Saved in:
Bibliographic Details
Main Authors: Serhiayenka, Pavel, Roche, Stephen, Carlson, Benjamin, Hong, Tae Min
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.20506
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917058394980352
author Serhiayenka, Pavel
Roche, Stephen
Carlson, Benjamin
Hong, Tae Min
author_facet Serhiayenka, Pavel
Roche, Stephen
Carlson, Benjamin
Hong, Tae Min
contents We present a generic parallel implementation of the decision tree-based machine learning (ML) method in hardware description language (HDL) on field programmable gate arrays (FPGA). A regression problem in high energy physics at the Large Hadron Collider is considered: the estimation of the magnitude of missing transverse momentum using boosted decision trees (BDT). A forest of twenty decision trees each with a maximum depth of ten using eight input variables of 16-bit precision is executed with a latency of less than 10 ns using O(0.1%) resources on Xilinx UltraScale+ VU9P -- approximately ten times faster and five times smaller compared to similar designs using high level synthesis (HLS) -- without the use of digital signal processors (DSP) while eliminating the use of block RAM (BRAM). We also demonstrate a potential application in the estimation of muon momentum for ATLAS RPC at HL-LHC.
format Preprint
id arxiv_https___arxiv_org_abs_2409_20506
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nanosecond hardware regression trees in FPGA at the LHC
Serhiayenka, Pavel
Roche, Stephen
Carlson, Benjamin
Hong, Tae Min
High Energy Physics - Experiment
Data Analysis, Statistics and Probability
Instrumentation and Detectors
We present a generic parallel implementation of the decision tree-based machine learning (ML) method in hardware description language (HDL) on field programmable gate arrays (FPGA). A regression problem in high energy physics at the Large Hadron Collider is considered: the estimation of the magnitude of missing transverse momentum using boosted decision trees (BDT). A forest of twenty decision trees each with a maximum depth of ten using eight input variables of 16-bit precision is executed with a latency of less than 10 ns using O(0.1%) resources on Xilinx UltraScale+ VU9P -- approximately ten times faster and five times smaller compared to similar designs using high level synthesis (HLS) -- without the use of digital signal processors (DSP) while eliminating the use of block RAM (BRAM). We also demonstrate a potential application in the estimation of muon momentum for ATLAS RPC at HL-LHC.
title Nanosecond hardware regression trees in FPGA at the LHC
topic High Energy Physics - Experiment
Data Analysis, Statistics and Probability
Instrumentation and Detectors
url https://arxiv.org/abs/2409.20506