Performance Evaluation of Software-Based Error Detection Mechanisms for Supply Noise Induced Timing Errors

Yutaka MASUDA; Takao ONOYE; Masanori HASHIMOTO

doi:10.1587/transfun.E100.A.1452

Performance Evaluation of Software-Based Error Detection Mechanisms for Supply Noise Induced Timing Errors

Yutaka MASUDA, Takao ONOYE, Masanori HASHIMOTO

Full Text Views

0

Share
Cite this

Summary :

Software-based error detection techniques, which includes error detection mechanism (EDM) transformation, are used for error localization in post-silicon validation. This paper evaluates the performance of EDM for timing error localization with a noise-aware logic simulator and 65-nm test chips assuming the following two EDM usage scenarios; (1) localizing a timing error occurred in the original program, and (2) localizing as many potential timing errors as possible. Simulation results show that the EDM transformation customized for quick error detection cannot locate electrical timing errors in the original program in the first scenario, but it detects 86% of non-masked errors potential bugs in the second scenario, which mean the EDM performance of detecting electrical timing errors affecting execution results is high. Hardware measurement results show that the EDM detects 25% of original timing errors and 56% of non-masked errors. Here, these hardware measurement results are not consistent with the simulation results. To investigate the reason, we focus on the following two differences between hardware and simulation; (1) design of power distribution network, and (2) definition of timing error occurrence frequency. We update the simulation setup for filling the difference and re-execute the simulation. We confirm that the simulation and the chip measurement results are consistent.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.7 pp.1452-1463

Publication Date: 2017/07/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E100.A.1452

Type of Manuscript: Special Section PAPER (Special Section on Design Methodologies for System on a Chip)

Category

Authors

Yutaka MASUDA
  Osaka University
Takao ONOYE
  Osaka University
Masanori HASHIMOTO
  Osaka University

Keyword

electrical timing error, software-based error detection, EDM transformation, error detection

Cite this

Copy

Yutaka MASUDA, Takao ONOYE, Masanori HASHIMOTO, "Performance Evaluation of Software-Based Error Detection Mechanisms for Supply Noise Induced Timing Errors" in IEICE TRANSACTIONS on Fundamentals, vol. E100-A, no. 7, pp. 1452-1463, July 2017, doi: 10.1587/transfun.E100.A.1452.
Abstract: Software-based error detection techniques, which includes error detection mechanism (EDM) transformation, are used for error localization in post-silicon validation. This paper evaluates the performance of EDM for timing error localization with a noise-aware logic simulator and 65-nm test chips assuming the following two EDM usage scenarios; (1) localizing a timing error occurred in the original program, and (2) localizing as many potential timing errors as possible. Simulation results show that the EDM transformation customized for quick error detection cannot locate electrical timing errors in the original program in the first scenario, but it detects 86% of non-masked errors potential bugs in the second scenario, which mean the EDM performance of detecting electrical timing errors affecting execution results is high. Hardware measurement results show that the EDM detects 25% of original timing errors and 56% of non-masked errors. Here, these hardware measurement results are not consistent with the simulation results. To investigate the reason, we focus on the following two differences between hardware and simulation; (1) design of power distribution network, and (2) definition of timing error occurrence frequency. We update the simulation setup for filling the difference and re-execute the simulation. We confirm that the simulation and the chip measurement results are consistent.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.1452/_p

Copy

@ARTICLE{e100-a_7_1452,
author={Yutaka MASUDA, Takao ONOYE, Masanori HASHIMOTO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Performance Evaluation of Software-Based Error Detection Mechanisms for Supply Noise Induced Timing Errors},
year={2017},
volume={E100-A},
number={7},
pages={1452-1463},
abstract={Software-based error detection techniques, which includes error detection mechanism (EDM) transformation, are used for error localization in post-silicon validation. This paper evaluates the performance of EDM for timing error localization with a noise-aware logic simulator and 65-nm test chips assuming the following two EDM usage scenarios; (1) localizing a timing error occurred in the original program, and (2) localizing as many potential timing errors as possible. Simulation results show that the EDM transformation customized for quick error detection cannot locate electrical timing errors in the original program in the first scenario, but it detects 86% of non-masked errors potential bugs in the second scenario, which mean the EDM performance of detecting electrical timing errors affecting execution results is high. Hardware measurement results show that the EDM detects 25% of original timing errors and 56% of non-masked errors. Here, these hardware measurement results are not consistent with the simulation results. To investigate the reason, we focus on the following two differences between hardware and simulation; (1) design of power distribution network, and (2) definition of timing error occurrence frequency. We update the simulation setup for filling the difference and re-execute the simulation. We confirm that the simulation and the chip measurement results are consistent.},
keywords={},
doi={10.1587/transfun.E100.A.1452},
ISSN={1745-1337},
month={July},}

Copy

TY - JOUR
TI - Performance Evaluation of Software-Based Error Detection Mechanisms for Supply Noise Induced Timing Errors
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1452
EP - 1463
AU - Yutaka MASUDA
AU - Takao ONOYE
AU - Masanori HASHIMOTO
PY - 2017
DO - 10.1587/transfun.E100.A.1452
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2017
AB - Software-based error detection techniques, which includes error detection mechanism (EDM) transformation, are used for error localization in post-silicon validation. This paper evaluates the performance of EDM for timing error localization with a noise-aware logic simulator and 65-nm test chips assuming the following two EDM usage scenarios; (1) localizing a timing error occurred in the original program, and (2) localizing as many potential timing errors as possible. Simulation results show that the EDM transformation customized for quick error detection cannot locate electrical timing errors in the original program in the first scenario, but it detects 86% of non-masked errors potential bugs in the second scenario, which mean the EDM performance of detecting electrical timing errors affecting execution results is high. Hardware measurement results show that the EDM detects 25% of original timing errors and 56% of non-masked errors. Here, these hardware measurement results are not consistent with the simulation results. To investigate the reason, we focus on the following two differences between hardware and simulation; (1) design of power distribution network, and (2) definition of timing error occurrence frequency. We update the simulation setup for filling the difference and re-execute the simulation. We confirm that the simulation and the chip measurement results are consistent.
ER -