gaining popularity owing to relative ease of assembly and maintenance compared to a supercomputer. Such clusters are able to solve much larger problems owing to increased memory and reduced compute time. The challenge, however, is to develop new algorithms and software that can exploit multiple processors. In this paper we discuss the parallel processing options and their implementations in a gradient-based design optimization software system. The main objectives are as follows-(a) implement a design optimization methodology for sizing, shape and topology optimization using two-level parallelism and (b) provide a benchmark in the area of FEA-based design optimization for studying speedups with increasing number of processors to speed development of effective parallel algorithms. The two-level parallelism is implemented using nested parallel gradient calculations in conjunction with parallel FEA, and parallel line search with parallel FEA. Two case studies involving topology and shape optimization are studied in detail and they include three-dimensional finite element meshes with about 160∈000 hexahedral elements and about 175∈000 nodes. Furthermore, the case studies have been implemented using a workbench where the topology and shape optimization have an interface with a commercial CAD package, permitting a solid model representation of both the initial and the final optimized part.",
keywords = "Cluster computing, Design optimization, Finite element analysis, MPI, Parallel processing, Shape optimization, Topology optimization",
author = "Subramaniam Rajan and Belegundu, {A. D.} and Damle, {A. S.} and D. Lau",
year = "2008",
month = "3",
doi = "10.1007/s11081-007-9007-1",
language = "English (US)",
volume = "9",
pages = "69--93",
journal = "Optimization and Engineering",
issn = "1389-4420",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Two-level parallelization for finite-element based design optimization via case studies

AU - Rajan, Subramaniam

AU - Belegundu, A. D.

AU - Damle, A. S.

AU - Lau, D.

PY - 2008/3

Y1 - 2008/3

N2 - Computing clusters created with commodity chips are gaining popularity owing to relative ease of assembly and maintenance compared to a supercomputer. Such clusters are able to solve much larger problems owing to increased memory and reduced compute time. The challenge, however, is to develop new algorithms and software that can exploit multiple processors. In this paper we discuss the parallel processing options and their implementations in a gradient-based design optimization software system. The main objectives are as follows-(a) implement a design optimization methodology for sizing, shape and topology optimization using two-level parallelism and (b) provide a benchmark in the area of FEA-based design optimization for studying speedups with increasing number of processors to speed development of effective parallel algorithms. The two-level parallelism is implemented using nested parallel gradient calculations in conjunction with parallel FEA, and parallel line search with parallel FEA. Two case studies involving topology and shape optimization are studied in detail and they include three-dimensional finite element meshes with about 160∈000 hexahedral elements and about 175∈000 nodes. Furthermore, the case studies have been implemented using a workbench where the topology and shape optimization have an interface with a commercial CAD package, permitting a solid model representation of both the initial and the final optimized part.

AB - Computing clusters created with commodity chips are gaining popularity owing to relative ease of assembly and maintenance compared to a supercomputer. Such clusters are able to solve much larger problems owing to increased memory and reduced compute time. The challenge, however, is to develop new algorithms and software that can exploit multiple processors. In this paper we discuss the parallel processing options and their implementations in a gradient-based design optimization software system. The main objectives are as follows-(a) implement a design optimization methodology for sizing, shape and topology optimization using two-level parallelism and (b) provide a benchmark in the area of FEA-based design optimization for studying speedups with increasing number of processors to speed development of effective parallel algorithms. The two-level parallelism is implemented using nested parallel gradient calculations in conjunction with parallel FEA, and parallel line search with parallel FEA. Two case studies involving topology and shape optimization are studied in detail and they include three-dimensional finite element meshes with about 160∈000 hexahedral elements and about 175∈000 nodes. Furthermore, the case studies have been implemented using a workbench where the topology and shape optimization have an interface with a commercial CAD package, permitting a solid model representation of both the initial and the final optimized part.

KW - Cluster computing

KW - Design optimization

KW - Finite element analysis

KW - MPI

KW - Parallel processing

KW - Shape optimization

KW - Topology optimization

UR - http://www.scopus.com/inward/record.url?scp=72449158782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72449158782&partnerID=8YFLogxK

U2 - 10.1007/s11081-007-9007-1

DO - 10.1007/s11081-007-9007-1

M3 - Article

VL - 9

SP - 69

EP - 93

JO - Optimization and Engineering

JF - Optimization and Engineering

SN - 1389-4420

IS - 1

ER -