CERN Accelerating science

ATLAS Slides
Report number	ATL-DAQ-SLIDE-2024-616
Title	QDIPS: Deep Sets Network for FPGA investigated for high speed inference on ATLAS
Author(s)	Antel, Claire (Universite de Geneve (CH))
Corporate author(s)	The ATLAS collaboration
Collaboration	ATLAS Collaboration
Submitted to	27th International Conference on Computing in High Energy & Nuclear Physics, Kraków, Pl, 19 - 25 Oct 2024
Submitted by	[email protected] on 05 Dec 2024
Subject category	Particle Physics - Experiment
Accelerator/Facility, Experiment	CERN LHC ; ATLAS
Free keywords	ATLAS Upgrade ; trigger ; TDAQ ; machine learning ; FPGA
Abstract	Deep sets network architectures have useful applications in finding correlations in unordered and variable length data input, thus having the interesting feature of being permutation invariant. Its use on FPGA would open up accelerated machine learning in areas where the input has no fixed length or order, such as inner detector hits for clustering or associated particle tracks for jet tagging. We adapted DIPS (Deep Impact Parameter Sets), a deep sets neural network flavour tagging algorithm previously used in ATLAS offline low-level flavour tagging and online b-jet trigger preselections, for use on FPGA with the aim to assess its performance and resource costs. QKeras and HLS4ML are used for quantisation-aware training and translation for FPGA implementation, respectively. Some challenges are addressed, such as finding replacements for functionality not available in HLS4ML (e.g. Time Distributed layers) and implementations of custom HLS4ML layers. Satisfactory implementations are tested on an actual FPGA board for the assessment of true resource consumption and latency. We show the optimal FPGA-based algorithm performance relative to CPU-based full precision performance previously achieved in the ATLAS trigger, as well as performance trade-offs when reducing FPGA resource usage as much as possible. The project aims to demonstrate a viable solution for performing sophisticated Machine Learning-based tasks for accelerated reconstruction or particle identification for early event rejection while running in parallel to other more intensive tasks on FPGA.