Feat/w3wave scaling

[MatthewMasarik-NOAA]

Pull Request Summary

Addresses the performance bottleneck found in subroutine W3NMIN.

Description

Provide a detailed description of what this PR does.

• Removes the bottleneck identified in W3NMIN. The body of W3NMIN is a nested loop over all processors, and all global sea points, scaling inversely as ~(NAPROC x NSEA).
• Two methods to remove this are included.
  • The first adds OMP parallel statements around the loops. This method provides no reduction when OMP threads are not used. It does retain a warning message for the case when a processor has no active seapoints. This is the only functionality currently provided by calling W3NMIN, so we have added it but hid it behind a DEBUGRUN #ifdef statement.
  • The second comments out the call to W3NMIN, completely removing the bottleneck.

Is a change of answers expected from this PR?

• No.

Please also include the following information:

• Add any suggestions for a reviewer

  • Performance gains from the 'W3NMIN' fix are shown by comparison alongside the current develop runtime
    

• Mention any labels that should be added:

  • enhancement.

• Are answer changes expected from this PR?

  • No.

• Co-authors

  • @GeorgeVandenberghe-NOAA, @JessicaMeixner-NOAA, @DeniseWorthen, @mvertens.

Issue(s) addressed

• Please list any issues associated with this PR, including those the PR will fix/close. For example:
  • Addresses WW3 scalability to meet operational runtime requirements #775, though will remain open while remaining testing completes.

Commit Message

W3NMIN bottleneck fix

Check list

• Branch is up to date with the authoritative repository (NOAA-EMC) develop branch.
• Checked the checklist for a developer submitting to develop.
• [na] If a version number update is required, checked the updating version number checklist.
• [na] If a new feature was added, a regression test for testing the new feature is added.

Testing

• How were these changes tested?

  • Full matrix run against develop.

• Are the changes covered by regression tests? (If not, why? Do new tests need to be added?)

  • No. The changes do not add a feature to be tested.

• Have the matrix regression tests been run (if yes, please note HPC and compiler)?

  • Yes. Orion / Intel.

• Please indicate the expected changes in the regression test output, (Note the list of known non-identical tests.)

  • There are no changes, except those known to be non-identical.

• Please provide the summary output of matrix.comp (matrix.Diff.txt, matrixCompFull.txt and matrixCompSummary.txt):

**********************************************************************        
********************* non-identical cases ****************************        
**********************************************************************        
mww3_test_03/./work_PR2_UQ_MPI_d2                     (15 files differ)       
mww3_test_03/./work_PR2_UNO_MPI_e                     (1 files differ)        
mww3_test_03/./work_PR2_UNO_MPI_d2                     (17 files differ)      
mww3_test_03/./work_PR3_UQ_MPI_d2                     (17 files differ)       
mww3_test_03/./work_PR3_UNO_MPI_d2_c                     (19 files differ)    
mww3_test_03/./work_PR3_UQ_MPI_d2_c                     (16 files differ)     
mww3_test_03/./work_PR1_MPI_d2                     (23 files differ)          
mww3_test_03/./work_PR3_UNO_MPI_e_c                     (1 files differ)      
mww3_test_03/./work_PR3_UQ_MPI_e_c                     (1 files differ)       
mww3_test_03/./work_PR3_UNO_MPI_d2                     (19 files differ)      
ww3_ta1/./work_UPD0F_U                     (0 files differ)                   
ww3_tp2.10/./work_MPI_OMPH                     (6 files differ)               
ww3_tp2.16/./work_MPI_OMPH                     (4 files differ)               
ww3_tp2.17/./work_ma                     (1 files differ)                     
ww3_tp2.17/./work_mc1                     (1 files differ)                    
ww3_tp2.17/./work_mc                     (1 files differ)                     
ww3_tp2.17/./work_a                     (1 files differ)                      
ww3_tp2.17/./work_b                     (1 files differ)                      
ww3_tp2.17/./work_mb                     (1 files differ)                     
ww3_tp2.17/./work_c                     (1 files differ)                      
ww3_tp2.17/./work_ma1                     (1 files differ)                    
ww3_tp2.6/./work_pdlib                     (1 files differ)                   
ww3_ufs1.3/./work_a                     (1 files differ)                                                                                              
**********************************************************************        
************************ identical cases *****************************        
**********************************************************************

• matrixDiff.txt
• matrixCompFull.txt
• matrixCompSummary.txt

[JessicaMeixner-NOAA]

matrixCompFull.txt
matrixCompSummary.txt
matrixDiff.txt