Parallelized Event Data Management System Based on MT-SNiPER Framework and PODIO

TL;DR

This paper introduces a parallelized event data management system based on MT-SNiPER and PODIO, enhancing data processing efficiency for large-scale high energy physics experiments.

Contribution

It presents the design and implementation of a parallelized event data management system integrating MT-SNiPER and PODIO for improved performance in HEP data processing.

Findings

System supports efficient multi-threaded event processing

Performance evaluation shows improved data handling efficiency

Successfully integrated with OSCAR software for HEP experiments

Abstract

Software framework serves as a skeleton for the offline data processing software for many high energy physics (HEP) experiments. The event data management, including the event data model (EDM), transient event store and data input/output, implements the core functionalities of the framework, and has a great impact on the performance of the entire offline software. Future HEP experiments are generating increasingly large amounts of data, bringing challenges to offline data processing. To address this issue, a common event data management system that supports efficient parallelized data processing applications has been developed based on SNiPER (Software for Non-collider Physics ExpeRiments) common software framework as well as PODIO, a common EDM toolkit for future HEP experiments. In this paper, the implementation of a parallelized event data management (PEDM) system is introduced, including the integration with MT-SNiPER and PODIO, as well as the implementation of GlobalStore to support multi-threaded event processing. Finally, the application and performance evaluation of the data management system in OSCAR (offline software of Super Tau Charm Facility) is presented.