HUNTing the Overlap
Hiding communication latency is an important optimization for parallel programs. Programmers or compilers achieve this by using non-blocking communication primitives and overlapping communication with computation or other communication operations. Using non-blocking communication raises two issues: performance and programmability. In terms of performance, optimizers need to find a good communication schedule and are sometimes constrained by lack of full application knowledge. In terms of programmability, efficiently managing non-blocking communication can prove cumbersome for complex applications. In this paper we present the design principles of HUNT, a runtime system designed to search and exploit some of the available overlap present at execution time in UPC programs. Using virtual memory support, our runtime implements demand-driven synchronization for data involved in communication operations. It also employs message decomposition and scheduling heuristics to transparently improve the non-blocking behavior of applications. We provide a user level implementation of HUNT on a variety of modern high performance computing systems. Results indicate that our approach is successful in finding some of the overlap available at execution time. While system and application characteristics influence performance, perhaps the determining factor is the time taken by the CPU to execute a signal handler. Demand driven synchronization at execution time eliminates the need for the explicit management of non-blocking communication. Besides increasing programmer productivity, this feature also simplifies compiler analysis for communication optimizations.
- Research Organization:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Director, Office of Science
- DOE Contract Number:
- DE-AC02-05CH11231
- OSTI ID:
- 891332
- Report Number(s):
- LBNL-58381; R&D Project: KWC003; BnR: 400403909; TRN: US200621%%827
- Resource Relation:
- Conference: The Fourteenth International Conference onParallel Architectures and Compilation Techniques, Saint Louis, MO,09/19/05-09/22/05
- Country of Publication:
- United States
- Language:
- English
Similar Records
Global Arrays Parallel Programming Toolkit
HPC-Colony: Services and Interfaces to Aupport Systems With Very Large Numbers of Processors