SHIELDeNN: Online Accelerated Framework for Fault-Tolerant Deep Neural Network Architectures

We propose SHIELDeNN, an end-to-end inference accelerator frame-work that synergizes the mitigation approach and computational resources to realize a low-overhead error-resilient Neural Network (NN) overlay. We develop a rigorous fault assessment paradigm to delineate a ground-truth fault-skeleton map for revealing the most vulnerable parameters in NN. The error-susceptible parameters and resource constraints are given to a function to find superior design. The error-resiliency magnitude offered by SHIELDeNN can be adjusted based on the given boundaries. SHIELDeNN methodology improves the error-resiliency magnitude of cnvW1A1 by 17.19% and 96.15% for 100 MBUs that target weight and activation layers, respectively.

[1]  Yu Cao,et al.  ALAMO: FPGA acceleration of deep learning algorithms with a modularized RTL compiler , 2018, Integr..

[2]  Luca Benini,et al.  Neurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes , 2017, IEEE Transactions on Parallel and Distributed Systems.

[3]  Luca Benini,et al.  YodaNN: An Architecture for Ultralow Power Binary-Weight CNN Acceleration , 2016, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[4]  Bo-Cheng Lai,et al.  Supporting compressed-sparse activations and weights on SIMD-like accelerator for sparse convolutional neural networks , 2018, 2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC).

[5]  Ray C. C. Cheung,et al.  Accurate and Compact Convolutional Neural Networks with Trained Binarization , 2019, BMVC.

[6]  William J. Dally,et al.  SCNN: An accelerator for compressed-sparse convolutional neural networks , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[7]  Philip Heng Wai Leong,et al.  FINN: A Framework for Fast, Scalable Binarized Neural Network Inference , 2016, FPGA.

[8]  Kunle Olukotun,et al.  Understanding and optimizing asynchronous low-precision stochastic gradient descent , 2017, 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA).

[9]  Pritish Narayanan,et al.  Deep Learning with Limited Numerical Precision , 2015, ICML.

[10]  Song Han,et al.  Trained Ternary Quantization , 2016, ICLR.

[11]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[12]  R. Allmon,et al.  Soft Error Susceptibilities of 22 nm Tri-Gate Devices , 2012, IEEE Transactions on Nuclear Science.

[13]  Ming-Wei Chang,et al.  Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base , 2015, ACL.

[14]  Jia Wang,et al.  DaDianNao: A Machine-Learning Supercomputer , 2014, 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture.

[15]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, NIPS.

[16]  Shawki Areibi,et al.  Deep Learning on FPGAs: Past, Present, and Future , 2016, ArXiv.

[17]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[18]  Horst Schirmeier,et al.  Efficient fault-injection-based assessment of software-implemented hardware fault tolerance , 2016 .

[19]  Xiang Gu,et al.  Tolerating Soft Errors in Deep Learning Accelerators with Reliable On-Chip Memory Designs , 2018, 2018 IEEE International Conference on Networking, Architecture and Storage (NAS).

[20]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[21]  Shuang Wu,et al.  Training and Inference with Integers in Deep Neural Networks , 2018, ICLR.