Speaker
Description
Track reconstruction is a cornerstone of modern collider experiments, and the HL-LHC ITk upgrade for ATLAS poses new challenges with its increased silicon hit clusters and strict throughput requirements. Deep learning approaches compare favorably with traditional combinatorial ones — as shown by the GNN4ITk project, a geometric learning tracking pipeline that achieves competitive physics performance at sub-second inference times. In this contribution, we evaluate a range of pipeline configurations and machine learning inference strategies that further improve track reconstruction at lower latencies. We present benchmarks for latency, throughput, memory usage, and power consumption across these pipelines. New developments include improved GPU-based module map performance and memory optimizations; model enhancements through pruning, quantization and advanced compilation techniques used in industry; and a custom graph segmentation approach. These upgrades allow the pipeline to target trigger-level track reconstruction in certain conditions. We also discuss improvements in track fitting, integrations into traditional-learned hybrid pipelines, GNN-based seeding, triplet-wise processing of cluster features, and production readiness with inference-as-a-service.
Significance
This is a major update to the ML-based tracking chain for ATLAS upgrade, that shows for the first time competitive physics performance with traditional techniques, as well as computational improvements, reducing latency by around 3x compared with previous reports.
References
https://indico.cern.ch/event/1338689/contributions/6011080/
https://cds.cern.ch/record/2871986/files/ATL-SOFT-PROC-2023-038.pdf
| Experiment context, if any | ATLAS experiment |
|---|