Fast inference of Boosted Decision Trees in FPGAs for particle physics

Summers, Sioni; Guglielmo, Giuseppe Di; Duarte, Javier; Harris, Philip; Hoang, Duc; Jindariani, Sergo; Kreinar, Edward; Loncar, Vladimir; Ngadiuba, Jennifer; Pierini, Maurizio; Rankin, Dylan; Tran, Nhan; Wu, Zhenbin

doi:10.1088/1748-0221/15/05/p05026

Title: Fast inference of Boosted Decision Trees in FPGAs for particle physics

Journal Article · Fri May 29 00:00:00 EDT 2020 · Journal of Instrumentation

DOI:https://doi.org/10.1088/1748-0221/15/05/p05026· OSTI ID:1647080

Summers, Sioni ^[1]; Guglielmo, Giuseppe Di ^[2];

^[3]; Harris, Philip ^[4]; Hoang, Duc ^[5]; Jindariani, Sergo ^[6]; Kreinar, Edward ^[7]; Loncar, Vladimir ^[8]; Ngadiuba, Jennifer ^[1]; Pierini, Maurizio ^[1]; Rankin, Dylan ^[4];

^[6]; Wu, Zhenbin ^[9]

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.

View Accepted Manuscript (DOE)

Cite

Export

Save

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

Citation Metrics:

Cited by: 19 works

Citation information provided by
Web of Science

References (15)

Machine learning at the energy and intensity frontiers of particle physics Radovic, Alexander; Williams, Mike; Rousseau, David Nature, Vol. 560, Issue 7716 https://doi.org/10.1038/s41586-018-0361-2	journal	August 2018
Boosted Decision Trees in the Level-1 Muon Endcap Trigger at CMS Acosta, Darin; Brinkerhoff, Andrew; Busch, Elena Journal of Physics: Conference Series, Vol. 1085 https://doi.org/10.1088/1742-6596/1085/4/042042	journal	September 2018
Studies of boosted decision trees for MiniBooNE particle identification Yang, Hai-Jun; Roe, Byron P.; Zhu, Ji Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 555, Issue 1-2 https://doi.org/10.1016/j.nima.2005.09.022	journal	December 2005
Scalable inference of decision tree ensembles: Flexible design for CPU-FPGA platforms Owaida, Muhsen; Zhang, Hantian; Zhang, Ce 2017 27th International Conference on Field Programmable Logic and Applications (FPL) https://doi.org/10.23919/FPL.2017.8056784	conference	September 2017
XGBoost: A Scalable Tree Boosting System Chen, Tianqi; Guestrin, Carlos Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939785	conference	January 2016
Distributed Inference over Decision Tree Ensembles on Clusters of FPGAs Owaida, Muhsen; Kulkarni, Amit; Alonso, Gustavo ACM Transactions on Reconfigurable Technology and Systems, Vol. 12, Issue 4 https://doi.org/10.1145/3340263	journal	November 2019
Decision Tree and Random Forest Implementations for Fast Filtering of Sensor Data Buschjager, Sebastian; Morik, Katharina IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 65, Issue 1 https://doi.org/10.1109/TCSI.2017.2710627	journal	January 2018
FPGA Implementation of Decision Trees and Tree Ensembles for Character Recognition in Vivado Hls Kułaga, Rafał; Gorgoń, Marek Image Processing & Communications, Vol. 19, Issue 2-3 https://doi.org/10.1515/ipc-2015-0012	journal	September 2014
Fast inference of deep neural networks in FPGAs for particle physics Duarte, J.; Han, S.; Harris, P. Journal of Instrumentation, Vol. 13, Issue 07 https://doi.org/10.1088/1748-0221/13/07/P07027	journal	July 2018
Boosted decision trees as an alternative to artificial neural networks for particle identification Roe, Byron P.; Yang, Hai-Jun; Zhu, Ji Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 543, Issue 2-3 https://doi.org/10.1016/j.nima.2004.12.018	journal	May 2005
Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree Gligorov, V. V.; Williams, M. Journal of Instrumentation, Vol. 8, Issue 02 https://doi.org/10.1088/1748-0221/8/02/P02013	journal	February 2013
Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC Chatrchyan, S.; Khachatryan, V.; Sirunyan, A. M. Physics Letters B, Vol. 716, Issue 1 https://doi.org/10.1016/j.physletb.2012.08.021	journal	September 2012
HLS4ML LHC Jet dataset (150 particles) Pierini, Maurizio; Duarte, Javier Mauricio; Tran, Nhan Zenodo https://doi.org/10.5281/zenodo.3602259	dataset	January 2020
Deep Learning and Its Application to LHC Physics Guest, Dan; Cranmer, Kyle; Whiteson, Daniel Annual Review of Nuclear and Particle Science, Vol. 68, Issue 1 https://doi.org/10.1146/annurev-nucl-101917-021019	journal	October 2018
Deep Learning and its Application to LHC Physics Guest, Dan; Cranmer, Kyle; Whiteson, Daniel arXiv https://doi.org/10.48550/arxiv.1806.11484	text	January 2018

Similar Records

Nanosecond machine learning regression with deep boosted decision trees in FPGA for high energy physics

Journal Article · Thu Sep 01 00:00:00 EDT 2022 · Journal of Instrumentation · OSTI ID:1647080

Carlson, B. T.; Bayer, Q.; Hong, T. M.; +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

Aarrestad, Thea; Loncar, Vladimir; Ghielmetti, Nicolò; +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

Duarte, Javier; Han, Song; Harris, Philip; +8 more

Related Subjects

79 ASTRONOMY AND ASTROPHYSICS
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
analysis and statistical methods
data processing methods
digital electronic circuits
trigger algorithms

Title: Fast inference of Boosted Decision Trees in FPGAs for particle physics

Citation Formats

References (15)

Similar Records

Related Subjects