Arm backend: Support memory planning in arm_executor_runner - #21774
Merged
Erik-Lundell merged 1 commit intoAug 12, 2026
Conversation
Support explicitly tagging tensors with mem_id = 2 for putting them in a SLOW_MEMORY_REGION and mem_id = 3 for putting in FAST_MEMORY_REGION. Keep default mem_id = 1 in SLOW_MEMORY_REGION. This gives users more flexibility in memory planning their programs. Add a new .fast_memory input section in .sram.bss that backs the fast memory allocator. The size of the memory area is set by a new cmake flag ET_ARM_BAREMETAL_PLANNED_FAST_MEMORY_SIZE. The slow memory region can still be allocated like planned et tensors are currently. Signed-off-by: Erik Lundell <erik.lundell@arm.com> Change-Id: Iedd5bb1e0d79b707a4884d41e5219997b502f083
Erik-Lundell
requested review from
kirklandsign and
larryliu0820
as code owners
August 12, 2026 11:46
Erik-Lundell
added
the
partner: arm
Erik-Lundell
added
the
release notes: none
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21774
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled JobAs of commit 9359bb7 with merge base 1f19ec6 ( CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
zingo
approved these changes
Aug 12, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Support explicitly tagging tensors with mem_id = 2 for putting them in a SLOW_MEMORY_REGION and mem_id = 3 for putting in FAST_MEMORY_REGION. Keep default mem_id = 1 in SLOW_MEMORY_REGION. This gives users more flexibility in memory planning their programs.
Add a new .fast_memory input section in .sram.bss that backs the fast memory allocator. The size of the memory area is set by a new cmake flag
ET_ARM_BAREMETAL_PLANNED_FAST_MEMORY_SIZE. The slow memory region can still be allocated like planned et tensors are currently.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils @Sebastian-Larsson @robell @rascani