Efficient prediction of crosstalk in VLSI interconnections using neural networks

Author

Ilumoka, A.A.

Author_Institution

Pettit Microelectron. Res. Center, Georgia Inst. of Technol., Atlanta, GA, USA

fYear

2000

fDate

2000

Firstpage

87

Lastpage

90

Abstract

The unique approach proposed for VLSI crosstalk prediction involves the creation of parameterized models of primitive interconnect structures-wirecells-using modular artificial neural networks (MANNs). The finite element method, a circuit simulator and a neural network multi-paradigm prototyping system are coupled together to produce a library of re-usable MANN-based wirecell models

Keywords

VLSI; circuit simulation; crosstalk; finite element analysis; integrated circuit interconnections; integrated circuit metallisation; integrated circuit modelling; integrated circuit packaging; neural nets; MANNs; VLSI crosstalk prediction; VLSI interconnections; circuit simulator; crosstalk; crosstalk prediction; finite element method; modular artificial neural networks; neural network multi-paradigm prototyping system; neural networks; parameterized models; primitive interconnect structures; re-usable MANN-based wirecell model library; wirecells; Artificial neural networks; Circuit simulation; Coupling circuits; Crosstalk; Finite element methods; Integrated circuit interconnections; Libraries; Predictive models; Very large scale integration; Virtual prototyping;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Performance of Electronic Packaging, 2000, IEEE Conference on.

Conference_Location

Scottsdale, AZ

Print_ISBN

0-7803-6450-3

Type

conf

DOI

10.1109/EPEP.2000.895499

Filename

895499