Can't see the forest for the trees

State restoration's limitations in post-silicon trace signal selection

Sai Ma, Debjit Pal, Rui Jiang, Sandip Ray, Shobha Vasudevan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

State Restoration Ratio (SRR) has been the de facto standard for evaluating quality of signals selected for post-silicon tracing and debug. Given a set S of selected signals, SRR measures the fraction of (gate-level) design states that can be inferred from observing signals in S at each cycle. Unfortunately, in spite of its widespread use, we found that SRR is intrinsically unsuitable as a metric for evaluating trace signal quality, as it captures neither the higher-level functionality of the design nor the constraints and requirements on trace signals imposed by architectural, physical, or security requirements. In this paper, we argue with strong empirical evidence that SRR must be replaced by a metric that closely models high-level behavioral coverage. We propose assertion coverage as a first step in this direction. We also present a new algorithm, based on Pagerank, for post-silicon trace selection. Pagerank is not designed to maximize SRR. We found that Pagerank has upto 70% higher behavioral coverage than SRR optimizing methods, and the RTL PageRank has upto 30% higher behavioral coverage than the netlist PageRank algorithm. Assertion coverage of PageRank RTL is upto 50% while SRR based methods have less than 5% assertion coverage.

Original languageEnglish (US)
Title of host publication2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-8
Number of pages8
ISBN (Electronic)9781467383882
DOIs
StatePublished - Jan 5 2016
Event34th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015 - Austin, United States
Duration: Nov 2 2015Nov 6 2015

Publication series

Name2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015

Other

Other34th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015
CountryUnited States
CityAustin
Period11/2/1511/6/15

Fingerprint

Restoration
Silicon

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

Ma, S., Pal, D., Jiang, R., Ray, S., & Vasudevan, S. (2016). Can't see the forest for the trees: State restoration's limitations in post-silicon trace signal selection. In 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015 (pp. 1-8). [7372542] (2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCAD.2015.7372542

Can't see the forest for the trees : State restoration's limitations in post-silicon trace signal selection. / Ma, Sai; Pal, Debjit; Jiang, Rui; Ray, Sandip; Vasudevan, Shobha.

2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1-8 7372542 (2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ma, S, Pal, D, Jiang, R, Ray, S & Vasudevan, S 2016, Can't see the forest for the trees: State restoration's limitations in post-silicon trace signal selection. in 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015., 7372542, 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015, Institute of Electrical and Electronics Engineers Inc., pp. 1-8, 34th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015, Austin, United States, 11/2/15. https://doi.org/10.1109/ICCAD.2015.7372542
Ma S, Pal D, Jiang R, Ray S, Vasudevan S. Can't see the forest for the trees: State restoration's limitations in post-silicon trace signal selection. In 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1-8. 7372542. (2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015). https://doi.org/10.1109/ICCAD.2015.7372542
Ma, Sai ; Pal, Debjit ; Jiang, Rui ; Ray, Sandip ; Vasudevan, Shobha. / Can't see the forest for the trees : State restoration's limitations in post-silicon trace signal selection. 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1-8 (2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015).
@inproceedings{b11bae3e721548bb9991c10c9117fca8,
title = "Can't see the forest for the trees: State restoration's limitations in post-silicon trace signal selection",
abstract = "State Restoration Ratio (SRR) has been the de facto standard for evaluating quality of signals selected for post-silicon tracing and debug. Given a set S of selected signals, SRR measures the fraction of (gate-level) design states that can be inferred from observing signals in S at each cycle. Unfortunately, in spite of its widespread use, we found that SRR is intrinsically unsuitable as a metric for evaluating trace signal quality, as it captures neither the higher-level functionality of the design nor the constraints and requirements on trace signals imposed by architectural, physical, or security requirements. In this paper, we argue with strong empirical evidence that SRR must be replaced by a metric that closely models high-level behavioral coverage. We propose assertion coverage as a first step in this direction. We also present a new algorithm, based on Pagerank, for post-silicon trace selection. Pagerank is not designed to maximize SRR. We found that Pagerank has upto 70{\%} higher behavioral coverage than SRR optimizing methods, and the RTL PageRank has upto 30{\%} higher behavioral coverage than the netlist PageRank algorithm. Assertion coverage of PageRank RTL is upto 50{\%} while SRR based methods have less than 5{\%} assertion coverage.",
author = "Sai Ma and Debjit Pal and Rui Jiang and Sandip Ray and Shobha Vasudevan",
year = "2016",
month = "1",
day = "5",
doi = "10.1109/ICCAD.2015.7372542",
language = "English (US)",
series = "2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--8",
booktitle = "2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015",
address = "United States",

}

TY - GEN

T1 - Can't see the forest for the trees

T2 - State restoration's limitations in post-silicon trace signal selection

AU - Ma, Sai

AU - Pal, Debjit

AU - Jiang, Rui

AU - Ray, Sandip

AU - Vasudevan, Shobha

PY - 2016/1/5

Y1 - 2016/1/5

N2 - State Restoration Ratio (SRR) has been the de facto standard for evaluating quality of signals selected for post-silicon tracing and debug. Given a set S of selected signals, SRR measures the fraction of (gate-level) design states that can be inferred from observing signals in S at each cycle. Unfortunately, in spite of its widespread use, we found that SRR is intrinsically unsuitable as a metric for evaluating trace signal quality, as it captures neither the higher-level functionality of the design nor the constraints and requirements on trace signals imposed by architectural, physical, or security requirements. In this paper, we argue with strong empirical evidence that SRR must be replaced by a metric that closely models high-level behavioral coverage. We propose assertion coverage as a first step in this direction. We also present a new algorithm, based on Pagerank, for post-silicon trace selection. Pagerank is not designed to maximize SRR. We found that Pagerank has upto 70% higher behavioral coverage than SRR optimizing methods, and the RTL PageRank has upto 30% higher behavioral coverage than the netlist PageRank algorithm. Assertion coverage of PageRank RTL is upto 50% while SRR based methods have less than 5% assertion coverage.

AB - State Restoration Ratio (SRR) has been the de facto standard for evaluating quality of signals selected for post-silicon tracing and debug. Given a set S of selected signals, SRR measures the fraction of (gate-level) design states that can be inferred from observing signals in S at each cycle. Unfortunately, in spite of its widespread use, we found that SRR is intrinsically unsuitable as a metric for evaluating trace signal quality, as it captures neither the higher-level functionality of the design nor the constraints and requirements on trace signals imposed by architectural, physical, or security requirements. In this paper, we argue with strong empirical evidence that SRR must be replaced by a metric that closely models high-level behavioral coverage. We propose assertion coverage as a first step in this direction. We also present a new algorithm, based on Pagerank, for post-silicon trace selection. Pagerank is not designed to maximize SRR. We found that Pagerank has upto 70% higher behavioral coverage than SRR optimizing methods, and the RTL PageRank has upto 30% higher behavioral coverage than the netlist PageRank algorithm. Assertion coverage of PageRank RTL is upto 50% while SRR based methods have less than 5% assertion coverage.

UR - http://www.scopus.com/inward/record.url?scp=84964426790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964426790&partnerID=8YFLogxK

U2 - 10.1109/ICCAD.2015.7372542

DO - 10.1109/ICCAD.2015.7372542

M3 - Conference contribution

T3 - 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015

SP - 1

EP - 8

BT - 2015 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -