Local search to improve coordinate-based task mapping
- Washington Univ., St. Louis, MO (United States)
- Knox College, Galesburg, IL (United States)
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
We present a local search strategy to improve the coordinate-based mapping of a parallel job’s tasks to the MPI ranks of its parallel allocation in order to reduce network congestion and the job’s communication time. The goal is to reduce the number of network hops between communicating pairs of ranks. Our target is applications with a nearest-neighbor stencil communication pattern running on mesh systems with non-contiguous processor allocation, such as Cray XE and XK Systems. Utilizing the miniGhost mini-app, which models the shock physics application CTH, we demonstrate that our strategy reduces application running time while also reducing the runtime variability. Furthermore, we further show that mapping quality can vary based on the selected allocation algorithm, even between allocation algorithms of similar apparent quality.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- AC04-94AL85000; 899808
- OSTI ID:
- 1238587
- Alternate ID(s):
- OSTI ID: 1251777
- Report Number(s):
- SAND-2015-8243J; PII: S0167819115001441
- Journal Information:
- Parallel Computing, Vol. 51, Issue C; ISSN 0167-8191
- Publisher:
- ElsevierCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
On the effects of allocation strategies for exascale computing systems with distributed storage and unified interconnects
|
journal | July 2018 |
Similar Records
Exploiting Geometric Partitioning in Task Mapping for Parallel Computes
Task mapping for non-contiguous allocations.