Award Date

1-1-2002

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical and Computer Engineering

First Committee Member

Henry Selvaraj

Number of Pages

79

Abstract

Our approach to the problem of partitioning the design (represented as a hypergraph) into Multi-FPGAs uses a bi-level approach by initially clustering the design and then applying the bipartitioning technique iteratively. Each partition generated by the iterative bipartitioning technique should meet the constraints given by the FPGAs input-output and number of CLBs. The traditional FM partitioning can be applied to partition the circuit into multiple FPGAs. FM partitioning aims to minimize the number of interconnections but fails to group the nodes with maximum interconnections into one partition. Thus FM algorithm looks at the partitioning problem with a global viewpoint, abandoning the details. The proposed algorithm adds another level of optimization to the partitioning heuristic. By clustering the nodes that are connected very closely in a netlist before partitioning, local optimization property is added to the FM algorithm. This clustered circuit is then partitioned to implement the design in multiple FPGAs. Bipartitioning using the Fiduccia Mattheyses algorithm is applied. (Abstract shortened by UMI.).

Keywords

Circuit; Fpgas; Multiple; Partitioning; Targeting

Controlled Subject

Electrical engineering

File Format

pdf

File Size

1648.64 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Download


COinS