ML-PLAC: Multiplierless Piecewise Linear Approximation for Nonlinear Function Evaluation
- 23 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 69 (4) , 1546-1559
Abstract
In this article, we propose a multiplierless piecewise linear (PWL) approximation computation (ML-PLAC) method for nonlinear unary functions. ML-PLAC seeks the minimum number of segments with the predefined fractional bit width and number of adders to satisfy the restriction on the maximum absolute error ( MAE ). Compared with the previous universal PWL approximation method, multiplication operations in the segmentor are replaced by a simulation of shift-and-add operations by reducing the fractional bit width of the slope of linear functions. Various numbers of segments are obtained by different predefined numbers of adders to balance the two numbers. In addition, adders are used to replace the multiplier in hardware architecture. The synthesized results prove that ML-PLAC has increased performance without any compromises. Compared with state-of-the-art methods, ML-PLAC saves 58.82% area, 38.16% delay, 60.31% power and 6.10% MAE when computing logarithmic functions; 51.51% area, 46.49% delay, and 46.95% power while maintaining the comparable MAE when computing antilogarithmic functions; 55.21% area, 25% delay, 61.21% power, and 37.30% MAE when computing hyperbolic tangent functions; 82.47% area, 60% delay, 77.51% power and 12.74% MAE when computing sigmoid functions; and 46.43% area, 31.43% delay, and 61.16% power while maintaining the same MAE when computing softsign functions.Keywords
Funding Information
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China (21KJB510012, 19KJB510038)
- Scientific Research Foundation for the High-Level Talents of Jinling Institute of Technology (jit-b-201907)
- Scientific Research Incubation Foundation of Jinling Institute of Technology (jit-fhxm-2007)
This publication has 34 references indexed in Scilit:
- Accelerating Recurrent Neural Networks: A Memory-Efficient ApproachIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017
- Double Logarithmic Arithmetic Technique for Low-Power 3-D Graphics ApplicationsIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2017
- Computing Arithmetic Functions Using Stochastic Logic by Series ExpansionIEEE Transactions on Emerging Topics in Computing, 2016
- Hierarchical Multipartite Function EvaluationIEEE Transactions on Computers, 2016
- A Low-Error, Cost-Efficient Design Procedure for Evaluating Logarithms to Be Used in a Logarithmic Arithmetic ProcessorIEEE Transactions on Computers, 2015
- An Improved Two-Step Binary Logarithmic Converter for FPGAsIEEE Transactions on Circuits and Systems II: Express Briefs, 2014
- New Metrics for the Reliability of Approximate and Probabilistic AddersIEEE Transactions on Computers, 2012
- Low Cost Hardware Implementation of Logarithm ApproximationIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2010
- A 231-MHz, 2.18-mW 32-bit Logarithmic Arithmetic Unit for Fixed-Point 3-D Graphics SystemIEEE Journal of Solid-State Circuits, 2006
- Algorithm and architecture for logarithm, exponential, and powering computationIEEE Transactions on Computers, 2004