[Bugfix][TE] Fix 64KB alignment for default memory allocator - #4057
Open
gygdh-001 wants to merge 1 commit into
Open
[Bugfix][TE] Fix 64KB alignment for default memory allocator#4057gygdh-001 wants to merge 1 commit into
gygdh-001 wants to merge 1 commit into
Conversation
initMemoryAllocator()'s fallback path used plain malloc(), whose address is not 64KB page-aligned. Ascend SVM (_devmm_mem_remote_map) requires a 64KB-aligned src_va, so aclrtHostRegister failed with EINVAL. Use posix_memalign(64KB) for the default allocator instead.
31 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
initMemoryAllocator()'s fallback path used plainmalloc, whose address is not 64KBpage-aligned. Ascend SVM (
_devmm_mem_remote_map) requires a 64KB-alignedsrc_va, soaclrtHostRegisterfailed with EINVAL. The fallback now usesposix_memalign(64 * 1024, ...).Fixes #4055
Module
mooncake-transfer-engine)mooncake-store)mooncake-reshard)mooncake-ep)mooncake-pg)mooncake-integration)mooncake-p2p-store)mooncake-wheel)mooncake-common)mooncake-rl)Type of Change
How Has This Been Tested?
Manual verification on Ascend 910B: cross-card
rdmapath reaches 7.2 GB/s (1MB block ×batch16 × 10 rounds, all ok). With the alignment fix, the fallback allocator returns 64KB-aligned
addresses and
aclrtHostRegisterno longer fails with EINVAL.Test results:
Checklist
./scripts/code_format.shAI Assistance Disclosure