PulseAugur
EN
LIVE 06:48:22

New hls4ml backend enables ML on radiation-hard FPGAs for physics experiments

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a new backend for the hls4ml tool, enabling the use of machine learning models on radiation-hard FPGAs. This advancement is demonstrated through a lightweight autoencoder designed for the PicoCal calorimeter in the LHCb Upgrade II experiment. The system achieves a latency of 25 ns and utilizes minimal FPGA resources, paving the way for ML applications in high-radiation environments. AI

IMPACT Enables low-latency ML inference in extreme environments, potentially accelerating scientific discovery in high-energy physics.

RANK_REASON The cluster describes a research paper detailing a new technical contribution to an existing tool (hls4ml) for a specific application domain (ML on radiation-hard FPGAs for high-energy physics). [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New hls4ml backend enables ML on radiation-hard FPGAs for physics experiments

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Katya Govorkova, Julian Garcia Pardinas, Vladimir Loncar, Victoria Nguyen, Sebastian Schmitt, Marco Pizzichemi, Loris Martinazzoli, Eluned Anne Smith ·

    Enabling Low-Latency Machine learning on Radiation-Hard FPGAs with hls4ml

    arXiv:2602.15751v2 Announce Type: replace-cross Abstract: This paper presents an end-to-end demonstration of a viable, ultra-fast, radiation-hard machine learning (ML) application on FPGAs, which could be used in future high-energy physics experiments. We present a three-fold con…

RELATED ENTITIES

RELATED TOPICS