Persistent and Partitioned MPI for Stencil Communication
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908494279475200 |
|---|---|
| author | Collom, Gerald Burmark, Jason Pearce, Olga Bienz, Amanda |
| author_facet | Collom, Gerald Burmark, Jason Pearce, Olga Bienz, Amanda |
| contents | Many parallel applications rely on iterative stencil operations, whose performance are dominated by communication costs at large scales. Several MPI optimizations, such as persistent and partitioned communication, reduce overheads and improve communication efficiency through amortized setup costs and reduced synchronization of threaded sends. This paper presents the performance of stencil communication in the Comb benchmarking suite when using non blocking, persistent, and partitioned communication routines. The impact of each optimization is analyzed at various scales. Further, the paper presents an analysis of the impact of process count, thread count, and message size on partitioned communication routines. Measured timings show that persistent MPI communication can provide a speedup of up to 37% over the baseline MPI communication, and partitioned MPI communication can provide a speedup of up to 68%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13370 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Persistent and Partitioned MPI for Stencil Communication Collom, Gerald Burmark, Jason Pearce, Olga Bienz, Amanda Distributed, Parallel, and Cluster Computing Many parallel applications rely on iterative stencil operations, whose performance are dominated by communication costs at large scales. Several MPI optimizations, such as persistent and partitioned communication, reduce overheads and improve communication efficiency through amortized setup costs and reduced synchronization of threaded sends. This paper presents the performance of stencil communication in the Comb benchmarking suite when using non blocking, persistent, and partitioned communication routines. The impact of each optimization is analyzed at various scales. Further, the paper presents an analysis of the impact of process count, thread count, and message size on partitioned communication routines. Measured timings show that persistent MPI communication can provide a speedup of up to 37% over the baseline MPI communication, and partitioned MPI communication can provide a speedup of up to 68%. |
| title | Persistent and Partitioned MPI for Stencil Communication |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2508.13370 |