Track reconstruction as a service for collider physics

2025-01-09

AI Summary

Real-time charged-particle tracking in high-energy collider experiments during the High-Luminosity LHC (HL-LHC) era faces severe computational bottlenecks. Method: This paper introduces the “Tracking Reconstruction as a Service” (TRaaS) paradigm, unifying rule-based (Patatrack) and learning-based (Exa.TrkX) tracking algorithms as low-latency, high-concurrency remote inference services on GPU clusters. TRaaS employs zero-copy memory mapping, asynchronous request scheduling, CUDA kernel optimization, and a lightweight cross-node data transfer protocol to enable lossless multi-CPU-core concurrency and efficient GPU utilization. Contribution/Results: Experiments demonstrate constant per-request latency, negligible data-transfer overhead, and significantly improved GPU utilization. TRaaS achieves millisecond-scale response times and supports thousands of concurrent requests—marking the first solution capable of meeting HL-LHC online reconstruction requirements for both real-time performance and scalability.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Motion & Tracking
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Security and Privacy: Tracking, profiling, and countermeasures against them

Abstract

Optimizing charged-particle track reconstruction algorithms is crucial for efficient event reconstruction in Large Hadron Collider (LHC) experiments due to their significant computational demands. Existing track reconstruction algorithms have been adapted to run on massively parallel coprocessors, such as graphics processing units (GPUs), to reduce processing time. Nevertheless, challenges remain in fully harnessing the computational capacity of coprocessors in a scalable and non-disruptive manner. This paper proposes an inference-as-a-service approach for particle tracking in high energy physics experiments. To evaluate the efficacy of this approach, two distinct tracking algorithms are tested: Patatrack, a rule-based algorithm, and Exa.TrkX, a machine learning-based algorithm. The as-a-service implementations show enhanced GPU utilization and can process requests from multiple CPU cores concurrently without increasing per-request latency. The impact of data transfer is minimal and insignificant compared to running on local coprocessors. This approach greatly improves the computational efficiency of charged particle tracking, providing a solution to the computing challenges anticipated in the High-Luminosity LHC era.

Problem

• GPU acceleration
• Charged particle tracking
• LHC experiment

Innovation

• Service-oriented Approach
• GPU Optimization
• Parallel Processing