| Issue |
EPJ Web of Conf.
Volume 295, 2024
26th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2023)
|
|
|---|---|---|
| Article Number | 02002 | |
| Number of page(s) | 6 | |
| Section | Online Computing | |
| DOI | https://doi.org/10.1051/epjconf/202429502002 | |
| Published online | 06 May 2024 | |
https://doi.org/10.1051/epjconf/202429502002
A vendor-unlocked ITS GPU reconstruction in ALICE
CERN
* e-mail: matteo.concas@cern.ch
Published online: 6 May 2024
In LHC Run 3, ALICE experiment’s upgrades enable recording Pb-Pb collisions at a 50 kHz rate using trigger-less continuous readout, managing a peak data rate of 1 TB/s primarily through GPU utilization. Two main phases of data processing exist: the synchronous phase, focused on TPC reconstruction consuming most computing resources, and the asynchronous phase with more GPU resources available. The Inner Tracking System (ITS) has been successfully ported to GPUs for primary vertex finding and track reconstruction, leveraging automatic code generation to support multiple GPU brands with a single code base. This work not only enhances ALICE’s computational capability but also sets a precedent for offloading reconstruction tasks to GPUs in other detectors.
© The Authors, published by EDP Sciences, 2024
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.