Dec 9 – 11, 2018
Rhode Island Convention Center
US/Eastern timezone

Deep Machine Learning on FPGAs for L1 trigger and Data Acquisition

Dec 10, 2018, 3:00 PM
Rhode Island Convention Center

Rhode Island Convention Center

One Sabin Street Providence, Rhode Island 02903 United States


Dylan Rankin (MIT)


Machine learning is becoming ubiquitous across HEP. There is great potential to improve trigger and DAQ performances with it. However, the exploration of such techniques within the field in low latency/power FPGAs has just begun. We present HLS4ML, a user-friendly software, based on High-Level Synthesis (HLS), designed to deploy network architectures on FPGAs. As a case study, we use HLS4ML for boosted-jet tagging with deep networks at the LHC. We map out resource usage and latency versus network architectures, to identify the typical problem complexity that HLS4ML could deal with. We discuss possible applications in current and future HEP experiments.

Primary author

Dylan Rankin (MIT)


Sergo Jindariani (FNAL)

Presentation materials