CoChat

Analyzing and Increasing the Reliability of Convolutional Neural Networks on GPUs

The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index.

Abstract

Graphics processing units (GPUs) are playing a critical role in convolutional neural networks (CNNs) for image detection. As GPU-enabled CNNs move into safety-critical environments, reliability is becoming a growing concern. In this paper, we evaluate and propose strategies to improve the reliability of object detection algorithms, as run on three NVIDIA GPU architectures. We consider three algorithms: 1) you only look once; 2) a faster region-based CNN (Faster R-CNN); and 3) a residual network, exposing live hardware to neutron beams. We complement our beam experiments with fault injection to better characterize fault propagation in CNNs. We show that a single fault occurring in a GPU tends to propagate to multiple active threads, significantly reducing the reliability of a CNN. Moreover, relying on error correcting codes dramatically reduces the number of silent data corruptions (SDCs), but does not reduce the number of critical errors (i.e., errors that could potentially impact safety-critical applications). Based on observations on how faults propagate on GPU architectures, we propose effective strategies to improve CNN reliability. We also consider the benefits of using an algorithm-based fault-tolerance technique for matrix multiplication, which can correct more than 87% of the critical SDCs in a CNN, while redesigning maxpool layers of the CNN to detect up to 98% of critical SDCs.

Overview

Integrity signals

Registry

Crossref · 10.1109/tr.2018.2878387

Cites

68 of 68 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 68 references

Research works printed but not linked: 4

  1. sridharan, 2009, The effect of input data on program vulnerability, Workshop on Silicon Errors in Logic-System Effects, 1
  2. 10.1109/TNS.2014.2301768 · DOI
  3. 2018, Log database for IEEE transaction on reliability, Github
  4. collobert, 0, BigLearn NIPS Workshop

Cited by

Items 101–200 of 223

Metadata

Authors
Santos, F. F. D., Pimenta, P. F., Lunardi, C., Draghetti, L., Carro, L., Kaeli, D., & Rech, P.
Affiliations
  • Universidade Federal do Rio Grande do Sul (BR)
  • Northeastern University (US)
Venue
IEEE Transactions on Reliability
Published
2019-06
Volume
68
Issue
2
Pages
663-677
ISSN
  • 0018-9529 (ISSN-L)
  • 1558-1721
OpenAlex
W2901848761
Cited by
226
References
67
Citations by year
2026: 18 · 2025: 18 · 2024: 41 · 2023: 33 · 2022: 42 · 2021: 34 · 2020: 27 · 2019: 13
FWCI
7.08
Type
journal article
Language
en
Open access
closed
Locations
  • IEEE Transactions on Reliability (publishedVersion)
  • Institutional Research Information System (Università degli Studi di Trento) (submittedVersion)
  • Science and Technology Facilities Council (submittedVersion)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Radiation Effects in Electronics
  • Physical Sciences › Computer Science › Computer Networks and Communications › Distributed systems and fault tolerance
  • Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
Keywords
convolutional neural networks, GPU reliability, fault injection, silent data corruption, error-correcting codes, algorithm-based fault tolerance, matrix multiplication, object detection, safety-critical systems, fault propagation, NVIDIA GPUs

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.