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

2026-02-17

AI Summary

This work addresses the urgent need for low-latency, deployable machine learning solutions on radiation-tolerant FPGAs in high-energy physics experiments. Targeting the PicoCal calorimeter for the LHCb Upgrade II, the authors propose a lightweight autoencoder combined with a hardware-aware 10-bit fixed-point quantization strategy to efficiently compress 32-sample temporal signals. By extending the hls4ml toolchain, they provide the first automated deployment support for Microchip PolarFire radiation-tolerant FPGAs. The implementation achieves a 25-nanosecond inference latency on PolarFire with minimal resource utilization, fitting within the FPGA’s built-in protected logic regions. This demonstrates the feasibility of deploying machine learning in high-radiation environments and fills a critical gap in ML deployment tools for radiation-tolerant FPGAs in high-energy physics.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

This paper presents the first 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 contribution, with the PicoCal calorimeter, planned for the LHCb Upgrade II experiment, used as a test case. First, we develop a lightweight autoencoder to compress a 32-sample timing readout, representative of that of the PicoCal, into a two-dimensional latent space. Second, we introduce a systematic, hardware-aware quantization strategy and show that the model can be reduced to 10-bit weights with minimal performance loss. Third, as a barrier to the adoption of on-detector ML is the lack of support for radiation-hard FPGAs in the High-Energy Physics community's standard ML synthesis tool, hls4ml, we develop a new backend for this library. This new back-end enables the automatic translation of ML models into High-Level Synthesis (HLS) projects for the Microchip PolarFire family of FPGAs, one of the few commercially available and radiation hard FPGAs. We present the synthesis of the autoencoder on a target PolarFire FPGA, which indicates that a latency of 25 ns can be achieved. We show that the resources utilized are low enough that the model can be placed within the inherently protected logic of the FPGA. Our extension to hls4ml is a significant contribution, paving the way for broader adoption of ML on FPGAs in high-radiation environments.

Problem

• radiation-hard FPGAs
• low-latency machine learning
• high-energy physics
• on-detector ML
• hls4ml

Innovation

• radiation-hard FPGA
• hls4ml
• hardware-aware quantization
• low-latency ML
• autoencoder