Optimized collectives for PGAS languages with one-sided communication (Poster)
Optimized collective operations are a crucial performance factor for many scientific applications. This work investigates the design and optimization of collectives in the context of Partitioned Global Address Space (PGAS) languages such as Unified Parallel C (UPC). Languages with one-sided communication permit a more flexible and expressive collective interface with application code, in turn enabling more aggressive optimization and more effective utilization of system resources. We investigate the design tradeoffs in a collectives implementation for UPC, ranging from resource management to synchronization mechanisms and target-dependent selection of optimal communication patterns. Our collectives are implemented in the Berkeley UPC compiler using the GASNet communication system, tuned across a wide variety of supercomputing platforms, and benchmarked against MPI collectives. Special emphasis is placed on the newly added Cray XT3 backend for UPC, whose characteristics are benchmarked in detail.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
- DOE Contract Number:
- AC02-05CH11231
- OSTI ID:
- 1511298
- Country of Publication:
- United States
- Language:
- English
Similar Records
Porting GASNet to Portals: Partitioned Global Address Space (PGAS) Language Support for the Cray XT
Scaling communication-intensive applications on BlueGene/P using one-sided communication and overlap
Tuning collective communication for Partitioned Global Address Space programming models
Conference
·
Mon May 04 00:00:00 EDT 2009
·
OSTI ID:1407075
Scaling communication-intensive applications on BlueGene/P using one-sided communication and overlap
Conference
·
Fri Jul 10 00:00:00 EDT 2009
·
OSTI ID:1407080
Tuning collective communication for Partitioned Global Address Space programming models
Journal Article
·
Sat Jun 11 20:00:00 EDT 2011
· Parallel Computing
·
OSTI ID:1407106