Speaker
Sergo Jindariani
(Fermilab)
Description
Machine learning is becoming ubiquitous across HEP. There is great potential to improve trigger and DAQ performance, and potentially in other real-time controls applications. 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 current applications in HEP experiments and future applications. We also report on recent progress in the past year on newer neural network architectures such as binary and ternary networks; models with orders of magnitude more parameters; and exploration of more HLS vendor tools.
Primary author
Sergo Jindariani
(Fermilab)
