2020 32nd International Conference on Microelectronics (ICM) 2020
DOI: 10.1109/icm50269.2020.9331771
|View full text |Cite
|
Sign up to set email alerts
|

Highly-Reliable Approximate Quadruple Modular Redundancy with Approximation-Aware Voting

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
1
1

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 17 publications
0
3
0
Order By: Relevance
“…• Fault Tolerance: AC enhances the failure tolerance of IoT-enabled assistive devices. Tolerating errors and inaccuracies in computations allows the system to run reliably even during hardware collapses or environmental disturbances [29].…”
Section: Approximate Computingmentioning
confidence: 99%
“…• Fault Tolerance: AC enhances the failure tolerance of IoT-enabled assistive devices. Tolerating errors and inaccuracies in computations allows the system to run reliably even during hardware collapses or environmental disturbances [29].…”
Section: Approximate Computingmentioning
confidence: 99%
“…The crux of redundant technique lies in fault monitoring, the objective of which is to identify fault channels in the system and reconfigure the system, isolate faults, and prevent fault propagation [1] Currently, the primary monitoring method for redundant sensors is voting. The purpose of signal voting is to improve the availability or integrity of signals, or both [2] . The redundancy will increases hardware cost, architecture complexity, maintenance work, and weight [3] .…”
Section: Introductionmentioning
confidence: 99%
“…In addition to soft errors, reliable operation of today's computing systems must contend with faults that may still be occurring at hardware level. Redundant systems have been widely used to address both errors and faults; schemes based on majority voting and modular redundancy such as triplemodular-redundancy (TMR) [6 -10], and quadruple-modularredundancy (QMR) [11,12], have been widely used. However, these schemes incur in a large hardware overhead, so degrading design metrics such as area and power [13].…”
Section: Introductionmentioning
confidence: 99%