Azamat Mametjanov

Can the length of `ERS.ne30pg2_r05_EC30to60E2r2.GPMPAS-JRA.mosart-rof_ocn_2way` be reduced from the default 11+5 days (Ld11) to Ld3 or shorter?

Yes, on Crusher with gnu running on 1 node with 64 MPI tasks: times out after 1 hour of wall-time. We can add a 2- or 4-node pelayout to make...

Okay. Cori-knl was also timing out of 45 min wall-time with 512 tasks on 8 nodes. E3SM-Project/E3SM#5156 lets it complete in 25 mins on 30 nodes. E3SM-Project/E3SM#5164 adds more nodes...

`corrupted size vs. prev_size` usually occurs when running out-of-memory: can you try increasing `OMP_STACKSIZE` from 128M to 256M or run in pure-MPI 128x1 (NTHRDS=1, MAX_MPITASKS_PER_NODE=128) instead of 64x2?

This latest backtrace is identical to what @whannah1 has been getting on Summit with `whannah/mmf/KPP-dev` branch and ``` -compset WCYCL1950-MMF1 -res ne120pg2_r0125_oRRS18to6v3 -compiler gnugpu -pecount 1536x7 ``` Since the error...

Just to document: - for runs with GNU, reprosum NaNs went away after adding `-fno-inline-arg-packing` to `eam/src/dynamics/se/inidat.F90` in Depends.[gnu,gnugpu].cmake in PR E3SM-Project/E3SM#5132 - for runs with Cray, the issue was...

Can't reproduce this issue any more. Closing.

Oops. Turns out that `maint-2.0` does not have this issue, but `master` does. Re-opening.

IBM compiler on Ascent/Summit has a similar issue for these 3 cases. There's a work-around for IBM in NGEET/fates#824 . Pinging @rgknox and @glemieux . Have you been able to...

The default pelayout (when `--pecount *` is omitted in `create_newcase`) is `pesize="any"` or `pesize="M"`. Medium and Large RRM-AMIP pelayouts have been on master since Feb 9 (also on `maint-2.0`) with...