Open
Conversation
…c, GPU-native chkfinite - is_cross_hermitian/is_cross_symmetric: wrap ≈ in GPUArraysCore.allowscalar so ROCArray/CuArray chunk comparison does not trigger scalar indexing in norm - chkfinite: use GPU-native all(isfinite, A) for AbstractGPUArray chunks (mapreduce on device); keep LAPACK.chkfinite for CPU chunks - chkfinite!: set finite[] = true on success so chkfinite(A::DArray) returns correctly Made-with: Cursor
Pivot value reads and ipiv write use scalar getindex/setindex; wrap body in GPUArraysCore.allowscalar() so LU with RowMaximum works on ROCArray/CuArray chunks. Made-with: Cursor
- ROCExt/CUDAExt: move(GPUProc, GPUProc, ::ROCArray/CuArray) so datadeps move_rewrap (unwrapped array) performs DtoD copy instead of identity - aliasing: tochunk GPU source with first(processors(memory_space(x))) - lu.jl: findmax pivot metrics + host 1×1 pivot read; geru! panel update - linalg.jl: chunk symmetry via norm bound (replaces allowscalar ≈) - IntelExt: minor; test/gpu.jl Intel + ROCm coverage Made-with: Cursor
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We now use
unsafe_free!to eagerly free Datadeps and DArray GPU allocations when safe to do so.This PR also:
DVectorinputs+and-methods forDArraysRefValueto a newGPURef, required for LU and other algorithmsTodo:
unsafe_free!to stencilsunsafe_free!DVectorinputs+and-