-
Notifications
You must be signed in to change notification settings - Fork 427
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Re-organize the backward split code generation, pt.2 #1873
Conversation
✅ Deploy Preview for pytorch-fbgemm-docs canceled.
|
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: a8f0fcb6a2dbf634c8ba70b8ecc24b6ca31bbb1a
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: 778aff8c5c593a2d0d2ec16deb36b56c3546b6ed
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: 9f40a36d39259f9a5baf888ae0fbd3b8a028e7d9
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: 1e38f77489bbd36ad3f93a0ca88daa77d334942a
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: ba6806af63d6913ab2bbfe191a87e3ced608467e
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: 906e4892e1d304e00174b1ee91021d0dda896df7
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: d9442f1d3b6810a227d586557a5a3587765ca2c4
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Differential Revision: D47385306 fbshipit-source-id: ed828eb421109407a8e923e1afa08fd431da4e39
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Reviewed By: sryap Differential Revision: D47385306 fbshipit-source-id: 8f8b9c033466e2ad3585ef20f0aa897af7594ec1
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Reviewed By: sryap Differential Revision: D47385306 fbshipit-source-id: 7fb6f02b900a0d1a82fd81b20e3abfcaad3a0e00
This pull request was exported from Phabricator. Differential Revision: D47385306 |
Summary: Pull Request resolved: pytorch#1873 - Use Jinja macros to simplify code generation in `embedding_backward_split_kernel_cta_template.cu` and `embedding_backward_split_kernel_warp_template.cu` - Update code generation of the kernel instantiations for the experimental optimizer cases Reviewed By: sryap Differential Revision: D47385306 fbshipit-source-id: 91c78e1857ea3996f9559f2c8c5f48e97ba2f1ac
This pull request was exported from Phabricator. Differential Revision: D47385306 |
This pull request has been merged in 9e24d2a. |
Summary:
Use Jinja macros to simplify code generation in
embedding_backward_split_kernel_cta_template.cu
andembedding_backward_split_kernel_warp_template.cu
Update code generation of the kernel instantiations for the experimental optimizer cases
Differential Revision: D47385306