Use nullptr to represent fallback kernels #11484
Merged
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11484
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit aef60d2 with merge base 8f05c35 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D76201866 |
Summary: `KernelKey`s can be constructed as either a "fallback" or "specialized" key. The "fallback" type uses the default constructor, and the "specialized" takes a specially formatted string. Internally, this was represented as a pointer to the optional key string and a bool for whether it is a fallback kernel. As it would not make sense to construct a "specialized" kernel without a key string, this diff eliminates the bool `is_fallback_` in favor of using `kernel_key_data_ == nullptr` to represent fallback kernels. Each `KernelKey` is nested within the `Kernel` data structure, which makes up the list of registered kernels. As the default size of the registered_kernels array is 2000 kernel entries, this diff can reduce the size of the `registered_kernels` array by 8 KB. This diff also changes the backing storage buffer for `registered_kernels_data` to ensure that there is enough space for each Kernel element in the array to be aligned according to `alignas(Kernel)`. Differential Revision: D76201866
|
This pull request was exported from Phabricator. Differential Revision: D76201866 |
larryliu0820
added
the
release notes: none
larryliu0820
approved these changes
Jun 9, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
KernelKeys can be constructed as either a "fallback" or "specialized" key. The "fallback" type uses the default constructor, and the "specialized" takes a specially formatted string. Internally, this was represented as a pointer to the optional key string and a bool for whether it is a fallback kernel. As it would not make sense to construct a "specialized" kernel without a key string, this diff eliminates the boolis_fallback_in favor of usingkernel_key_data_ == nullptrto represent fallback kernels.Each
KernelKeyis nested within theKerneldata structure, which makes up the list of registered kernels. As the default size of the registered_kernels array is 2000 kernel entries, this diff can reduce the size of theregistered_kernelsarray by 8 KB.This diff also changes the backing storage buffer for
registered_kernels_datato ensure that there is enough space for each Kernel element in the array to be aligned according toalignas(Kernel).Differential Revision: D76201866