High Energy and Thermal Neutron Sensitivity of Google Tensor Processing Units

Rech, Rubens Luiz; Malde, Sujit; Cazzaniga, Carlo; Kastriotou, Maria; Létiche, Manon; Frost, Christopher; Rech, Paolo

doi:10.1109/tns.2022.3142092

Cited by 18 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, we tested only object detection neural networks, while we explored the reliability of reinforcement learning models. In [24], the authors report the Edge TPU reliability under high energy and thermal neutron radiation. The authors tested several different types of classification and object detection neural networks, while in this work we use the same device and the same radiation type but report the reinforcement learning reliability of 4 different models.…”

Section: Coral Edge Tpumentioning

confidence: 99%

Neutrons Sensitivity of Deep Reinforcement Learning Policies on EdgeAI Accelerators

Bodmann,

Saveriano,

Kritikakou

et al. 2024

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

Autonomous robots and their application are becoming popular in several different fields, including tasks where robots closely interact with humans. Therefore, the reliability of computation must be paramount. In this work, we measure the reliability of Google's Coral Edge TPU executing three Deep Reinforcement Learning (DRL) models through an accelerated neutrons beam. We experimentally collect data that, when scaled to the natural neutron flux, accounts for more than 5 million years. Based on our extensive evaluation, we quantify and qualify the radiation-induced corruption on the correctness of DRL. Crucially, our data shows that the Edge TPU executing DRL has an error rate that is up to 18 times higher the limit imposed by international reliability standards. We found that, despite the feedback and intrinsic redundancy of DRL, the propagation of the fault induces the model to fail in the vast majority of cases or the model manages to finish but reports wrong metrics (i.e. speed, final position, reward). We provide insights on how radiation corrupts the model, on how the fault propagates in the computation, and about the failure characteristic of the controlled robot.

show abstract

Section: Coral Edge Tpumentioning

confidence: 99%

Neutrons Sensitivity of Deep Reinforcement Learning Policies on EdgeAI Accelerators

Bodmann,

Saveriano,

Kritikakou

et al. 2024

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

show abstract

“…Software-level [57], [58], [61]- [63], [66]- [91] RTL-level [92], [93] Microarchitectural-level [94] Gate-level [95]- [98] Transistor-level [99], [100] Chip-level [101]- [110] Radiation experiments [81]- [85], [111]- [114] Memristor crossbar-based architectures [115]- [118] oretical study is presented for Feed-Forward Neural Networks (FFNNs) deducing the number of failing neurons and synapses an FFNN can tolerate.…”

Section: Fault Injection Experiments and Frameworkmentioning

confidence: 99%

“…Finally, results on the reliability to neutrons of Google Coral TPU are reported in [114], considering elementary operations and several CNN models. It turns out that, despite the high error rate, most neutron induced errors only slightly modify the convolution output and do not change the detection or classification of CNNs.…”

Section: Fault Injection Experiments and Frameworkmentioning

confidence: 99%

Testability and Dependability of AI Hardware: Survey, Trends, Challenges, and Perspectives

Liu

Stratigopoulos³

2023

IEEE Des. Test

View full text Add to dashboard Cite

In recent years, there has been an expedited trend in embracing bold and radical innovation of computer architectures, aiming at the continuation of computing performance improvement despite the slowed-down physical device scaling. One new frontier in this field focuses on Artificial Intelligence (AI) hardware. While functionality of AI hardware still remains the main focus, testability and dependability of these new architectures need to be addressed before the mainstream adoption. This survey paper covers the state-of-the-art in research and development of dependability and testability solutions for AI hardware including digital or analog implementations of Artificial Neural Networks (ANNs) and Spiking Neural Networks (SNNs), used in accelerators and neuromorphic designs. Trends, challenges and perspectives are also discussed in this paper.

show abstract

“…Except for our pioneering works ([14] [19]), this is the only work employing resource-constrained devices in the experiments. The remaining works consider FPGA implementations of ML algorithms [5][12][6] [15][17] [7] or their execution on generic graphics processing units (GPUs) [11], and ML specialised accelerators [13][16] [18]. All works, with exception of [5], adopted neutron irradiation for their experiments.…”

Section: Related Work In Machine Learning Soft Error Assessment and M...mentioning

confidence: 99%

A Lightweight Mitigation Technique for Resource- Constrained Devices Executing DNN Inference Models Under Neutron Radiation

Gava

Hanneman

Abich

et al. 2023

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

Deep neural network (DNN) models are being deployed in safety-critical embedded devices for object identification, recognition, and even trajectory prediction. Optimised versions of such models, in particular the convolutional ones, are becoming increasingly common in resource-constrained edge-computing devices (e.g., sensors, drones), which typically rely on reduced memory footprint, low power budget and low-performance microprocessors. DNN models are prone to radiation-induced soft errors, and tackling their occurrence in resource-constrained devices is a mandatory and substantial challenge. While traditional replication-based soft error mitigation techniques will likely account for a reasonable performance penalty, hardware solutions are even more costly. To undertake this almost contradictory challenge, this work evaluates the efficiency of a lightweight software-based mitigation technique, called Register Allocation Technique (RAT), when applied to a convolutional neural network (CNN) model running on two commercial Arm microprocessors (i.e., Cortex-M4 and M7) under the effects of neutron radiation. Gathered results obtained from two neutron radiation campaigns suggest that RAT can reduce the number of critical faults in the CNN model running on both Arm Cortex-M microprocessors. Results also suggest that the SDC FIT rate of the RAT-hardened CNN model can be reduced in up to 83% with a runtime overhead of 32%.

show abstract

High Energy and Thermal Neutron Sensitivity of Google Tensor Processing Units

Cited by 18 publications

References 28 publications

Neutrons Sensitivity of Deep Reinforcement Learning Policies on EdgeAI Accelerators

Neutrons Sensitivity of Deep Reinforcement Learning Policies on EdgeAI Accelerators

Testability and Dependability of AI Hardware: Survey, Trends, Challenges, and Perspectives

A Lightweight Mitigation Technique for Resource- Constrained Devices Executing DNN Inference Models Under Neutron Radiation

Contact Info

Product

Resources

About