...
Notes from Patrick Worley (Unlicensed) on interpreting timings in case_scripts/timing/CESM_timing.rs.* (communicated from email by Peter Caldwell): CESM_timing.rs files include output like the following:
TOT Run Time: 685.744 seconds 68.574 seconds/mday 3.45 myears/wday
LND Run Time: 13.492 seconds 1.349 seconds/mday 175.45 myears/wday
ROF Run Time: 4.397 seconds 0.440 seconds/mday 538.35 myears/wday
ICE Run Time: 136.503 seconds 13.650 seconds/mday 17.34 myears/wday
ATM Run Time: 438.496 seconds 43.850 seconds/mday 5.40 myears/wday
OCN Run Time: 336.464 seconds 33.646 seconds/mday 7.04 myears/wday
GLC Run Time: 0.000 seconds 0.000 seconds/mday 0.00 myears/wday
WAV Run Time: 0.000 seconds 0.000 seconds/mday 0.00 myears/wday
CPL Run Time: 80.499 seconds 8.050 seconds/mday 29.41 myears/wday
CPL COMM Time: 599.469 seconds 59.947 seconds/mday 3.95 myears/wday
For layouts like the one above (with OCN running in parallel from everything else and ICE and LND running in parallel on the same cores used for ATM), Pat computes max (OCN, ATM + max(LND, ICE)) and compares it to the "TOT Run Time". The difference between these numbers is the amount of time spent in communication overhead. "CPL COMM Time" is kind of useless because it can include load imbalance from components that finish early (smaller "CPL COMM TIme" means better load balancing). CPL Run Time is also unpredictable because it includes MPI communication and may depend on which nodes CPL is running on.
...