Mixed Precision Training of Convolutional Neural Networks using Integer Operations
Dipankar Das(Malaviya National Institute of Technology Jaipur), Vadim Pirogov(Intel (United States)), Dhiraj Kalamkar, Naveen Mellempudi, Kunal Banerjee(Walmart (United States)), Alexander Heinecke, Evarist Fomenko, Pradeep Dubey(Stony Brook University), Nikita Shustrov, K. Vaidyanathan, Evangelos Georganas(Intel (United States)), Dheevatsa Mudigere, Bharat Kaul(Intel (United Kingdom)), Srinivas Sridharan(Intel (United States)), Roman Dubtsov(Intel (United States)), Sasikanth Avancha, Jesús Corbal
arXiv (Cornell University)
February 15, 2018
Cited by 29
Related Papers
SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training
|Unknown|2020|462
Critical Assessment of Metagenome Interpretation: the second round of challenges
|Nature Methods|2022|393
GraphMat
|Proceedings of the VLDB Endowment|2015|292
Mixed Precision Training of Convolutional Neural Networks using Integer Operations
|ArXiv.org|2018|115
Ternary Neural Networks with Fine-Grained Quantization
|arXiv (Cornell University)|2017|61