Winograd Convolution: A Perspective from Fault Tolerance [article]

Xinghua Xue, Haitong Huang, Cheng Liu, Ying Wang, Tao Luo, Lei Zhang
2022 arXiv   pre-print
Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation. Other than the computing efficiency, we observe its great potential in improving NN fault tolerance and evaluate its fault tolerance comprehensively for the first time. Then, we explore the use of fault tolerance of winograd convolution for either fault-tolerant or energy-efficient NN processing. According to our experiments,
more » ... nograd convolution can be utilized to reduce fault-tolerant design overhead by 27.49\% or energy consumption by 7.19\% without any accuracy loss compared to that without being aware of the fault tolerance
arXiv:2202.08675v1 fatcat:clnipyq3sbbstkez2kbkdrmtlq