Reconfigurable Computing Challenge: Transformer for Jet Tagging on Versal AI Engines

Abstract:Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is challenging. We present an initial implementation of a quantized, integer-only transformer for jet tagging on the AMD Versal AI Engine (AIE), mapping dense and multi-head attention (MHA) layers to AIE tiles. The main contribution is a reusable software framework that represents transformer layers as composable AIE building blocks and automatically generates the corresponding Vitis graph code from a high-level Python model description. This framework provides a foundation for future research and is released as open-source software at this https URL.

4 pages, 4 figures. In FCCM 2026 proceedings

Machine Learning (cs.LG); Hardware Architecture (cs.AR)

arXiv:2606.17500 [cs.LG]

(or arXiv:2606.17500v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.17500 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

2026 IEEE 34th Int. Symp. on Field-Programmable Custom Computing Machines (FCCM), Atlanta, GA, USA, 2026, pp. 307-310

https://doi.org/10.1109/FCCM68464.2026.00078 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.