Genetic optimization applied to via and route strategy

To meet increased demand and higher PCB design expectations, research engineers have been tasked to develop models to automate PCB placement and routing procedures using machine learning and artificial intelligence techniques. Since placement and routing are still tedious manual processes which limit the design search space, these techniques allow engineers to quickly investigate better solutions. The Move37 team within Cadence Design Systems found via placement to be a crucial problem to be solved and integrated into their OrbitIO platform. We evaluated multiple non-gradient-based optimization strategies and compiled data of their performance. From these tests, a genetic algorithm-based strategy was sought due to its fast convergence and the ability to substitute cost functions. In this study, we converted the via placement problem to a simpler layer assignment problem by enforcing the location of vias and pins to be the same. We then determined an optimal layer assignment given a set of flylines, i.e. logical connections, using a genetic optimization library called DEAP. We coined this genetic optimization approach to via strategy GO VIA.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2020

Author dc:creator

• Zumbo, Zachary J.

Advisor dc:contributor.advisor

• Jacob White and Taylor Hogan.

• Electrical Engineering and Computer Science.

Statement dc:rights

• MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/129860

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/129860