Generating Routing-Driven Power Distribution Networks with Machine-Learning Technique
| Autor: | Yen-Chih Chiu, Szu-Pang Mu, Chien-Hsueh Lin, Mango C.-T. Chao, Li-De Chen, Cheng-Hong Tsai, Wen-Hsiang Chang |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Engineering
Speedup Equal-cost multi-path routing Computer science 020209 energy Distributed computing Design flow 02 engineering and technology 01 natural sciences 0103 physical sciences Electronic engineering 0202 electrical engineering electronic engineering information engineering Overhead (computing) Electrical and Electronic Engineering Power network design Block (data storage) 010302 applied physics Static routing business.industry Computer Graphics and Computer-Aided Design 020202 computer hardware & architecture Link-state routing protocol Multipath routing Node (circuits) Routing (electronic design automation) business Software |
| Zdroj: | ISPD |
| DOI: | 10.1145/2872334.2872353 |
| Popis: | As technology node keeps scaling and design complexity keeps increasing, power distribution networks (PDNs) require more routing resource to meet IR-drop and electro-migration (EM) constraints. This paper presents a design flow to generate a PDN that can result in near-minimal overhead for the routing of the underlying standard cells while satisfying both IR-drop and EM constraints based on a given cell placement. The design flow relies on a machine-learning model to quickly predict the total wire length of global route associated with a given PDN configuration in order to speed up the search process. The experimental results based on various 28 nm industrial block designs have demonstrated the accuracy of the learned model for predicting the routing cost and the effectiveness of the proposed framework for reducing the routing cost of the final PDN. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|