Fix GPU dispatch for PolymorphicArenaAllocator in DefaultInitialization#6808
Merged
ax3l merged 1 commit intoBLAST-WarpX:developmentfrom Apr 27, 2026
Merged
Conversation
Follow-up from transitioning to polymorphic particle containers. `amrex::RunOnGpu<PolymorphicArenaAllocator>` is `false_type` because AMReX does not specialize `RunOnGpu` for this allocator. This causes `DefaultInitializeRuntimeAttributes` to take the CPU code path even when particle data lives on device, leading to segfaults when ionization or user-defined runtime attributes are used with SYCL (and potentially other GPU backends that don't have UVA). This affected users that used runtime attributes on hardware that did not successfully fell back to unified memory (and we try to avoid that anyway). Co-Authored-By: Tim Williams <[email protected]>
ax3l
added
bug
WeiqunZhang
approved these changes
Apr 27, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up from transitioning to polymorphic particle containers #6374.
Isolated from #6801
amrex::RunOnGpu<PolymorphicArenaAllocator>isfalse_typebecause AMReX does not specializeRunOnGpufor this allocator. This causesDefaultInitializeRuntimeAttributesto take the CPU code path even when particle data lives on device, leading to segfaults when ionization or user-defined runtime attributes are used with SYCL (and potentially other GPU backends that don't have UVA).This affected users that used runtime attributes on hardware that did not successfully fell back to unified memory (and we try to avoid that anyway).