Abstract
In this paper, we present an FPGA design of an extremely low latency scientific machine learning application at the edge. Real-time prediction of errant high-energy particle beams at scientific facilities such as Spallation Neutron Source (SNS) is crucial to avoid damages to the equipment. Machine learning techniques are becoming increasingly effective to detect subtle signatures of the errant beams in the noisy sensor signals. However, to minimize potential damage done by errant beam, real-time errant beam detection has to be completed with extremely low latency, usually less than 1 microsecond. By stream processing the input features and employing out-of-order execution of decision nodes among the decision trees, we demonstrate that our highly efficient FPGA implementation can achieve 60 nanoseconds of computing latency for complex random forest models with 10,000 input features.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2022 32nd International Conference on Field-Programmable Logic and Applications, FPL 2022 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 411-417 |
| Number of pages | 7 |
| ISBN (Electronic) | 9781665473903 |
| DOIs | |
| State | Published - 2022 |
| Event | 32nd International Conference on Field-Programmable Logic and Applications, FPL 2022 - Belfast, United Kingdom Duration: Aug 29 2022 → Sep 2 2022 |
Publication series
| Name | Proceedings - 2022 32nd International Conference on Field-Programmable Logic and Applications, FPL 2022 |
|---|
Conference
| Conference | 32nd International Conference on Field-Programmable Logic and Applications, FPL 2022 |
|---|---|
| Country/Territory | United Kingdom |
| City | Belfast |
| Period | 08/29/22 → 09/2/22 |
Funding
ACKNOWLEDGEMENT This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). This research is sponsored, in part, by the Office of Advanced Scientific Computing Research in the U.S. Department of Energy through the Sawtooth project, and by the RAPIDS SciDAC Institute for Computer Science and Data. Additionally this research used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory. This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). This research is sponsored, in part, by the Office of Advanced Scientific Computing Research in the U.S. Department of Energy through the Sawtooth project, and by the RAPIDS SciDAC Institute for Computer Science and Data. Additionally this research used resources at the Spallation Neutron Source, a DOE Office of Science User Facility operated by the Oak Ridge National Laboratory.