Functional Criticality Classification of Structural Faults in AI Accelerators
作者： Krishnendu Chakrabarty , Fei Su , Arjun Chaudhuri , Jonti Talukdar
DOI: 10.1109/ITC44778.2020.9325272
关键词:
摘要: The ubiquitous application of deep neural networks (DNNs) has led to a rise in demand for artificial intelligence (AI) accelerators. This paper studies the problem classifying structural faults such an accelerator based on their functional criticality. We analyze impact stuck-at processing elements (PEs) $128 \times 128$ systolic array designed perform classification MNIST dataset using both 32-bit and 16-bit data paths. present two-tier machine-learning (ML) method assess criticality these faults. address minimizing misclassification by utilizing generative adversarial (GANs). ML/GAN-based assessment leads less than 1% test escapes during evaluation.
sci-hub.st 参考文章(12)
, Generative Adversarial Nets neural information processing systems. ,vol. 27, pp. 2672- 2680 ,(2014) , 10.3156/JSOFT.29.5_177_2
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Hinrich Schütze, Emre Velipasaoglu, Jan O. Pedersen, Performance thresholding in practical text classification Proceedings of the 15th ACM international conference on Information and knowledge management - CIKM '06. pp. 662- 671 ,(2006) , 10.1145/1183614.1183709
Yu-Hsin Chen, Tushar Krishna, Joel S. Emer, Vivienne Sze, Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks IEEE Journal of Solid-State Circuits. ,vol. 52, pp. 127- 138 ,(2017) , 10.1109/JSSC.2016.2616357
Rolf Ernst, Marco Di Natale, Mixed Criticality Systems—A History of Misconceptions? IEEE Design & Test of Computers. ,vol. 33, pp. 65- 74 ,(2016) , 10.1109/MDAT.2016.2594790
Norman P. Jouppi, Cliff Young, Nishant Patil, David Patterson, Gaurav Agrawal, Raminder Bajwa, Sarah Bates, Suresh Bhatia, Nan Boden, Al Borchers, Rick Boyle, Pierre-luc Cantin, Clifford Chao, Chris Clark, Jeremy Coriell, Mike Daley, Matt Dau, Jeffrey Dean, Ben Gelb, Tara Vazir Ghaemmaghami, Rajendra Gottipati, William Gulland, Robert Hagmann, C. Richard Ho, Doug Hogberg, John Hu, Robert Hundt, Dan Hurt, Julian Ibarz, Aaron Jaffey, Alek Jaworski, Alexander Kaplan, Harshit Khaitan, Daniel Killebrew, Andy Koch, Naveen Kumar, Steve Lacy, James Laudon, James Law, Diemthu Le, Chris Leary, Zhuyuan Liu, Kyle Lucke, Alan Lundin, Gordon MacKean, Adriana Maggiore, Maire Mahony, Kieran Miller, Rahul Nagarajan, Ravi Narayanaswami, Ray Ni, Kathy Nix, Thomas Norrie, Mark Omernick, Narayana Penukonda, Andy Phelps, Jonathan Ross, Matt Ross, Amir Salek, Emad Samadiani, Chris Severn, Gregory Sizikov, Matthew Snelham, Jed Souter, Dan Steinberg, Andy Swing, Mercedes Tan, Gregory Thorson, Bo Tian, Horia Toma, Erick Tuttle, Vijay Vasudevan, Richard Walter, Walter Wang, Eric Wilcox, Doe Hyun Yoon, In-Datacenter Performance Analysis of a Tensor Processing Unit international symposium on computer architecture. ,vol. 45, pp. 1- 12 ,(2017) , 10.1145/3079856.3080246
Guanpeng Li, Siva Kumar Sastry Hari, Michael Sullivan, Timothy Tsai, Karthik Pattabiraman, Joel Emer, Stephen W. Keckler, Understanding error propagation in deep learning neural network (DNN) accelerators and applications ieee international conference on high performance computing data and analytics. pp. 8- ,(2017) , 10.1145/3126908.3126964
Simone Bianco, Remi Cadene, Luigi Celona, Paolo Napoletano, Benchmark Analysis of Representative Deep Neural Network Architectures IEEE Access. ,vol. 6, pp. 64270- 64277 ,(2018) , 10.1109/ACCESS.2018.2877890
Jeff Jun Zhang, Kanad Basu, Siddharth Garg, Fault-Tolerant Systolic Array Based Accelerators for Deep Neural Network Execution IEEE Design & Test of Computers. ,vol. 36, pp. 44- 53 ,(2019) , 10.1109/MDAT.2019.2915656
Yingdi Liu, Nilanjan Mukherjee, Janusz Rajski, Sudhakar M. Reddy, Jerzy Tyszer, Deterministic Stellar BIST for Automotive ICs IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. ,vol. 39, pp. 1699- 1710 ,(2020) , 10.1109/TCAD.2019.2925353