Dakota Reference Manual  Version 6.4
Large-Scale Engineering Optimization and Uncertainty Analysis
 All Pages

Specify the scheduling of concurrent iterators when Dakota is run in parallel


This keyword is related to the topics:


Alias: none

Argument(s): none

Required/Optional Description of Group Dakota Keyword Dakota Keyword Description
(Choose One)
Group 1 master Specify a dedicated master partition for parallel iterator scheduling
peer Specify a peer partition for parallel iterator scheduling


An important feature for component-based iterators is that execution of sub-iterator runs may be performed concurrently. The optional iterator_scheduling specification supports user override of the automatic parallel configuration for the number of iterator servers. That is, if the automatic configuration is undesirable for some reason, the user can enforce a desired number of partitions at the iterator parallelism level. Currently, hybrid, multi_start, and pareto_set component-based iterators support concurrency in their sub-iterators. Refer to ParallelLibrary and the Parallel Computing chapter of the Users Manual [5] for additional information.