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.

Analyzing and increasing the reliability of convolutional neural networks on GPUs / Santos, F. F. D.; Pimenta, P. F.; Lunardi, C.; Draghetti, L.; Carro, L.; Kaeli, D.; Rech, P.. - In: IEEE TRANSACTIONS ON RELIABILITY. - ISSN 0018-9529. - 68:2(2019), pp. 663-677. [10.1109/TR.2018.2878387]

Analyzing and increasing the reliability of convolutional neural networks on GPUs

Rech P.
2019-01-01

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.
2
Santos, F. F. D.; Pimenta, P. F.; Lunardi, C.; Draghetti, L.; Carro, L.; Kaeli, D.; Rech, P.
Analyzing and increasing the reliability of convolutional neural networks on GPUs / Santos, F. F. D.; Pimenta, P. F.; Lunardi, C.; Draghetti, L.; Carro, L.; Kaeli, D.; Rech, P.. - In: IEEE TRANSACTIONS ON RELIABILITY. - ISSN 0018-9529. - 68:2(2019), pp. 663-677. [10.1109/TR.2018.2878387]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/346709
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 93
  • ???jsp.display-item.citation.isi??? ND
social impact