Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml

Elham E Khoda, Dylan Rankin, Rafael Teixeira de Lima, Philip Harris, Scott Hauck, Shih-Chieh Hsu, Michael Kagan, Vladimir Loncar, Chaitanya Paikara, Richa Rao, Sioni Summers, Caterina Vernieri, Aaron Wang
University of Washington, Seattle, WA 98195, USA
arXiv:2207.00559 [cs.LG]




   author={Khoda, Elham E and Rankin, Dylan and de Lima, Rafael Teixeira and Harris, Philip and Hauck, Scott and Hsu, Shih-Chieh and Kagan, Michael and Loncar, Vladimir and Paikara, Chaitanya and Rao, Richa and Summers, Sioni and Vernieri, Caterina and Wang, Aaron},

   keywords={Machine Learning (cs.LG), High Energy Physics – Experiment (hep-ex), Instrumentation and Detectors (physics.ins-det), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Physical sciences, FOS: Physical sciences},

   title={Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml},



   copyright={Creative Commons Attribution 4.0 International}


Recurrent neural networks have been shown to be effective architectures for many tasks in high energy physics, and thus have been widely adopted. Their use in low-latency environments has, however, been limited as a result of the difficulties of implementing recurrent architectures on field-programmable gate arrays (FPGAs). In this paper we present an implementation of two types of recurrent neural network layers — long short-term memory and gated recurrent unit — within the hls4ml framework. We demonstrate that our implementation is capable of producing effective designs for both small and large models, and can be customized to meet specific design requirements for inference latencies and FPGA resources. We show the performance and synthesized designs for multiple neural networks, many of which are trained specifically for jet identification tasks at the CERN Large Hadron Collider.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: