Exploiting input data sparsity in neural network compute units
作者： Ravi Narayanaswami , Dong Hyuk Woo
DOI:
关键词:
摘要: A computer-implemented method includes receiving, by a computing device, input activations and determining, by a controller of the computing device, whether each of the …
lens.org 参考文章(42)
Toshio Akabane, Naoyuki Fukuda, Yoshiji Fujimoto, Apparatus for calculating matrices ,(1991)
Ravi Narayanaswami, Hanumanthrao Nimishakavi, Ikuji Nobugaki, Niraj Kumar, Semiconductor multi-device system with logic means for controlling the operational mode of a set of input/output data bus drivers ,(1990)
Corinthios M, High speed signal processor for vector transformation ,(1971)
Alex Nugent, Nanotechnology neural network methods and systems ,(2003)
Gordon Clyde Fossum, Data Structure For Tiling And Packetizing A Sparse Matrix ,(2011)
Kevin Gurney, An introduction to neural networks ,(1997)
Joshua B Fryman, Allan D Knies, David Pardo Keppel, Dong Hyuk Woo, Collective communications apparatus and method for parallel systems ,(2014)
Jack I. Jmaev, Patrick F. Castelaz, Dwight E. Mills, Steven C. Woo, Tammy L. Henrikson, Neural engine for emulating a neural network ,(1993)
Robert Gwilym Dimond, Method of transferring data, a method of processing data, an accelerator, a computer system and a computer program ,(2011)
David M. Keaton, Thomas S. Plum, Automated safe secure techniques for eliminating undefined behavior in computer software ,(2005)