Process Transfer Efficiency

Process Transfer Efficiency considers inefficiency due to time in process MPI data transfer, i.e. ignoring MPI inside OpenMP.

If a network simulator is used to calculate runtime for process MPI on an ideal network (i.e. zero latency and infinite bandwidth) while leaving MPI inside OpenMP unchanged, then it is expressed as:

\[Process Transfer Efficiency = \frac{Total Runtime On Ideal Network}{Total Runtime On Real Network}\]

In order to fully understand the formulas, you may also visit the glossary of the metrics terms.