Harnessing machine learning to improve the success rate of stimuli generation

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

doi:10.1109/HLDVT.2005.1568823

Harnessing machine learning to improve the success rate of stimuli generation

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

^*Corresponding author for this work

School of Computer Science

IBM

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

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 language	English
Title of host publication	Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05
Pages	112-118
Number of pages	7
DOIs	https://doi.org/10.1109/HLDVT.2005.1568823
State	Published - 2005
Event	Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05 - Napa Valley, CA, United States Duration: 30 Nov 2005 → 2 Dec 2005

Publication series

Name	Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT
Volume	2005
ISSN (Print)	1552-6674

Conference

Conference	Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05
Country/Territory	United States
City	Napa Valley, CA
Period	30/11/05 → 2/12/05

Access to Document

10.1109/HLDVT.2005.1568823

Cite this

Fine, S., Freund, A., Jaeger, I., Naveh, Y., Ziv, A., & Mansour, Y. (2005). Harnessing machine learning to improve the success rate of stimuli generation. In Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05 (pp. 112-118). Article 1568823 (Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT; Vol. 2005). https://doi.org/10.1109/HLDVT.2005.1568823

@inproceedings{750ebf1099a342609af5fd25b5d5df9f,

title = "Harnessing machine learning to improve the success rate of stimuli generation",

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.",

author = "Shai Fine and Ari Freund and Itai Jaeger and Yehuda Naveh and Avi Ziv and Yishay Mansour",

year = "2005",

doi = "10.1109/HLDVT.2005.1568823",

language = "אנגלית",

isbn = "0780395719",

series = "Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT",

pages = "112--118",

booktitle = "Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05",

note = "Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05 ; Conference date: 30-11-2005 Through 02-12-2005",

}

Fine, S, Freund, A, Jaeger, I, Naveh, Y, Ziv, A & Mansour, Y 2005, Harnessing machine learning to improve the success rate of stimuli generation. in Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05., 1568823, Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT, vol. 2005, pp. 112-118, Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05, Napa Valley, CA, United States, 30/11/05. https://doi.org/10.1109/HLDVT.2005.1568823

Harnessing machine learning to improve the success rate of stimuli generation. / Fine, Shai; Freund, Ari; Jaeger, Itai et al.
Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05. 2005. p. 112-118 1568823 (Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT; Vol. 2005).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Harnessing machine learning to improve the success rate of stimuli generation

AU - Fine, Shai

AU - Freund, Ari

AU - Jaeger, Itai

AU - Naveh, Yehuda

AU - Ziv, Avi

AU - Mansour, Yishay

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=33846635953&partnerID=8YFLogxK

U2 - 10.1109/HLDVT.2005.1568823

DO - 10.1109/HLDVT.2005.1568823

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:33846635953

SN - 0780395719

SN - 9780780395718

T3 - Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT

SP - 112

EP - 118

BT - Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05

T2 - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05

Y2 - 30 November 2005 through 2 December 2005

ER -

Fine S, Freund A, Jaeger I, Naveh Y, Ziv A, Mansour Y. Harnessing machine learning to improve the success rate of stimuli generation. In Proceedings - Tenth Annual IEEE International High Level Design Validation and Test Workshop, HLDVT'05. 2005. p. 112-118. 1568823. (Proceedings - IEEE International High-Level Design Validation and Test Workshop, HLDVT). doi: 10.1109/HLDVT.2005.1568823

Harnessing machine learning to improve the success rate of stimuli generation

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this