The kernels selected from NPB were set up and executed with 4, 8, 16, 32, 64, and 256 processes in a multiprocessor cluster in order to record communication information during execution (sender node, destination node, timestamp, type of transmission, etc).
Therefore, for this scenario, we can expect a minimum of conflicts between the concurrent processes, which means that we do not need to consider any process communication during the execution of a library routine.
Finally, tight coupled applications are characterized by the synchronous operation of systems, allowing direct inter-system communication during program execution.
Multi component approach uses DVFS to reduce power consumption of CPU during communication, execution and computation phases.
However, this is not always possible in practice, due to scalability limitations in applications, communication limitations generated by programs during execution, and network restrictions.
There is usually a very small amount of data communication between the modules, increasing the parallelism during execution.
Data management has to be taken into consideration before data capture, during execution of protocols and during analysis and communication of results.
BfsEnumP1-2 stassignly assign tasks to processors without communication between processors during the construction of a family tree, whereas BfsEnumP3 dynamically makes the assignment depending on computational environment during execution.
allows rate changes in actors during execution.
when during execution reconfiguration can occur.
To provide feedback information during execution, specify a periodic-renderer.
