Most Resource Efficient Matrix Vector Multiplication on FPGAs
Open Access
- 5 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 3881-3898
Abstract
Fast and resource-efficient inference in artificial neural networks (ANNs) is of utmost importance and drives many new developments in the area of new hardware architectures, e.g., by means of systolic arrays or algorithmic optimization such as pruning. In this paper, we present a novel method for lowering the computation effort for ANN inference utilizing ideas from information theory.Weight matrices are sliced into submatrices of logarithmic aspect ratios. These slices are then factorized. This reduces the number of required computations without compromising on fully parallel processing. We create a new hardware architecture for this dedicated purpose. We also provide a tool to map these sliced and factorized matrices efficiently to reconfigurable hardware. By comparing to the state of the art FPGA implementations, we can prove our claim by lowering hardware resources measured in look-up-tables (LUTs) by a factor of three to six. Our method does not rely on any particular property of the weight matrices of the ANN. It works for the general task of multiplying an input vector with a constant matrix and is also suitable for digital signal processing beyond ANNs.Keywords
Funding Information
- German Research Foundation Deutsche Forschungsgesellschaft (DFG) through the Project Berechnungscodierung (RE 4182/4-1, MU 3735/8-1)
This publication has 50 references indexed in Scilit:
- An Artificial Neural Network Approach for Early Fault Detection of Gearbox BearingsIEEE Transactions on Smart Grid, 2015
- Convolutional Neural Networks for Speech RecognitionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Speech recognition with deep recurrent neural networks2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- The Mailman algorithm: A note on matrix–vector multiplicationInformation Processing Letters, 2009
- Some Optimizations of Hardware Multiplication by Constant MatricesIEEE Transactions on Computers, 2005
- QuantizationIEEE Transactions on Information Theory, 1998
- Matching pursuits with time-frequency dictionariesIEEE Transactions on Signal Processing, 1993
- Gaussian elimination is not optimalNumerische Mathematik, 1969
- A SIGNED BINARY MULTIPLICATION TECHNIQUEQuarterly Journal of Mechanics and Applied Mathematics, 1951