% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Xavier:1034038,
author = {Xavier, Joseph Arnold and Pedro Gutiérrez Hermosillo
Muriedas, Juan and Nassyr, Stepan and Sedona, Rocco and
Götz, Markus and Streit, Achim and Riedel, Morris and
Cavallaro, Gabriele},
title = {{V}ectorized {H}ighly {P}arallel {D}ensity-{B}ased
{C}lustering for {A}pplications {W}ith {N}oise},
journal = {IEEE access},
volume = {12},
issn = {2169-3536},
address = {New York, NY},
publisher = {IEEE},
reportid = {FZJ-2024-06868},
pages = {181679 - 181692},
year = {2024},
abstract = {Clustering in data mining involves grouping similar objects
into categories based on their characteristics. As the
volume of data continues to grow and advancements in
high-performance computing evolve, a critical need has
emerged for algorithms that can efficiently process these
computations and exploit the various levels of parallelism
offered by modern supercomputing systems. Exploiting Single
Instruction Multiple Data (SIMD) instructions enhances
parallelism at the instruction level and minimizes data
movement within the memory hierarchy. To fully harness a
processor’s SIMD capabilities and achieve optimal
performance, adapting algorithms for better compatibility
with vector operations is necessary. In this paper, we
introduce a vectorized implementation of the Density-based
Clustering for Applications with Noise (DBSCAN) algorithm
suitable for the execution on both shared and distributed
memory systems. By leveraging SIMD, we enhance the
performance of distance computations. Our proposed
Vectorized HPDBSCAN (VHPDBSCAN) demonstrates a performance
improvement of up to two times over the state-of-the-art
parallel version, Highly Parallel DBSCAN (HPDBSCAN), on the
ARM-based A64FX processor on two different datasets with
varying dimensions. We have parallelized computations which
are essential for the efficient workload distribution. This
has significantly enhanced the performance on higher
dimensional datasets. Additionally, we evaluate
VHPDBSCAN’s energy consumption on the A64FX and Intel Xeon
processors. The results show that in both processors, due to
the reduced runtime, the total energy consumption of the
application is reduced by $50\%$ on the A64FX Central
Processing Unit (CPU) and by approximately $19\%$ on the
Intel Xeon 8368 CPU compared to HPDBSCAN.},
cin = {JSC},
ddc = {621.3},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / 5122 - Future
Computing $\&$ Big Data Systems (POF4-512) / 5112 -
Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and
Research Groups (POF4-511) / EUPEX - EUROPEAN PILOT FOR
EXASCALE (101033975) / EUROCC-2 (DEA02266)},
pid = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-5122 /
G:(DE-HGF)POF4-5112 / G:(EU-Grant)101033975 /
G:(DE-Juel-1)DEA02266},
typ = {PUB:(DE-HGF)16},
UT = {WOS:001375797900029},
doi = {10.1109/ACCESS.2024.3507193},
url = {https://juser.fz-juelich.de/record/1034038},
}