Fast inference of Boosted Decision Trees in FPGAs for particle physics

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.

[1]  Mohammad Jaleel Soreefan.  Deep learning and its application , 2019 .

[2]  Muhsen Owaida,et al.  Distributed Inference over Decision Tree Ensembles on Clusters of FPGAs , 2019, ACM Trans. Reconfigurable Technol. Syst..

[3]  Y. Coadou,et al.  Boosted Decision Trees , 2016, Artificial Intelligence for High Energy Physics.

[4]  B. Roe,et al.  Studies of boosted decision trees for MiniBooNE particle identification , 2005, physics/0508045.

[5]  D. Whiteson,et al.  Deep Learning and Its Application to LHC Physics , 2018, Annual Review of Nuclear and Particle Science.

[6]  Katharina Morik,et al.  Decision Tree and Random Forest Implementations for Fast Filtering of Sensor Data , 2018, IEEE Transactions on Circuits and Systems I: Regular Papers.

[7]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[8]  Ryszard S. Romaniuk,et al.  Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC , 2012 .

[9]  Song Han,et al.  Fast inference of deep neural networks in FPGAs for particle physics , 2018, Journal of Instrumentation.

[10]  Mike Williams,et al.  Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree , 2012, 1210.6861.

[11]  Gustavo Alonso,et al.  Scalable inference of decision tree ensembles: Flexible design for CPU-FPGA platforms , 2017, 2017 27th International Conference on Field Programmable Logic and Applications (FPL).

[12]  Antonino Mazzeo,et al.  Decision Tree-Based Multiple Classifier Systems: An FPGA Perspective , 2015, MCS.

[14]  Kazuhiro Terao,et al.  Machine learning at the energy and intensity frontiers of particle physics , 2018, Nature.

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Danna Zhou,et al.  d. , 1934, Microbial pathogenesis.

[17]  Wei Shi,et al.  Boosted Decision Trees in the Level-1 Muon Endcap Trigger at CMS , 2018, Journal of Physics: Conference Series.

[18]  B. Roe,et al.  Boosted Decision Trees, an Alternative to Artificial Neural Networks , 2004 .

[19]  B. Roe,et al.  Boosted decision trees as an alternative to artificial neural networks for particle identification , 2004, physics/0408124.

[20]  Rafał Kułaga,et al.  FPGA Implementation of Decision Trees and Tree Ensembles for Character Recognition in Vivado Hls , 2014 .