Fast inference of Boosted Decision Trees in FPGAs for particle physics
Journal Article
·
· Journal of Instrumentation
- European Organization for Nuclear Research (CERN), Geneva (Switzerland)
- Columbia Univ., New York, NY (United States)
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States); Univ. of California, San Diego, CA (United States)
- Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
- Rhodes College, Memphis, TN (United States)
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- HawkEye360, Herndon, VA (United States)
- European Organization for Nuclear Research (CERN), Geneva (Switzerland); Inst. of Physics Belgrade (Serbia)
- Univ. of Illinois, Chicago, IL (United States)
We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based real-time processing, such as in the Level-1 Trigger system of a collider experiment. These developments open up prospects for physicists to deploy BDTs in FPGAs for identifying the origin of jets, better reconstructing the energies of muons, and enabling better selection of rare signal processes.
- Research Organization:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP); European Research Council (ERC); National Science Foundation (NSF)
- Grant/Contract Number:
- AC02-07CH11359; 772369; 1606321; 115164
- OSTI ID:
- 1647080
- Report Number(s):
- arXiv:2002.02534; FERMILAB-PUB-20-400-CMS-SCD; oai:inspirehep.net:1779172; TRN: US2202982
- Journal Information:
- Journal of Instrumentation, Vol. 15, Issue 5; ISSN 1748-0221
- Publisher:
- Institute of Physics (IOP)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Cited by: 19 works
Citation information provided by
Web of Science
Web of Science
Similar Records
Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics
Fast convolutional neural networks on FPGAs with hls4ml
Fast inference of deep neural networks in FPGAs for particle physics
Journal Article
·
Thu Sep 01 00:00:00 EDT 2022
· Journal of Instrumentation
·
OSTI ID:1647080
+1 more
Fast convolutional neural networks on FPGAs with hls4ml
Journal Article
·
Fri Jul 16 00:00:00 EDT 2021
· Machine Learning: Science and Technology
·
OSTI ID:1647080
+17 more
Fast inference of deep neural networks in FPGAs for particle physics
Journal Article
·
Fri Jul 27 00:00:00 EDT 2018
· Journal of Instrumentation
·
OSTI ID:1647080
+8 more