# Process Serialization Efficiency

The Process Serialisation Efficiency describes any loss of efficiency due to MPI dependencies causing processes to wait.

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:

$Process Serialization Efficiency = 1 - \frac{Total Runtime On Ideal Network - Maximum Computation Time}{Total Runtime}$

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