Add relative time to analyze

[davidscn]

Main changes of this PR

One idea to approach #1988

Motivation and additional information

Looks as follows

                                                                  eid |        sum    count               mean        min        max |        %
                                                              _GLOBAL | 42996789.0        1         42996789.0 42996789.0 42996789.0 |    100.0
                                                              advance |   881580.0        1           881580.0   881580.0   881580.0 |     2.05
                                              advance/m2n.receiveData |      151.0        1              151.0      151.0      151.0 |      0.0
                           advance/map.pou.mapData.FromA-MeshToB-Mesh |   850430.0        1           850430.0   850430.0   850430.0 |     1.98
                                                         construction |    11671.0        1            11671.0    11671.0    11671.0 |     0.03
                                               construction/configure |    11036.0        1            11036.0    11036.0    11036.0 |     0.03
                                   construction/startProfilingBackend |      621.0        1              621.0      621.0      621.0 |      0.0
                                                             finalize |    41010.0        1            41010.0    41010.0    41010.0 |      0.1
...

Author's checklist

• I used the pre-commit hook to prevent dirty commits and used pre-commit run --all to format old commits.
• I added a changelog file with make changelog if there are user-observable changes since the last release.
• I added a test to cover the proposed changes in our test suite.
• For breaking changes: I documented the changes in the appropriate porting guide.
• I sticked to C++17 features.
• I sticked to CMake version 3.16.3.
• I squashed / am about to squash all commits that should be seen as one.

Reviewers' checklist

• Does the changelog entry make sense? Is it formatted correctly?
• Do you understand the code changes?

[fsimonis]

If we do filter by eid followed by sort by rank, then we should have all durations we need for computing this per-rank.

Below, we would have to pl.col("dur") / global_runtime[pl.col("rank")] or similar.

For parallel participants, we can sum this relative time just like we do with dur.