Deploying a Hybrid PVFinder Algorithm for Primary Vertex Reconstruction in LHCb's GPU-Resident HLT1
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910030255620096 |
|---|---|
| author | Akar, Simon Elashri, Mohamed Henderson, Conor Sokoloff, Michael |
| author_facet | Akar, Simon Elashri, Mohamed Henderson, Conor Sokoloff, Michael |
| contents | LHCb's Run 3 upgrade introduced a fully software-based trigger system operating at 30~MHz, processing an average of 5.6 proton-proton collision vertices per bunch crossing (event). This work presents the development of an inference engine for PVFinder, a hybrid deep neural network for finding primary vertices, the proton-proton collision points from which all subsequent particle decays originate into Allen, LHCb's High Level Trigger (HLT1) framework. The integration addresses critical real-time constraints including fixed memory pools, single-stream execution, and sub-400~$μ$s per-event processing budgets on NVIDIA GPUs. We introduce a translation layer that bridges Allen's Structure-of-Arrays (SoA) data layout with cuDNN's tensor format while maintaining zero-copy semantics and deterministic behavior. Current performance shows the CNN stage contributes significant throughput overhead. We present a roadmap targeting order-of-magnitude improvements through mixed-precision computing, model compression and other techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19959 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deploying a Hybrid PVFinder Algorithm for Primary Vertex Reconstruction in LHCb's GPU-Resident HLT1 Akar, Simon Elashri, Mohamed Henderson, Conor Sokoloff, Michael High Energy Physics - Experiment LHCb's Run 3 upgrade introduced a fully software-based trigger system operating at 30~MHz, processing an average of 5.6 proton-proton collision vertices per bunch crossing (event). This work presents the development of an inference engine for PVFinder, a hybrid deep neural network for finding primary vertices, the proton-proton collision points from which all subsequent particle decays originate into Allen, LHCb's High Level Trigger (HLT1) framework. The integration addresses critical real-time constraints including fixed memory pools, single-stream execution, and sub-400~$μ$s per-event processing budgets on NVIDIA GPUs. We introduce a translation layer that bridges Allen's Structure-of-Arrays (SoA) data layout with cuDNN's tensor format while maintaining zero-copy semantics and deterministic behavior. Current performance shows the CNN stage contributes significant throughput overhead. We present a roadmap targeting order-of-magnitude improvements through mixed-precision computing, model compression and other techniques. |
| title | Deploying a Hybrid PVFinder Algorithm for Primary Vertex Reconstruction in LHCb's GPU-Resident HLT1 |
| topic | High Energy Physics - Experiment |
| url | https://arxiv.org/abs/2602.19959 |