GPU coprocessors as a service for deep learning inference in high energy physics

Krupa, J.; Lin, Kelvin; Flechas, Maria Acosta; Dinsmore, Jack T.; Duarte, J.; Harris, P.; Hauck, Scott; Holzman, B.; Hsu, S.‐C.; Klijnsma, T.; Liu, Mia; Pedro, K.; Rankin, D.; Suaysom, Natchanon; Trahms, Matthew; Tran, N. V.

doi:10.1088/2632-2153/abec21

Cited by 24 publications

(18 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This includes GPUs and potentially even field-programmable gate arrays (FPGAs) or ML-specific processors such as the GraphCore intelligence processing units (IPUs) [67] through specialized ML compilers [68][69][70]. These coprocessing accelerators can be integrated into existing CPU-based experimental software frameworks as a scalable service that grows to meet the transient demand [71][72][73].…”

Section: Resultsmentioning

confidence: 99%

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton–proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms, while significantly improving the reconstruction quality over rule-based algorithms for granular detectors. We introduce MLPF, a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, computationally efficient, and scalable graph neural network optimized using a multi-task objective on simulated events. We report the physics and computational performance of the MLPF algorithm on a Monte Carlo dataset of top quark–antiquark pairs produced in proton–proton collisions in conditions similar to those expected for the high-luminosity LHC. The MLPF algorithm improves the physics response with respect to a rule-based benchmark algorithm and demonstrates computationally scalable particle-flow reconstruction in a high-pileup environment.

show abstract

Section: Resultsmentioning

confidence: 99%

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…This works shows how a tracking pipeline based on geometric deep learning can achieve state-of-the-art computing performance that scales linearly with the number of spacepoints, showing great promise for the next generation of HEP experiments. The inference pipeline has been optimized on GPU systems, on the assumption that the next generation of HEP experiments will have widespread access to accelerators either locally in heterogeneous systems [27,53] or remotely [54,55].…”

Section: Discussionmentioning

confidence: 99%

Performance of a geometric deep learning pipeline for HL-LHC particle tracking

Murnane

Calafiura

et al. 2021

Eur. Phys. J. C

Self Cite

View full text Add to dashboard Cite

The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX’s tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.

show abstract

“…Results are given in Fig 9, separately for CPUs and GPUs. Having in mind an offline application, one could maximally benefit if the network throughput by running the network at once across batches of events, e.g., implementing the inference-as-a-service concept discussed in [106].…”

Section: Latency and Power Measurementsmentioning

confidence: 99%

Lightweight Jet Reconstruction and Identification as an Object Detection Task

Pol

Aarrestad

Говоркова

et al. 2022

Preprint

View full text Add to dashboard Cite

We apply object detection techniques based on deep convolutional blocks to end-to-end jet identification and reconstruction tasks encountered at the CERN Large Hadron Collider (LHC). Collision events produced at the LHC and represented as an image composed of calorimeter and tracker cells are given as an input to a Single Shot Detection network. The algorithm, named PFJet-SSD performs simultaneous localization, classification and regression tasks to cluster jets and reconstruct their features. This all-in-one single feed-forward pass gives advantages in terms of execution time and an improved accuracy w.r.t. traditional rule-based methods. A further gain is obtained from network slimming, homogeneous quantization, and optimized runtime for meeting memory and latency constraints of a typical real-time processing environment. We experiment with 8-bit and ternary quantization, benchmarking their accuracy and inference latency against a single-precision floating-point. We show that the ternary network closely matches the performance of its full-precision equivalent and outperforms the state-of-the-art rule-based algorithm. Finally, we report the inference latency on different hardware platforms and discuss future applications.

show abstract

GPU coprocessors as a service for deep learning inference in high energy physics

Cited by 24 publications

References 66 publications

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

MLPF: efficient machine-learned particle-flow reconstruction using graph neural networks

Performance of a geometric deep learning pipeline for HL-LHC particle tracking

Lightweight Jet Reconstruction and Identification as an Object Detection Task

Contact Info

Product

Resources

About