SIGMA: A Sparse and Irregular GEMM Accelerator with Flexible Interconnects for DNN Training
Eric Qin(Georgia Institute of Technology), Tushar Krishna(Georgia Institute of Technology), Sudarshan Srinivasan(Intel (United Kingdom)), Hyoukjun Kwon(Georgia Institute of Technology), Bharat Kaul(Intel (United Kingdom)), Ananda Samajdar(Georgia Institute of Technology), Dipankar Das(Malaviya National Institute of Technology Jaipur), Vineet Nadella(Georgia Institute of Technology)
Cited by 462
Related Papers
GraphMat
|Proceedings of the VLDB Endowment|2015|292
Mixed Precision Training of Convolutional Neural Networks using Integer Operations
|ArXiv.org|2018|115
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
|Unknown|2020|110
Ternary Neural Networks with Fine-Grained Quantization
|arXiv (Cornell University)|2017|61
Parallel Efficient Sparse Matrix-Matrix Multiplication on Multicore Platforms
|Lecture notes in computer science|2015|59