1–2 de junio de 2026
Edificio Histórico de la Universidad de Oviedo
Europe/Madrid zona horaria

FPGA-Aware Graph Neural Networks for the CMS Phase-2 Muon Trigger

1 jun 2026, 9:45
15m
Aula Escalonada (Edificio Histórico de la Universidad de Oviedo)

Aula Escalonada

Edificio Histórico de la Universidad de Oviedo

Ponente

Santiago Folgueras (Universidad de Oviedo)

Descripción

Real-time event reconstruction at the HL-LHC demands machine-learning algorithms that fit strict FPGA latency, resource, and throughput budgets, motivating a co-design between model architecture and firmware implementation. We present an FPGA-aware Graph Neural Network targeting the CMS Overlap Muon Track Finder (OMTF), exploring quantisation schemes from float32 down to INT8-PO2 together with fixed-size graph representations and latency-driven structural choices on AMD/Xilinx platforms. To make these designs reproducible and integration-ready, we introduce ARC, a plugin-agnostic, contract-driven framework that generates DUTs from interface YAMLs, orchestrates HLS, and provides a reusable verification runtime shared across algorithm variants. The combined flow shows that ML exploration and rigorous interface verification can co-evolve, replacing fragile ad-hoc testbenches with regression-friendly, contract-bound artefacts. Resulting GNN configurations meet L1-trigger-compatible resource and latency budgets, charting a viable path toward ML-based track-finding in the CMS Phase-2 trigger system.

Autor

Sr. Pelayo Leguina López (ICTEA- Universidad de Oviedo)

Coautor

Santiago Folgueras (Universidad de Oviedo)

Materiales de la presentación