Skip to yearly menu bar Skip to main content

Workshop: NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences

Ultra Fast Transformers on FPGAs for Particle Physics Experiments

Zhixing Jiang · Ziang Yin · Elham E Khoda · Vladimir Loncar · Ekaterina Govorkova · Eric Moreno · Philip Harris · Scott Hauck · Shih-chieh Hsu


This work introduces a highly efficient implementation of the transformer architecture on a Field-Programmable Gate Array (FPGA) by using the hls4ml tool. Given the demonstrated effectiveness of transformer models in addressing a wide range of problems, their application in experimental triggers within particle physics becomes a subject of significant interest. In this work, we have implemented critical components of a transformer model, such as multi-head attention and softmax layers. To evaluate the effectiveness of our implementation, we have focused on a particle physics jet flavor tagging problem, employing a public dataset. We recorded latency under 2 microseconds on the Xilinx UltraScale+ FPGA, which is compatible with hardware trigger requirements at the CERN Large Hadron Collider experiments.

Chat is not available.