[CRL] Avoid sticky device error state on host buffer registration - #528
Merged
Conversation
leoda1
requested review from
MC952-arch,
aoyulong and
mikethegoblin
as code owners
August 3, 2026 12:43
leoda1
changed the title
MC952-arch
reviewed
Aug 4, 2026
…ix the dependencies between the QP/Workers/Shard
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR Category
CRL (Communication Runtime Layer)
PR Types
Bug Fixes
PR Description
Registering a host buffer went through
detectPtrTypeAndMaybeCacheIpc, whose probing IPC call leaves a sticky error in the device runtime. On chips whose runtime cannot clear that state, all later device calls fail.getLastErrorto the device adaptor (implemented for CUDA) to clear the sticky error after the IPC probe.flagcxP2pEngineRegEx/flagcxP2pRpcRegisterHost, which take an explicit pointer-type hint so host registration skips the IPC probe entirely and never produces the error.flagcxP2pRegisterHostin the interservice Python wrapper, and let it also locatelibflagcx.sounder$FLAGCX_PATH/build/lib.