A part of large-scale future supercomputing architectures will rely on a combination of IBM POWER9 and Nvidia GPU processors. In order to anticipate software design, implementation and optimization decisions and optimally prepare scientific applications targetting exascale computing, it is mandatory to already analyze application performance on prototype hardware. In this article an evaluation of the performance of the IBM POWER8 system is provided in the context of a widely-used computational neuroscientific application modeling large-scale neuronal network and using detailed morphologies referred as NEURON. This evaluation describes in details the way to accurately model the performance of the system but also provides a first detailed analysis of representative kernels of NEURON. From this analysis, optimization opportunities can be suggested at the level of the application but also at the level of the performance measurement and system setup.