NeuraLUT-assemble: hardware-aware assembling of sub-neural networks for efficient LUT inference
OA Location
Author(s)
Andronic, Marta
Constantinides, George A
Type
Conference Paper
Abstract
Efficient neural networks (NNs) leveraging lookup tables (LUTs) have demonstrated significant potential for emerging AI applications, particularly when deployed on field-programmable gate arrays (FPGAs) for edge computing. These architectures promise ultra-low latency and reduced resource utilization, broadening neural network adoption in fields such as particle physics. However, existing LUT-based designs suffer from accuracy degradation due to the large fan-in required by neurons being limited by the exponential scaling of LUT resources with input width. In practice, in prior work this tension has resulted in the reliance on extremely sparse models. We present NeuraLUT-Assemble, a novel framework that addresses these limitations by combining mixed-precision techniques with the assembly of larger neurons from smaller units, thereby increasing connectivity while keeping the number of inputs of any given LUT manageable. Additionally, we intro-duce skip-connections across entire LUT structures to improve gradient flow. NeuraLUT-Assemble closes the accuracy gap between LUT-based methods and (fully-connected) MLP-based models, achieving competitive accuracy on tasks such as network intrusion detection, digit classification, and jet classification, demonstrating up to 8.42x reduction in the area-delay product compared to the state-of-the-art at the time of the publication.
Date Issued
2025-05-28
Date Acceptance
2025-05-01
Citation
2025 IEEE 33rd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2025, pp.208-216
ISBN
979-8-3315-0282-9
ISSN
2576-2613
Publisher
IEEE Computer Society
Start Page
208
End Page
216
Journal / Book Title
2025 IEEE 33rd Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)
Copyright Statement
Copyright © 2025, IEEE.
Identifier
http://arxiv.org/abs/2504.00592v1
Source
33rd International Symposium on Field Programmable Custom Computing Machines-FCCM-Annual
Subjects
Computer Science
Computer Science, Hardware & Architecture
Computer Science, Software Engineering
Engineering
Engineering, Electrical & Electronic
Science & Technology
Technology
Publication Status
Published
Start Date
2025-05-04
Finish Date
2025-05-07
Coverage Spatial
Fayetteville, AR, USA