From Wikipedia, the free encyclopedia
This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these template messages)(Learn how and when to remove this template message)
- is number of processors.
- is the problem size.
- is number of machine words in a packet sent over the network.
- is the latency, or time at which a processor takes to initiate a communication on a network.
- is the bandwidth, or time per machine word at which a processor can inject or receive machine words from the network.
- is the largest computation time expended on a processor.
- is the time spent in communication on the network.
This model assumes that for any subset of processors, a block permutation among the processors takes time, where is the size of the largest block.
Analysis of common parallel algorithms
- Point to point communication:
- Reduction :
- Parallel prefix:
- All to all:
- David R., Helman; David A., Bader; JaJa, Joseph (1998). "A Randomized Parallel Sorting Algorithm with an Experimental Study" (PDF). Journal of Parallel and Distributed Computing. 52: 1–23. Retrieved 26 October 2012.
- Bader, David A.; Jaja, Joseph (1996). "Practical parallel algorithms for dynamic data redistribution, median finding, and selection". Proceedings of the 10th IEEE International Parallel Processing Symposium: 292–301.