GRAU: Generic Reconfigurable Activation Unit Design for Neural Network Hardware Accelerators
Hardware Architecture
2026-02-27 v1 Artificial Intelligence
Abstract
With the continuous growth of neural network scales, low-precision quantization is widely used in edge accelerators. Classic multi-threshold activation hardware requires 2^n thresholds for n-bit outputs, causing a rapid increase in hardware cost as precision increases. We propose a reconfigurable activation hardware, GRAU, based on piecewise linear fitting, where the segment slopes are approximated by powers of two. Our design requires only basic comparators and 1-bit right shifters, supporting mixed-precision quantization and nonlinear functions such as SiLU. Compared with multi-threshold activators, GRAU reduces LUT consumption by over 90%, achieving higher hardware efficiency, flexibility, and scalability.
Cite
@article{arxiv.2602.22352,
title = {GRAU: Generic Reconfigurable Activation Unit Design for Neural Network Hardware Accelerators},
author = {Yuhao Liu and Salim Ullah and Akash Kumar},
journal= {arXiv preprint arXiv:2602.22352},
year = {2026}
}