Fix non-blocking communication for adaptive time step

[SeverinDiederichs]

This PR resolves #288.
Previously, the last rank would send the new time step to the first rank. However, because the first rank is n_rank_z time steps ahead of the last rank, the last rank needs to send the data only if its time step is below max_step - n_rank_z - 1.

With this fix, the warning from #288 disappears.

Additionally, the non-blocking send is finished in the next time step and not in the + n_rank_z time step.

• Small enough (< few 100s of lines), otherwise it should probably be split into smaller PRs
• Tested (describe the tests in the PR description)
• Runs on GPU (basic: the code compiles and run well with the new module)
• Contains an automated test (checksum and/or comparison with theory)
• Documented: all elements (classes and their members, functions, namespaces, etc.) are documented
• Constified (All that can be const is const)
• Code is clean (no unwanted comments, )
• Style and code conventions are respected at the bottom of https://github.com/Hi-PACE/hipace
• Proper label and GitHub project, if applicable

[MaxThevenet]

Looks good to me, thanks!