Mapping of data between non-matching meshes is a key ingredient of multi-physics simulations. Black-box data mapping, which only operates on clouds of mesh vertices without connectivity, enables modular software environments. We recently developed such a black-box approach that is capable of handling very large data sets on parallel systems. More precisely, we implemented partition-of-unity radial-basis-function interpolation into the coupling library preCICE. The method tackles the data mapping problem by decomposing it into smaller, independent subproblems, which makes it well-suited for parallel computing. Tests on real-world geometries showed that the method is scalable and orders of magnitude more efficient than previous data mapping in preCICE. Consequently, the implementation greatly extends the applicability of preCICE, benefiting the library's large user community.