Allow kernel manual registration #491
Closed
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
✅ Deploy Preview for resplendent-gnome-14e531 canceled.
|
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
6a17ee1 to
8a1f1c2
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
8a1f1c2 to
a61a375
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
a61a375 to
f8f3a94
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
f8f3a94 to
11f18f2
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
11f18f2 to
7275e09
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
7275e09 to
dfdcf50
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
dfdcf50 to
3d959be
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
larryliu0820
force-pushed
the
export-D49439673
branch
from
3d959be to
3bd619d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
Summary: X-link: pytorch/pytorch#110086 Exposing a codegen mode for generating a hook for user to register their kernels. If we pass `--manual-registration` flag to `gen_executorch.py`, we will generate the following files: 1. RegisterKernels.h which declares a `register_all_kernels()` API inside `torch::executor` namespace. 2. RegisterKernelsEverything.cpp which implements `register_all_kernels()` by defining an array of generated kernels. This way user can depend on the library declared by `executorch_generated_lib` macro (with `manual_registration=True`) and be able to include `RegisterKernels.h`. Then they can manually call `register_all_kernels()` instead of relying on C++ static initialization mechanism which is not available in some embedded systems. Reviewed By: cccclai Differential Revision: D49439673
larryliu0820
added a commit
to larryliu0820/pytorch
that referenced
this pull request
Sep 26, 2023
…0086) Summary: X-link: pytorch/executorch#491 Exposing a codegen mode for generating a hook for user to register their kernels. If we pass `--manual-registration` flag to `gen_executorch.py`, we will generate the following files: 1. RegisterKernels.h which declares a `register_all_kernels()` API inside `torch::executor` namespace. 2. RegisterKernelsEverything.cpp which implements `register_all_kernels()` by defining an array of generated kernels. This way user can depend on the library declared by `executorch_generated_lib` macro (with `manual_registration=True`) and be able to include `RegisterKernels.h`. Then they can manually call `register_all_kernels()` instead of relying on C++ static initialization mechanism which is not available in some embedded systems. Test Plan: Rely on the unit test: ``` buck2 test fbcode//executorch/runtime/kernel/test:test_kernel_manual_registration ``` Reviewed By: cccclai Differential Revision: D49439673
larryliu0820
force-pushed
the
export-D49439673
branch
from
3bd619d to
8a53eef
Compare
|
This pull request was exported from Phabricator. Differential Revision: D49439673 |
|
This pull request has been merged in 153cf3b. |
Gasoonjia
pushed a commit
that referenced
this pull request
Jul 30, 2024
* Minimal android app build * Improve script * Detect physical device as well
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:
Exposing a codegen mode for generating a hook for user to register their kernels.
If we pass
--manual-registrationflag togen_executorch.py, we will generate the following files:register_all_kernels()API insidetorch::executornamespace.register_all_kernels()by defining an array of generated kernels.This way user can depend on the library declared by
executorch_generated_libmacro (withmanual_registration=True) and be able to includeRegisterKernels.h. Then they can manually callregister_all_kernels()instead of relying on C++ static initialization mechanism which is not available in some embedded systems.Reviewed By: cccclai
Differential Revision: D49439673