Minimizing area of VLSI power distribution networks using river formation dynamics

Date12 November 2018
Published date12 November 2018
Pages417-429
DOIhttps://doi.org/10.1108/JSIT-10-2017-0097
AuthorSatyabrata Dash,Sukanta Dey,Deepak Joshi,Gaurav Trivedi
Subject MatterInformation & knowledge management,Information systems,Information & communications technology
Minimizing area of VLSI power
distribution networks using river
formation dynamics
Satyabrata Dash,Sukanta Dey,Deepak Joshi and Gaurav Trivedi
Indian Institute of Technology Guwahati, Guwahati, India
Abstract
Purpose The purpose of this paper is to demonstratethe application of river formation dynamics to size
the widths of power distribution network for very large-scale integration designs so that the wire area
required by power rails is minimized.The area minimization problem is transformed into a single objective
optimizationproblem subject to various design constraints,such as IR drop and electromigrationconstraints.
Design/methodology/approach The minimization process is carried out using river formation
dynamics heuristic.The random probabilistic search strategy of riverformation dynamics heuristic is used to
advance through stringent design requirements to minimize the wire area of an over-designed power
distributionnetwork.
Findings A number of experiments are performed on several power distribution benchmarks to
demonstrate the effectiveness of river formation dynamics heuristic. It is observed that the riverformation
dynamics heuristic outperforms other standard optimization techniques in most cases, and a power
distribution network having 16 million nodes is successfully designed for optimal wire area using river
formationdynamics.
Originality/value Although many resear ch works are presente d in the literature to m inimize wire
area of power distribution network, these research works convey little idea on optimizing very large-scale
power distribution networks (i.e. networks having more than four million nodes) using an automated
environment. The originality in this research is the illustration of an automated environment equipped
with an efcient optimization technique based on random probabilistic movement of water drops in
solving very large-scale power distribution networks without sacricing accuracy and additional
computational cost. Based on the computation of river formation dynamics, the knowledge of minimum
area bounded by optimum IR drop value can be of signicant advantage in reduction of routable space
and in system performance improvement.
Keywords Power distribution network, River formation dynamics, Single objective optimization
Paper type Research paper
1. Introduction
With design sizes roughly doublingat each new technology node, designing a robust power
distribution network (PDN) is a challengingjob because of high current demand and power
consumption. At the same time, the decrease in supply voltage allows a smaller margin of
voltage drop across the power rails during power distribution. As PDN consumes a large
portion of routing resources [almost30 per cent or more (below 28 nm)], with increase in the
size of PDN and supply voltagevariations, the voltage drops across these power rails (due to
metal resistance) cannot bepushed aside (Allan et al., 2002). Therefore, the PDN needs to be
designed with a wider width than signal nets and minimizing the power network area can
reduce the routable space and save the space for systemperformance improvement.
In general, PDN analysis is performedas a perfunctory signoff procedure as it is usedat
a later stage within the design ow to enable designersto correct major PDN-related issues,
such as IR drop, L(di/dt) noise and electromigration issues (Dharchoudhury et al.,1998;
Minimizing
area of VLSI
power
417
Received16 October 2017
Revised6 February 2018
Accepted14 February 2018
Journalof Systems and
InformationTechnology
Vol.20 No. 4, 2018
pp. 417-429
© Emerald Publishing Limited
1328-7265
DOI 10.1108/JSIT-10-2017-0097
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/1328-7265.htm

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT