arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2512.12850cs.ARcs.LGcs.SYeess.SYhep-ex

KANELÉ:基于Kolmogorov-Arnold网络的高效LUT评估

KANELÉ: Kolmogorov-Arnold Networks for Efficient LUT-based Evaluation

Massachusetts Institute of Technology(麻省理工学院)

Duc Hoang, Aarush Gupta, Philip Harris

AI总结:

提出KANELÉ框架,利用Kolmogorov-Arnold网络(KAN)的独特性质,通过量化与剪枝协同优化,首次系统实现FPGA上的高效LUT映射,相比先前方法加速高达2700倍并节省大量资源。

摘要:

低延迟、资源高效的FPGA神经网络推理对于需要实时能力和低功耗的应用至关重要。基于查找表(LUT)的神经网络是一种常见解决方案,结合了强大的表示能力和高效的FPGA实现。在这项工作中,我们介绍了KANELÉ,一个利用Kolmogorov-Arnold网络(KAN)独特性质进行FPGA部署的框架。与传统的多层感知器(MLP)不同,KAN使用可学习的一维样条作为边缘激活函数,其域固定,这种结构天然适合离散化和高效的LUT映射。我们提出了第一个在FPGA上实现KAN的系统设计流程,通过量化与剪枝协同优化训练,以实现紧凑、高吞吐量和低延迟的KAN架构。我们的结果表明,与先前的KAN-on-FPGA方法相比,加速高达2700倍,并节省了数量级的资源。此外,KANELÉ在广泛使用的基准测试中匹配或超越了其他基于LUT的架构,特别是在涉及符号或物理公式的任务中,同时平衡了FPGA硬件上的资源使用。最后,我们通过将框架扩展到实时、高能效的控制系统,展示了其多功能性。

英文摘要:

Low-latency, resource-efficient neural network inference on FPGAs is essential for applications demanding real-time capability and low power. Lookup table (LUT)-based neural networks are a common solution, combining strong representational power with efficient FPGA implementation. In this work, we introduce KANELÉ, a framework that exploits the unique properties of Kolmogorov-Arnold Networks (KANs) for FPGA deployment. Unlike traditional multilayer perceptrons (MLPs), KANs employ learnable one-dimensional splines with fixed domains as edge activations, a structure naturally suited to discretization and efficient LUT mapping. We present the first systematic design flow for implementing KANs on FPGAs, co-optimizing training with quantization and pruning to enable compact, high-throughput, and low-latency KAN architectures. Our results demonstrate up to a 2700x speedup and orders of magnitude resource savings compared to prior KAN-on-FPGA approaches. Moreover, KANELÉ matches or surpasses other LUT-based architectures on widely used benchmarks, particularly for tasks involving symbolic or physical formulas, while balancing resource usage across FPGA hardware. Finally, we showcase the versatility of the framework by extending it to real-time, power-efficient control systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑