Reconfigurable convolutional kernels for neural networks on FPGAs

M Hardieck, M Kumm, K Möller, P Zipf - Proceedings of the 2019 ACM …, 2019 - dl.acm.org
Convolutional neural networks (CNNs) gained great success in machine learning
applications and much attention was paid to their acceleration on field programmable gate …

Multiplication by Constants

F de Dinechin, M Kumm - … -Specific Arithmetic: Computing Just Right for the …, 2023 - Springer
Multiplication by a constant is probably the most useful and best studied case of operator
specialization, in particular for its importance in the construction of digital filters. There are …

Field Programmable Gate Arrays

F de Dinechin, M Kumm - … -Specific Arithmetic: Computing Just Right for the …, 2023 - Springer
Field programmable gate arrays (FPGAs) are a natural target for application-specific
arithmetic, and many of the techniques developed in this book were motivated by FPGA …