LIPFD-NPU: Low-overhead Instruction-driven Permanent Fault Detection for Neural Processing Unit
Authors:
- 28 October 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 22-23
Abstract
Neural Processing Unit (NPU) has become the state-of-the-art solution for accelerating artificial neural networks and is increasingly integrated on the System-on-Chip (SoC) of edge devices such as smartphones and cameras. However, adopting NPU in mission-critical systems, such as aerospace aircraft and autonomous driving demands high reliability, which is currently less explored on industrial NPUs. In this work, we target one of the critical reliability issues - permanent fault - for modern NPUs and provide an instruction-driven fault detection method named LIPFD-NPU. The approach executes dedicated network instructions in a self-testing fashion and generates fine-grained information on the potential fault's location, type and level of impact. An FPGA-based fault emulation framework is used to verify LIPFD-NPU. The results indicate that LIPFD-NPU effectively detects faults with tiny overheads of 0.2% in silicon area and 0.5% in power consumption.Keywords
This publication has 6 references indexed in Scilit:
- MOZART+: Masking Outputs With Zeros for Improved Architectural Robustness and Testing of DNN AcceleratorsIEEE Transactions on Device and Materials Reliability, 2022
- Online Testing of a Row-Stationary Convolution Accelerator2021
- A Self-Test Framework for Detecting Fault-induced Accuracy Drop in Neural Network Accelerators2021
- Accelerating hybrid and compact neural networks targeting perception and control domains with coarse-grained dataflow reconfigurationJournal of Semiconductors, 2020
- On the Resilience of RTL NN Accelerators: Fault Characterization and Mitigation2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017