Harnessing machine learning to improve the success rate of stimuli generation

Shai Fine, Ari Freund, Itai Jaeger, Yehuda Naveh, Avi Ziv, Yishay Mansour

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The initial state of a design under verification has a major impact on the ability of stimuli generators to successfully generate the requested stimuli. For complexity reasons, most stimuli generators use sequential solutions without planning ahead. Therefore, in many cases they fail to produce a consistent stimuli due to an inadequate selection of the initial state. We propose a new method, based on machine learning techniques, to improve generation success by learning the relationship between the initial state vector and generation success. We applied the proposed method in two different settings, with the objective of improving generation success and coverage in processor and system level generation. In both settings, the proposed method significantly reduced generation failures and enabled faster coverage.

Original languageEnglish
Title of host publicationProceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05
Pages112-118
Number of pages7
DOIs
StatePublished - 2005
EventTenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05 - Napa Valley, CA, United States
Duration: 30 Nov 20052 Dec 2005

Publication series

NameProceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT
Volume2005
ISSN (Print)1552-6674

Conference

ConferenceTenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05
Country/TerritoryUnited States
CityNapa Valley, CA
Period30/11/052/12/05

Fingerprint

Dive into the research topics of 'Harnessing machine learning to improve the success rate of stimuli generation'. Together they form a unique fingerprint.

Cite this