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

Gram Koski; Sean Lipps; Zhenghua Ma; G. Abarajithan; Ryan Kastner

cs.LGJun 16, 2026

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

Authors: Gram Koski, Sean Lipps, Zhenghua Ma, G. Abarajithan, Ryan Kastner

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 https://github.com/KastnerRG/particle_transformer_aie.

Explore similar work

Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging
May 20, 2026Aaron Wang, Zihan Zhao, Alan Xia +5High Energy Physics Transformer Attention
HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction
Jun 18, 2026Siqi Miao, Shitij Govil, Jack P. Rodgers +5High Energy Physics Heterogeneous Graph Transformers
Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Survey
Sep 1, 2026Arjan Blankestijn, Uraz Odyurt, Amirreza YousefzadehField-Programmable Gate Arrays Accelerator

May 20, 2026 · hep-exJ/K move · Enter open · S save

Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging

Aaron Wang, Zihan Zhao, Alan Xia, Chang Sun+4

Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems responsible for deciding which collision events to store impose strict latency and accuracy constraints. While transformer architectures achieve the highest jet tagging accuracy when compute is unconstrained, their quadratic self-attention cost makes inference restrictive on trigger budget. Existing efficient variants reduce the computational cost, but hinder the classification performance. To address this limitation, we introduce the Patch Hierarchical Attention Transformer (PHAT-JeT), which combines two mechanisms: a physics-inspired geometric message-passing module that encodes local detector-plane structure, and a hierarchical patch-based attention scheme that computes exact attention within small particle groups while preserving global context through lightweight patch-token communication. Within a restricted budget, PHAT-JeT achieves state-of-the-art accuracy and background rejection among all resource-constrained jet tagging models on four benchmarks (\textsc{hls4ml}, JetClass, Top Tagging, and Quark--Gluon). Our code is available at https://github.com/aaronw5/PHAT-JeT.

High Energy Physics Transformer Attention Transformer Architectures Message Passing Neural Networks

Open paper Ask about it PDF

Abstract

Explore similar work

Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

Recent Developments in Transformer Inference Deployment on FPGA Platforms: A Survey