% 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”.
@INPROCEEDINGS{Bartolomeu:1041259,
author = {Bartolomeu, Rodrigo and Halver, Rene and Meinke, Jan and
Sutmann, Godehard},
title = {{A}ssessing the {P}erformance of {P}ortable {P}rogramming
{M}odels {A}cross {GPU} {V}endors for the {N}-{B}ody
{P}roblem},
volume = {15580},
address = {Cham},
publisher = {Springer Nature Switzerland},
reportid = {FZJ-2025-02193},
isbn = {978-3-031-85700-3},
series = {Lecture Notes in Computer Science},
pages = {119-133},
year = {2025},
comment = {Parallel Processing and Applied Mathematics},
booktitle = {Parallel Processing and Applied
Mathematics},
abstract = {With the inclusion of Aurora in the TOP500 list in November
2023 three different GPU (Graphics Processing Unit) vendors
are represented in the top 10 of the list. Each vendor has
its own preferred model for programming GPUs. For this paper
we implemented the N-body problem using portable programming
frameworks and the vendors’ preferred APIs. We show how
the performance of the portable solutions compares to the
performance of the native solution on each hardware both in
absolute numbers and as fraction of the achievable peak
performance.},
month = {Sep},
date = {2024-09-08},
organization = {Parallel Processing and Applied
Mathematics, Ostrava (Czech Republic),
8 Sep 2024 - 11 Sep 2024},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / MultiXscale - Centre
of Excellence in exascale-oriented application co-design and
delivery for multiscale simulations (101093169)},
pid = {G:(DE-HGF)POF4-5111 / G:(EU-Grant)101093169},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
UT = {WOS:001529693300009},
doi = {10.1007/978-3-031-85700-3_9},
url = {https://juser.fz-juelich.de/record/1041259},
}