Skip to content

Conversation

@peterbell10
Copy link
Collaborator

@peterbell10 peterbell10 commented Jul 26, 2021

Stack from ghstack:

This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
libtorch_python on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

Differential Revision: D29962048

This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Jul 26, 2021

🔗 Helpful links

💊 CI failures summary and remediations

As of commit d443e36 (more details on the Dr. CI page):


💚 💚 Looks good so far! There are no failures yet. 💚 💚


This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
pairs: Sequence[PythonSignatureNativeFunctionPair],
pred: Callable[[NativeFunction], bool]
) -> Dict[BaseOperatorName, List[PythonSignatureNativeFunctionPair]]:
grouped: Dict[BaseOperatorName, List[PythonSignatureNativeFunctionPair]] = defaultdict(list)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sometimes, I'm really not convinced that typing helps with readability...


namespace torch { namespace autograd {

inline Tensor dispatch_arange(const Scalar& end, Tensor result) {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do you know why we have so many of these bindings that are manual?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not sure. I see that arange specifically was manually bound in #7016.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

cc @gchanan do you remember if this is still valid? :)

This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
peterbell10 added a commit to peterbell10/pytorch that referenced this pull request Jul 26, 2021
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

ghstack-source-id: 4ffde84
Pull Request resolved: pytorch#62187
peterbell10 added a commit to peterbell10/pytorch that referenced this pull request Jul 26, 2021
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

ghstack-source-id: 4ffde84
Pull Request resolved: pytorch#62187
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
@peterbell10 peterbell10 added the module: codegen Issues related to the codegen for Aten and Autograd label Jul 28, 2021
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

[ghstack-poisoned]
@albanD
Copy link
Collaborator

albanD commented Jul 28, 2021

@albanD has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

Copy link
Collaborator

@albanD albanD left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

SGTM

This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

Differential Revision: [D29962048](https://our.internmc.facebook.com/intern/diff/D29962048)

[ghstack-poisoned]
This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

Differential Revision: [D29962048](https://our.internmc.facebook.com/intern/diff/D29962048)

[ghstack-poisoned]
@albanD
Copy link
Collaborator

albanD commented Aug 5, 2021

@albanD has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

This file can take 3 minutes on its own to compile, and after
python_functions.cpp is the second limiting factor for compile time of
`libtorch_python` on a 32-core threadripper. This splits it into 3 files that
take around 1 minute each to compile.

Differential Revision: [D29962048](https://our.internmc.facebook.com/intern/diff/D29962048)

[ghstack-poisoned]
@albanD
Copy link
Collaborator

albanD commented Aug 6, 2021

@albanD has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator.

@facebook-github-bot
Copy link
Contributor

@albanD merged this pull request in 44ede71.

@facebook-github-bot facebook-github-bot deleted the gh/peterbell10/104/head branch August 29, 2021 14:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cla signed Merged module: codegen Issues related to the codegen for Aten and Autograd open source

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants