Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Iiyama, Y.; Cerminara, G.; Gupta, A.; Kieseler, J.; Lončar, Vladimir; Pierini, M.; Qasim, Shah Rukh; Rieger, M.; Summers, S.; Onsem, Gerrit Van; Wozniak, K. A.; Ngadiuba, J.; Guglielmo, Giuseppe Di; Duarte, J.; Harris, P.; Rankin, D.; Jindariani, S.; Liu, Mia; Pedro, K.; Tran, N. V.; Kreinar, Edward; Wu, Z.

doi:10.3389/fdata.2020.598927

Cited by 55 publications

(39 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many commonly used NN layers are supported: Dense; Convolution; BatchNormalization; and several Activation layers. In addition, domain specific layers can be easily added, one example being compressed distance-weighted graph networks [42].…”

Section: Motivationmentioning

confidence: 99%

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

et al. 2021

Self Cite

View full text Add to dashboard Cite

Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption. One technique to limit model size is quantization, which implies using fewer bits to represent weights and biases. Such an approach usually results in a decline in performance. Here, we introduce a method for designing optimally heterogeneously quantized versions of deep neural network models for minimum-energy, high-accuracy, nanosecond inference and fully automated deployment on chip. With a per-layer, per-parameter type automatic quantization procedure, sampling from a wide range of quantizers, model energy consumption and size are minimized while high accuracy is maintained. This is crucial for the event selection procedure in proton-proton collisions at the CERN Large Hadron Collider, where resources are strictly limited and a latency of O(1) µs is required. Nanosecond inference and a resource consumption reduced by a factor of 50 when implemented on field-programmable gate array hardware are achieved. FIG.I. An ultra-compressed deep neural network for particle identification on a Xilinx FPGA.

show abstract

Section: Motivationmentioning

confidence: 99%

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The algorithm is simple to port to computing architectures that support common ML frameworks like TensorFlow without significant investment. 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

“…Work has also been done to accelerate the inference of deep neural networks with heterogeneous resources beyond GPUs, like field-programmable gate arrays (FPGAs) [49][50][51][52][53][54][55][56][57]. This work extends to GNN architectures [29,58]. Specifically, in Ref.…”

Section: Inference Timingmentioning

confidence: 99%

Charged Particle Tracking via Edge-Classifying Interaction Networks

Dezoort

Thais

Duarte

et al. 2021

Comput Softw Big Sci

Self Cite

View full text Add to dashboard Cite

Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high-energy particle physics. In particular, particle tracking data are naturally represented as a graph by identifying silicon tracker hits as nodes and particle trajectories as edges, given a set of hypothesized edges, edge-classifying GNNs identify those corresponding to real particle trajectories. In this work, we adapt the physics-motivated interaction network (IN) GNN toward the problem of particle tracking in pileup conditions similar to those expected at the high-luminosity Large Hadron Collider. Assuming idealized hit filtering at various particle momenta thresholds, we demonstrate the IN’s excellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking: graph construction, edge classification, and track building. The proposed IN architecture is substantially smaller than previously studied GNN tracking architectures; this is particularly promising as a reduction in size is critical for enabling GNN-based tracking in constrained computing environments. Furthermore, the IN may be represented as either a set of explicit matrix operations or a message passing GNN. Efforts are underway to accelerate each representation via heterogeneous computing resources towards both high-level and low-latency triggering applications.

show abstract

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Cited by 55 publications

References 33 publications

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors

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

Charged Particle Tracking via Edge-Classifying Interaction Networks

Contact Info

Product

Resources

About