Machine learning evaluation in the Global Event Processor FPGA for the ATLAS trigger upgrade

TL;DR

This paper demonstrates how machine learning algorithms can be automatically generated and deployed within the FPGA-based Global Event Processor of the ATLAS experiment, significantly enhancing real-time event filtering performance.

Contribution

It introduces methods to automatically create machine learning algorithms for FPGA deployment in high-energy physics, achieving low latency and resource-efficient implementations.

Findings

ML algorithms achieved latency of 1.2 microseconds

Resource utilization was less than 5% on Xilinx FPGA

Successful deployment within the GEP system demonstrated improved filtering performance

Abstract

The Global Event Processor (GEP) FPGA is an area-constrained, performance-critical element of the Large Hadron Collider's (LHC) ATLAS experiment. It needs to very quickly determine which small fraction of detected events should be retained for further processing, and which other events will be discarded. This system involves a large number of individual processing tasks, brought together within the overall Algorithm Processing Platform (APP), to make filtering decisions at an overall latency of no more than 8ms. Currently, such filtering tasks are hand-coded implementations of standard deterministic signal processing tasks. In this paper we present methods to automatically create machine learning based algorithms for use within the APP framework, and demonstrate several successful such deployments. We leverage existing machine learning to FPGA flows such as hls4ml and fwX to significantly reduce the complexity of algorithm design. These have resulted in implementations of various machine learning algorithms with latencies of 1.2us and less than 5% resource utilization on an Xilinx XCVU9P FPGA. Finally, we implement these algorithms into the GEP system and present their actual performance. Our work shows the potential of using machine learning in the GEP for high-energy physics applications. This can significantly improve the performance of the trigger system and enable the ATLAS experiment to collect more data and make more discoveries. The architecture and approach presented in this paper can also be applied to other applications that require real-time processing of large volumes of data.