Parallel multithreaded deduplication of data sequences in nuclear structure calculations

0573716 - ÚJF 2025 RIV GB eng J - Journal Article
Langr, D. - Dytrych, Tomáš
Parallel multithreaded deduplication of data sequences in nuclear structure calculations.
International Journal of High Performance Computing Applications. Roč. 38, č. 1 (2024), s. 5-16. ISSN 1094-3420. E-ISSN 1741-2846
R&D Projects: GA ČR(CZ) GA22-14497S
Research Infrastructure: e-INFRA CZ II - 90254
Institutional support: RVO:61389005
Keywords : Data sequences * deduplication * multithreading * nuclear structure * parallel algorithm * symmetry-adapted no-core shell model * unique sequences
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 3.1, year: 2022
Method of publishing: Limited access
https://doi.org/10.1177/10943420231183697

High performance computing (HPC) applications that work with redundant sequences of data can benefit from their deduplication. We study this problem on the symmetry-adapted no-core shell model (SA-NCSM), where redundant sequences of different kinds naturally emerge in the data of the basis of the Hilbert space physically relevant to a modeled nucleus. For a fast solution of this problem on multicore architectures, we propose and present three multithreaded algorithms, which employ either concurrent hash tables or parallel sorting methods. Furthermore, we present evaluation and comparison of these algorithms based on experiments performed with real-world SA-NCSM calculations. The results indicate that the fastest option is to use a concurrent hash table, provided that it supports sequences of data as a type of table keys. If such a hash table is not available, the algorithm based on parallel sorting is a viable alternative.
Permanent Link: https://hdl.handle.net/11104/0349724