English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

New challenges in Astronomy and Astrophysics (AA) are urging the need for alarge number of exceptionally computationally intensive simulations. "Exascale"(and beyond) computational facilities are mandatory to address the size oftheoretical problems and data coming from the new generation of observationalfacilities in AA. Currently, the High Performance Computing (HPC) sector isundergoing a profound phase of innovation, in which the primary challenge tothe achievement of the "Exascale" is the power-consumption. The goal of thiswork is to give some insights about performance and energy footprint ofcontemporary architectures for a real astrophysical application in an HPCcontext. We use a state-of-the-art N-body application that we re-engineered andoptimized to exploit the heterogeneous underlying hardware fully. Wequantitatively evaluate the impact of computation on energy consumption whenrunning on four different platforms. Two of them represent the current HPCsystems (Intel-based and equipped with NVIDIA GPUs), one is a micro-clusterbased on ARM-MPSoC, and one is a "prototype towards Exascale" equipped withARM-MPSoCs tightly coupled with FPGAs. We investigate the behavior of thedifferent devices where the high-end GPUs excel in terms of time-to-solutionwhile MPSoC-FPGA systems outperform GPUs in power consumption. Our experiencereveals that considering FPGAs for computationally intensive application seemsvery promising, as their performance is improving to meet the requirements ofscientific applications. This work can be a reference for future platformsdevelopment for astrophysics applications where computationally intensivecalculations are required.

Performance and energy footprint assessment of FPGAs and GPUs on HPC systems using Astrophysics application