Greater than the sum of its LUTs: scaling up LUT-based neural networks with AmigoLUT
File(s)
Published version
Author(s)
Type
Conference Paper
Abstract
Applications like high-energy physics and cybersecurity require extremely high throughput and low latency neural network (NN) inference. Lookup-table-based NNs address these constraints by implementing NNs as lookup tables (LUTs), achieving inference latency on the order of nanoseconds. Since LUTs are a fundamental FPGA building block, LUT-based NNs efficiently map to FPGAs. LogicNets (and its successors) form one class of LUT-based NNs that target FPGAs, mapping neurons directly to LUTs to meet low latency constraints with minimal resources. However, it is difficult to build larger, more performant LUT-based NNs like LogicNets because LUT usage increases exponentially with respect to neuron fan-in (i.e., number of synapses X synapse bitwidth). A large LUT-based NN quickly runs out of LUTs on an FPGA. Our work AmigoLUT addresses this issue by creating ensembles of smaller LUT-based NNs that scale linearly with respect to the number of models. AmigoLUT improves the scalability of LUT-based NNs, reaching higher throughput with up to an order of magnitude fewer LUTs than the largest LUT-based NNs.
Date Issued
2025-02-27
Date Acceptance
2025-02-01
Citation
Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, 2025, pp.25-35
ISBN
9798400713965
Publisher
ACM
Start Page
25
End Page
35
Journal / Book Title
Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays
Copyright Statement
Copyright © 2025 Owner/Author. This work is licensed under a Creative Commons Attribution International 4.0 License (https://creativecommons.org/licenses/by/4.0/)
License URL
Identifier
10.1145/3706628.3708874
Source
FPGA '25: The 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays
Subjects
Edge AI
FPGA
hardware-software codesign
neural networks
Publication Status
Published
Start Date
2025-02-27
Finish Date
2025-03-01
Coverage Spatial
Monterey, CA, USA
Date Publish Online
2025-02-27