Bit Level Data Unpacking Using Heterogeneous Architecture Setups

Momed, Mohammad; Buschmann, Malte; Wissing, Christoph; Neumann, Philipp; Blekman, Freya

doi:10.1007/978-3-032-29912-3_43

Contribution to a conference proceedings/Contribution to a book

PUBDB-2026-00778

Bit Level Data Unpacking Using Heterogeneous Architecture Setups

Momed, M. (Corresponding author)DESY* ; Blekman, F.Extern*DESY* ; Buschmann, M.DESY* ; Wissing, C.DESY* ; Neumann, P.Extern*DESY*

2026
Springer Nature Switzerland Cham
ISBN: 978-3-032-29921-5, 978-3-032-29912-3 (electronic)

Computational Science – ICCS 2026 Workshops / Paszynski, Maciej (Editor) [https://orcid.org/0000-0001-7766-6052] ; Cham : Springer Nature Switzerland, 2026, Chapter 43 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-032-29911-6=978-3-032-29912-3 ; doi:10.1007/978-3-032-29912-3
26th International Conference on Computational Science, ICCS2026, Hamburg, Germany, 29 Jun 2026 - 1 Jul 2026 Cham : Springer Nature Switzerland, Lecture Notes in Computer Science 16786, : 1st, 13 (2026) [10.1007/978-3-032-29912-3_43]

This record in other databases:

Please use a persistent id in citations: doi:10.1007/978-3-032-29912-3_43

Abstract: Modern high-performance computing centers increasingly opt for heterogeneous system designs, integrating general-purpose computing cores with accelerators, to deliver high computing performance and high efficiency. Scientific computing codes need to adapt to this change in cluster architecture, which introduces the challenge of hardware portability. In the following, we introduce a hardware portable code for the implementation of a data unpacking algorithm, a key part of the data processing system for particle detector readout systems, in the environment provided by the C++ abstraction framework with the header-only Alapka library. This concept has great relevance for the international high-energy physics research at CERN, where different computer accelerators from diverse vendors are used. This code is portable to CUDA, HIP, OpenMP, and serial code, requiring no tailoring to a specific platform. We validate the approach using the high-throughput data processing requirements of the CMS experiment at CERN and verify the conservative, lossless nature of the given data unpacking procedure. The performance improvement using heterogeneous hardware exceeds 32 times in average throughput for the single-threaded case.

Contributing Institute(s):

Research Program(s):