Add the DYAMOND resolution-ladder benchmark - #102
Merged
Conversation
Runs one fixed request pipeline across 30/15/7.5/3.75 km MPAS output, a 64x range in cell count up to 41,943,042 faces, at a Globus Compute endpoint because the largest grid is 19.8 GB. Separates JIT compilation, per-grid bounds construction, and the per-request reduction, since collapsing them reports a 59.5 s first call as the cost of a 1.4 s operation. Uses both face-centred and node-centred fields so one request exercises two mesh locations.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a benchmark that runs one fixed request pipeline (open, load, global mean, zonal mean at two bin widths, regional subset, zonal mean of the subset) unchanged across the DYAMOND-1 MPAS ladder at 30, 15, 7.5, and 3.75 km, a 64x range in cell count up to 41,943,042 faces. It runs at a Globus Compute endpoint because the largest grid is 19.8 GB, and it separates JIT compilation, per-grid bounds construction, and the per-request reduction so a 59.5 s cold call is not reported as the cost of a 1.4 s operation. No library code changes; the harness and the recorded run land under benchmarks/dyamond.