Add normalGMBolusVelocity to the gm package #5167
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This reverts commit 2c6f496.
|
Ran the nightly suite again to confirm:
|
|
test merge passes:
@mark-petersen -- we may need to rework the PR in reference to it being non-BFB. Maybe state that there are potential order-of-operations differences possible, but not found in testing on chrysalis? |
mark-petersen
changed the title
mark-petersen
added
BFB
|
@jonbob I updated the first PR comment to be more detailed description of the purpose of this PR, and how the non-bfb result occurs. |
jonbob
added a commit
that referenced
this pull request
Sep 6, 2022
…5167) Add normalGMBolusVelocity to the gm package This PR is needed to put the normalGMBolusVelocity in the gm package, so it is not allocated when GM is off. Otherwise, extra memory is allocated unnecessarily for high-resolution simulations. This reverts commit 2c6f496, which was a small change in #5099 to make that PR BFB on intel-19 optimized in MPAS-Ocean standalone. This PR is BFB with gcc-9 debug, gcc-9 optimized, and intel-19 debug. For intel-19 optimized there is a mismatch with master of 1e-12 on the first timestep for the MPAS-Ocean standalone compass test ocean_global_ocean_QU240_PHC_performance_test on chrysalis. It appears that intel-19 conducts some optimization that changes the order of operations for the lines involved. We expect this PR to be bfb for all E3SM tests. [BFB]
|
Thanks @mark-petersen - I think that's much more clear Merged to next |
|
merged to master and nonBFB results blessed on compy-pgi |
32 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is needed to put the
normalGMBolusVelocityin the gm package, so it is not allocated when GM is off. Otherwise, extra memory is allocated unnecessarily for high-resolution simulations.This reverts commit 2c6f496, which was a small change in #5099 to make that PR BFB on intel-19 optimized in MPAS-Ocean standalone.
This PR is BFB with gcc-9 debug, gcc-9 optimized, and intel-19 debug. For intel-19 optimized there is a mismatch with master of 1e-12 on the first timestep for the MPAS-Ocean standalone compass test
ocean_global_ocean_QU240_PHC_performance_teston crysalis. It appears that intel-19 conducts some optimization that changes the order of operations for the lines involved here.We expect this PR to be bfb for all E3SM tests.
[BFB]