The Google Coral Edge Tensor Processing Unit (Edge TPU) offers low-power, high-performance capabilities ideal for enabling deep learning in space. However, as a commercial product, no reliability considerations are made in its design. As a device targeted by current and future space computing platforms, it is vital to mission success to understand the vulnerabilities and possible failure modes prior to flight. In this research, we evaluate the soft-error vulnerabilities of the Edge TPU and propose fault-mitigation techniques to improve device reliability. Several Edge TPUs were irradiated using a wide spectrum neutron beam at the Los Alamos Neutron Science Center to evaluate the reliability of two machine-learning applications with common use cases within the space domain: image classification and semantic segmentation. Through experimentation, a vulnerability within the onboard memory is identified. Responsible for caching model parameters for increased performance, the onboard memory represents a critical device area. Any upsets within the cache risk compromising data integrity and model determinism. Across a variety of models tested, fault accumulation and persistence are consistently observed, resulting in the degradation of model accuracy and confidence. To alleviate the impact of radiation, we propose two fault-mitigation techniques: Naive Refreshing (NR) and Golden Batch Refreshing (GBR). NR periodically reloads model parameters to clear corrupted data. GBR is proposed as an alternative method to reduce reload frequency and improve performance. By leveraging knowledge of the cache vulnerabilities and applying one or more mitigation strategies, Edge TPUs can be properly considered for integration into existing and future flight hardware.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Soft-Error Characterization and Mitigation Strategies for Edge Tensor Processing Units in Space


    Beteiligte:
    Garrett, Tyler (Autor:in) / Roffe, Seth (Autor:in) / George, Alan (Autor:in)


    Erscheinungsdatum :

    01.08.2024


    Format / Umfang :

    5981692 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Soft-Error Effects on Graphics Processing Units

    Rech, Paolo / Oliveira, Daniel / Navaux, Philippe et al. | Springer Verlag | 2016


    Soft Error Mitigation in Soft-Core Processors

    Martínez-Álvarez, Antonio / Cuenca-Asensi, Sergio / Restrepo-Calle, Felipe | Springer Verlag | 2016


    Wildfire Mitigation Strategies Using Space Technol...

    Singhroy, Dr V. / Pulver, K.A.R. / Alkins, R. et al. | AIAA | 2005