[ET Device Support] DeviceAllocator interface and DeviceAllocatorRegistry#19496
Merged
Conversation
…stry This diff introduces the `DeviceAllocator` abstract interface and `DeviceAllocatorRegistry` for device-specific memory allocation. This is a foundational abstraction that enables the runtime to dispatch memory operations to the appropriate device backend other than CPU (CUDA, etc.). **DeviceAllocator interface provides:** - `allocate()` / `deallocate()` - Dynamic device memory allocation - `copy_host_to_device()` / `copy_device_to_host()` - Data transfer between host and device - `device_type()` - Returns the device type this allocator handles **DeviceAllocatorRegistry provides:** - Singleton registry mapping DeviceType → DeviceAllocator - `register_allocator()` / `get_allocator()` methods - Fixed-size array indexed by device type (no dynamic allocation, embedded-friendly) **Design notes:** - Registry stores raw pointers (non-owning) - allocators are expected to be singletons with static lifetime - Follows ExecuTorch's embedded-first philosophy (no std::unique_ptr, no heap allocation in registry) - Convenience free functions `register_device_allocator()` and `get_device_allocator()` for ease of use Differential Revision: [D93635656](https://our.internmc.facebook.com/intern/diff/D93635656/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19496
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This was referenced May 12, 2026
Merged
This PR needs a
|
Gasoonjia
added a commit
that referenced
this pull request
May 12, 2026
…stry (#19498) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #19496 by @Gasoonjia ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/gasoonjia/167/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/167/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/gasoonjia/167/orig Differential Revision: [D93635656](https://our.internmc.facebook.com/intern/diff/D93635656/) @diff-train-skip-merge Co-authored-by: gasoonjia <gasoonjia@icloud.com>
Gasoonjia
added a commit
that referenced
this pull request
May 12, 2026
…vice mapping (#19497) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #18474 * #18473 * #18472 * #18375 * __->__ #19497 * #19496 Adds the NonConstBufferDevice table to the FlatBuffer schema (program.fbs) and the corresponding Python dataclass to schema.py. This enables mapping each non-constant planned memory buffer to a specific device type (CPU, CUDA, etc.). The field is optional and absent for CPU-only programs, ensuring zero binary size regression. Differential Revision: [D97335597](https://our.internmc.facebook.com/intern/diff/D97335597/)
Gasoonjia
added a commit
that referenced
this pull request
May 12, 2026
…r device type (#18375) Stack from [ghstack](https://github.com/ezyang/ghstack) (oldest at bottom): * #18474 * #18473 * #18472 * __->__ #18375 * #19497 * #19496 Extends memory planning to separate device tensors from CPU tensors into distinct memory buffers. Non-CPU TensorSpecs (e.g., CUDA) are pre-assigned device-specific mem_ids before the greedy/naive algorithm runs, ensuring they get planned into independent memory buffers that never share space with CPU tensors. Differential Revision: [D97447105](https://our.internmc.facebook.com/intern/diff/D97447105/)
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.
Stack from ghstack (oldest at bottom):
This diff introduces the
DeviceAllocatorabstract interface andDeviceAllocatorRegistryfor device-specific memory allocation. This is a foundational abstraction that enables the runtime to dispatch memory operations to the appropriate device backend other than CPU (CUDA, etc.).DeviceAllocator interface provides:
allocate()/deallocate()- Dynamic device memory allocationcopy_host_to_device()/copy_device_to_host()- Data transfer between host and devicedevice_type()- Returns the device type this allocator handlesDeviceAllocatorRegistry provides:
register_allocator()/get_allocator()methodsDesign notes:
register_device_allocator()andget_device_allocator()for ease of useDifferential Revision: D93635656