Evaluation of Xilinx Deep Learning Processing Unit under Neutron Irradiation
D. Agiakatsikas, N. Foutris, A. Sari, V. Vlagkoulis, I. Souvatzoglou, M. Psarakis, M. Luján, M. Kastriotou, C. Cazzaniga
arXiv:2206.01981v18 citationsh-index: 24
Originality Synthesis-oriented
AI Analysis
This addresses dependability issues for hardware used in radiation-prone environments, such as aerospace or nuclear applications, and is incremental as it applies existing evaluation methods to a new hardware component.
The paper investigated the reliability of the Xilinx Deep-Learning Processing Unit (DPU) when exposed to neutron radiation, specifically analyzing how Single Event Effects (SEEs) affect the accuracy of the DPU while running the resnet50 model on a Xilinx Ultrascale+ MPSoC.
This paper studies the dependability of the Xilinx Deep-Learning Processing Unit (DPU) under neutron irradiation. It analyses the impact of Single Event Effects (SEEs) on the accuracy of the DPU running the resnet50 model on a Xilinx Ultrascale+ MPSoC.