Bug fix for FMS2 issue #761, broadcast from root pe

[nikizadehgfdl]

• This addresses the FMS issue $761
  FMS2+MOM6 model crashes during restart with mpich errors NOAA-GFDL/FMS#761

• There is a mpp_broadcast in the FMS2 subroutine
  get_unlimited_dimension_name() and this subroutine has to be called by
  all pes, so it cannot be inside a if(is_root_pe()) block

[codecov]

Codecov Report

Merging #1462 (d0ab103) into dev/gfdl (77175fe) will increase coverage by 0.00%.
The diff coverage is 0.00%.

❗ Current head d0ab103 differs from pull request most recent head 3223bba. Consider uploading reports for the commit 3223bba to get more accurate results

@@            Coverage Diff            @@
##           dev/gfdl    #1462   +/-   ##
=========================================
  Coverage     29.13%   29.13%           
=========================================
  Files           235      235           
  Lines         71039    71038    -1     
=========================================
  Hits          20694    20694           
+ Misses        50345    50344    -1     

Impacted Files	Coverage Δ
src/framework/MOM_restart.F90	26.00% <0.00%> (+0.03%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 77175fe...3223bba. Read the comment docs.

[Hallberg-NOAA]

Although I agree that this PR fixes a problem that was introduced by FMS2, I think that we do not want any processors apart from the root PE issuing any warning messages, so that we are not deluged with a flood of redundant messages. Please add a second expression to the logical test that is now on line 1102, so that it reads if ((t1 /= t2) .and. is_root_PE()) then, to avoid excessive numbers of warnings.

[marshallward]

Gaea regression: https://gitlab.gfdl.noaa.gov/ogrp/MOM6/-/pipelines/13336 ✔️