Hardware Acceleration of Kolmogorov-Arnold Network (KAN) for Lightweight Edge Inference

TL;DR

This paper presents a hardware-accelerated approach for Kolmogorov-Arnold Networks (KAN), significantly reducing hardware resources and energy consumption while boosting accuracy, through an innovative algorithm-hardware co-design methodology.

Contribution

It introduces a novel co-design framework combining algorithm and circuit techniques to accelerate KAN for lightweight edge inference.

Findings

Hardware area reduced by 41.78 times

Energy consumption decreased by 77.97 times

Achieved 3.03% accuracy boost over traditional DNN hardware

Abstract

Recently, a novel model named Kolmogorov-Arnold Networks (KAN) has been proposed with the potential to achieve the functionality of traditional deep neural networks (DNNs) using orders of magnitude fewer parameters by parameterized B-spline functions with trainable coefficients. However, the B-spline functions in KAN present new challenges for hardware acceleration. Evaluating the B-spline functions can be performed by using look-up tables (LUTs) to directly map the B-spline functions, thereby reducing computational resource requirements. However, this method still requires substantial circuit resources (LUTs, MUXs, decoders, etc.). For the first time, this paper employs an algorithm-hardware co-design methodology to accelerate KAN. The proposed algorithm-level techniques include Alignment-Symmetry and PowerGap KAN hardware aware quantization, KAN sparsity aware mapping strategy, and circuit-level techniques include N:1 Time Modulation Dynamic Voltage input generator with analog-CIM (ACIM) circuits. The impact of non-ideal effects, such as partial sum errors caused by the process variations, has been evaluated with the statistics measured from the TSMC 22nm RRAM-ACIM prototype chips. With the best searched hyperparameters of KAN and the optimized circuits implemented in 22 nm node, we can reduce hardware area by 41.78x, energy by 77.97x with 3.03% accuracy boost compared to the traditional DNN hardware.