| Issue |
EPJ Web Conf.
Volume 337, 2025
27th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2024)
|
|
|---|---|---|
| Article Number | 01166 | |
| Number of page(s) | 8 | |
| DOI | https://doi.org/10.1051/epjconf/202533701166 | |
| Published online | 07 October 2025 | |
https://doi.org/10.1051/epjconf/202533701166
Versal ACAP processing for ATLAS-TileCal signal reconstruction
Instituto de Física Corpuscular (CSIC-UV), catedràtic José Beltran 2, Paterna, València, Spain
* e-mail: fran.hervas@ific.uv.es
Published online: 7 October 2025
Particle detectors at accelerators generate a large amount of data, requiring analysis to derive insights. Collisions lead to signal pile-up, where multiple particles produce signals in the same detector sensors, complicating individual signal identification. This contribution describes the implementation of a deep learning algorithm on a Versal Adaptive Compute Acceleration Platform (ACAP) device for improved processing via parallelization and concurrency. The system will emulate the real conditions in the ATLAS Tile Calorimeter signal reconstruction module. Connected to a host computer via Peripheral Component Interconnect express (PCIe), this system aims for enhanced speed and energy efficiency over Central Processing Units (CPUs) and Graphics Processing Units (GPUs). In the contribution, we will describe in detail the data processing and the hardware, firmware and software components of the system, as well as the implementation of the deep learning algorithm on Versal ACAP device, and the system for transferring data in an efficient way.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.