Add CuPy and Dask+CuPy backends for kriging (#951)#960
Merged
Conversation
Replace the GPU stubs with working implementations. Variogram fitting and matrix inversion stay on CPU (small matrices). The per-pixel prediction runs on GPU via vectorized CuPy operations, matching the existing numpy algorithm. Variogram model functions now auto-detect the array module so they work with both numpy and cupy inputs.
Tests for CuPy and Dask+CuPy kriging backends covering prediction accuracy, all three variogram models, and variance output. Adds _to_numpy() helper and cupy/dask_cupy backends to _make_template().
Covers basic interpolation, variance output, variogram model comparison, and a soil pH mapping example.
brendancol
added
enhancement
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
_kriging_gpu_not_implstubs with working CuPy and Dask+CuPy backends. Kriging was the only interpolation method without GPU support._spherical,_exponential,_gaussian) now pick numpy or cupy based on the input array via_get_xp(), so the same closure works for all backends without duplication.k0 @ K_inv), which CuPy dispatches to cuBLAS.17_Kriging.ipynb) walks through interpolation, variance, variogram model comparison, and a soil pH mapping example.Test plan
Closes #951