Paper Info
Title
Parallel Implementation in a Industrial Framework of Statistical Tolerancing Analysis in Microelectronics
Abstract
The aim of this work is to report on a parallel implementation of methods for tolerance analysis in the framework of a microelectronics design center. The methods were designed to run parallelly on different platforms which could have different computational performances. In order to distribute the computations over a network of workstations, the algorithm was designed not by using a parallel compiler, but by using a RPC multi-server network. We have used essentially two methods. The first is the Monte Carlo approach, the second is based on an approximation by numerical integration or quadrature technique [1, 2, 3, 4], which requires far less function evaluations than the Monte Carlo method. These two approaches have been implemented in a parallel algorithm to be used on a cluster of multivendor workstations.
Year
DOI
Venue
1999
10.1007/3-540-48311-X_93
Euro-Par
Keywords
Field
DocType
parallel algorithm,statistical tolerancing analysis,parallel implementation,monte carlo method,monte carlo approach,different platform,industrial framework,rpc multi-server network,parallel compiler,function evaluation,different computational performance,multivendor workstations,monte carlo,numerical integration
Monte Carlo method,Microelectronics,Computer science,Parallel algorithm,Tolerance analysis,Numerical integration,Parallel computing,Workstation,Quadrature (mathematics),Computation
Conference
Volume
ISSN
ISBN
1685
0302-9743
3-540-66443-2
Citations 
PageRank 
References 
0
0.34
2
Authors
3
Name
Order
Citations
PageRank
Salvatore Rinaudo13811.36
Francesco Moschella200.34
Marcello A. Anile371.86