Accelerating the Particle-In-Cell code ECsim with OpenACC
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914402284863488 |
|---|---|
| author | Boella, Elisabetta Shukla, Nitin Spiga, Filippo Chimeh, Mozhgan Kabiri Bettencourt, Matt Innocenti, Maria Elena |
| author_facet | Boella, Elisabetta Shukla, Nitin Spiga, Filippo Chimeh, Mozhgan Kabiri Bettencourt, Matt Innocenti, Maria Elena |
| contents | The Particle-In-Cell (PIC) method is a computational technique widely used in plasma physics to model plasmas at the kinetic level. In this work, we present our effort to prepare the semi-implicit energy-conserving PIC code ECsim for exascale architectures. To achieve this, we adopted a pragma-based acceleration strategy using OpenACC, which enables high performance while requiring minimal code restructuring. On the pre-exascale Leonardo system, the accelerated code achieves a $5 \times$ speedup and a $3 \times$ reduction in energy consumption compared to the CPU reference code. Performance comparisons across multiple NVIDIA GPU generations show substantial benefits from the GH200 unified memory architecture. Finally, strong and weak scaling tests on Leonardo demonstrate efficiency of $70 \%$ and $78 \%$ up to 64 and 1024 GPUs, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16624 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Accelerating the Particle-In-Cell code ECsim with OpenACC Boella, Elisabetta Shukla, Nitin Spiga, Filippo Chimeh, Mozhgan Kabiri Bettencourt, Matt Innocenti, Maria Elena Plasma Physics Distributed, Parallel, and Cluster Computing The Particle-In-Cell (PIC) method is a computational technique widely used in plasma physics to model plasmas at the kinetic level. In this work, we present our effort to prepare the semi-implicit energy-conserving PIC code ECsim for exascale architectures. To achieve this, we adopted a pragma-based acceleration strategy using OpenACC, which enables high performance while requiring minimal code restructuring. On the pre-exascale Leonardo system, the accelerated code achieves a $5 \times$ speedup and a $3 \times$ reduction in energy consumption compared to the CPU reference code. Performance comparisons across multiple NVIDIA GPU generations show substantial benefits from the GH200 unified memory architecture. Finally, strong and weak scaling tests on Leonardo demonstrate efficiency of $70 \%$ and $78 \%$ up to 64 and 1024 GPUs, respectively. |
| title | Accelerating the Particle-In-Cell code ECsim with OpenACC |
| topic | Plasma Physics Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2603.16624 |