BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing

Built on

K. Asanović et al., “The landscape of parallel computing research: A view from Berkeley,” Tech. Rep. UCB/EECS-2006-183, Dec 2006
2006
Earlier work this paper cites.
J. Bachrach et al., “Chisel: Constructing hardware in a Scala embedded language,” in DAC
2012
Earlier work this paper cites.
S. Mittal, “A survey of techniques for approximate computing,” ACM Computing Surveys
2016
Earlier work this paper cites.
I. Hubara et al., “Quantized neural networks: Training neural networks with low precision weights and activations,” arXiv preprint arXiv:1609.07061
Original
2016
Earlier work this paper cites.

P. Judd et al., “Stripes: Bit-serial deep neural network computing,” in MICRO
2016
Cited alongside, same era.
E. Park et al., “Weighted-entropy-based quantization for deep neural networks,” in CVPR
2017
Cited alongside, same era.
Y. Umuroglu and M. Jahre, “Streamlined deployment for quantized neural networks,” arXiv preprint arXiv:1709.04060
Original
2017
Cited alongside, same era.
Y. Umuroglu et al., “FINN: A framework for fast, scalable binarized neural network inference,” in FPGA
2017
Cited alongside, same era.

T. B. Preußer, “Generic and universal parallel matrix summation with a flexible compression goal for Xilinx FPGAs,” in FPL
2017
Later among the works it cites.
D. J. Moss et al., “A customizable matrix multiplication framework for the Intel HARPv2 Xeon+ FPGA platform: A deep learning case study,” in FPGA
2018
Closest in time.
F. Pedersoli et al., “Espresso: Efficient forward propagation for BCNNs,” in ICLR
2018
Closest in time.