Towards globally optimal design of multipliers for FPGAs

A Böttcher, M Kumm - IEEE Transactions on Computers, 2023 - ieeexplore.ieee.org
The design of a multiplier typically consists of three steps:(1) partial product generation,(2)
compressor tree design and (3) the selection of the final adder. Conventionally, these three …

Resource optimal design of large multipliers for FPGAs

M Kumm, J Kappauf, M Istoan… - 2017 IEEE 24th …, 2017 - ieeexplore.ieee.org
This work presents a resource optimal approach for the design of large multipliers for
FPGAs. These are composed of smaller multipliers which can be DSP blocks or logic-based …

Optimizing bit-serial matrix multiplication for reconfigurable computing

Y Umuroglu, D Conficconi, L Rasnayake… - ACM Transactions on …, 2019 - dl.acm.org
Matrix-matrix multiplication is a key computational kernel for numerous applications in
science and engineering, with ample parallelism and data locality that lends itself well to …

Towards hardware IIR filters computing just right: Direct form I case study

A Volkova, M Istoan, F De Dinechin… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
Linear Time Invariant (LTI) filters are often specified and simulated using high-precision
software, before being implemented in low-precision fixed-point hardware. A problem is that …

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 …