Andrew M. Bradley
Andrew M. Bradley
@bartgol, yes, exactly.
Eventually we want YAKL's allocator to use the same buffer as the rest of the processes. At that point, it would be good to have the ATMBufferManager advertise the high-water...
This is on Chrysalis. With Intel, I see this error for n30 with out-of-the-box settings except for pack size 1. With GNU, I haven't yet been able to reproduce this...
Yes, they are in e3sm.log. On Summit, you're using GNU for all runs, right? GNU is fine so far on Chrysalis.
Intel debug build, all other settings the same, runs without a problem.
./atmchange theta_hydrostatic_mode=False
As an alternative for the savvy caller, could they request transfer of a bundle exactly once?
Am I correct that the current s/w stack can't be run from this branch?
Tagging @rljacob @ndkeen @jgfouca @PeterCaldwell @AaronDonahue. Trey, I don't know the right answers to your questions in terms of what everyone wants. But in terms of technical steps: 1. We...
I marked this PR as WIP so that the autotester doesn't run on it until it's ready.