Repository navigation
Conversation
christiangnrd
force-pushed
the
diagcopy
branch
from
October 20, 2026 14:35
6c081b4 to
cbf2b9e
Compare
christiangnrd
changed the title
copyto for GPU Diagonalscopyto! for GPU Diagonals
The generic AnyGPUArray copyto! is more specific than LinearAlgebra's Diagonal method, so it launched a kernel over all n^2 entries calling setindex!(::Diagonal). On Julia 1.10 that method's error path eagerly builds a string, which POCL/SPIR-V rejects, breaking cholesky(::Diagonal) for JLArrays with KA 0.10. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
christiangnrd
force-pushed
the
diagcopy
branch
from
October 22, 2026 14:33
cbf2b9e to
11c0d7f
Compare
Cover the method directly, including a conversion between element types, rather than only through `cholesky`.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Diagonal{T, <:AbstractGPUArray}is one of Adapt's wrapped arrays, so GPUArrays' genericcopyto!(::AnyGPUArray, ::AnyGPUArray)takes precedence over LinearAlgebra'scopyto!for Diagonals. Instead of copying the diagonal, it launched a kernel over all n² entries, each callingsetindex!(::Diagonal, ...).cholesky(::Diagonal)gets there throughcholcopy.This adds a method that copies only the diagonal, as LinearAlgebra does:
choleskyof a 4096×4096 JLArrayDiagonalgoes from 42 ms to 0.2 ms.setindex!'s error path builds its message eagerly, which POCL can't compile. Without this,cholesky(::Diagonal)fails on JLArrays once they move to KernelAbstractions 0.10 ([JLArrays] Support KA 0.10 #826).