Closed mark-a-potts closed 4 years ago
Regression testing (via rt.sh) of ufs-weather-model develop branch successfully passed on Hera. I will also follow up with regression testing of ufs-weather-model public release branch. RegressionTests_hera.intel.log
Regression testing of ufs-weather-model ufs_public_release branch successfully passed on Hera. RegressionTests_hera.intel.log
Yes, I agree. Do you want me to change that and re-submit the pull request?
M
On 2/6/20 10:11 AM, MinsukJi-NOAA wrote:
@MinsukJi-NOAA approved this pull request.
Seems the two lines are redundant since hash is assigned a value filtered by abs(). What do you think?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/NOAA-EMC/NEMS/pull/25?email_source=notifications&email_token=AH4Q2UVJOODKSYVEI7RMICTRBQSBXA5CNFSM4KQV6CJ2YY3PNVWWK3TUL52HS4DFWFIHK3DMKJSXC5LFON2FEZLWNFSXPKTDN5WW2ZLOORPWSZGOCUQ2CBA#pullrequestreview-354525444, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH4Q2UUWOJYV4FOZWFIX6N3RBQSBXANCNFSM4KQV6CJQ.
-- Mark A. Potts, Ph.D. Sr. HPC Software Developer RedLine Performance Solutions, LLC Phone 202-744-9469 Mark.Potts@noaa.gov mpotts@redlineperf.com
Okay. I think if you push the change to openmpi-fix branch, the PR will automatically update.
Done.
On 2/6/20 10:50 AM, MinsukJi-NOAA wrote:
Okay. I think if you push the change to openmpi-fix branch, the PR will automatically update.
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/NOAA-EMC/NEMS/pull/25?email_source=notifications&email_token=AH4Q2UUZH2S7JKUVHSPTEKTRBQWV5A5CNFSM4KQV6CJ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEK7WTOY#issuecomment-582969787, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH4Q2UW6S324JEO66DPUCVDRBQWV5ANCNFSM4KQV6CJQ.
-- Mark A. Potts, Ph.D. Sr. HPC Software Developer RedLine Performance Solutions, LLC Phone 202-744-9469 Mark.Potts@noaa.gov mpotts@redlineperf.com
Mark/Minsuk,
Would you please create a pull request in ufs-weather-model so that this change can be tested and we can update the ufs-weather-model release branch?
Mark, I am going to delete the openmpi-fix branch since it's been successfully merged. Let me know if you have objections.
No problem.
Thanks,
-M
On 2/14/20 9:55 AM, MinsukJi-NOAA wrote:
Mark, I am going to delete the openmpi-fix branch since it's been successfully merged. Let me know if you have objections.
— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub https://github.com/NOAA-EMC/NEMS/pull/25?email_source=notifications&email_token=AH4Q2URKPBAUCJI7QXAJ5MLRC2WFVA5CNFSM4KQV6CJ2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOELZJDUY#issuecomment-586322387, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH4Q2URQGVK73MNJLFXATZTRC2WFVANCNFSM4KQV6CJQ.
-- Mark A. Potts, Ph.D. Sr. HPC Software Developer RedLine Performance Solutions, LLC Phone 202-744-9469 Mark.Potts@noaa.gov mpotts@redlineperf.com
This fixes a problem when using openmpi. When the MPI_Comm_Split hash is negative, openmpi fails. This adds an abs() call to the hash that is created for the split.