hardsigmoid: add cuda kernels#36351
Closed
vkuzo wants to merge 5 commits intogh/vkuzo/27/basefrom
Closed
Conversation
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 9, 2020
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 598c203 Pull Request resolved: #36351
💊 Build failures summary and remediationsAs of commit 1a27431 (more details on the Dr. CI page):
XLA failureJob pytorch_xla_linux_xenial_py3_6_clang7_test is failing. Please create an issue with title prefixed by 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 on the GitHub issue tracker. This comment has been revised 17 times. |
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D20955589](https://our.internmc.facebook.com/intern/diff/D20955589) [ghstack-poisoned]
vkuzo
added a commit
that referenced
this pull request
Apr 10, 2020
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 24645f5 Pull Request resolved: #36351
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D20955589](https://our.internmc.facebook.com/intern/diff/D20955589) [ghstack-poisoned]
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D20955589](https://our.internmc.facebook.com/intern/diff/D20955589) [ghstack-poisoned]
| } | ||
|
|
||
| void hardsigmoid_kernel(TensorIterator& iter) { | ||
| AT_DISPATCH_FLOATING_TYPES_AND2(at::ScalarType::Half, at::ScalarType::BFloat16, iter.dtype(), "hardsigmoid_cuda", [&]() { |
Contributor
There was a problem hiding this comment.
Tensorflow uses a different definition, https://www.tensorflow.org/api_docs/python/tf/keras/activations/hard_sigmoid,
we do not have a use case for that definition, so lets stick with this one
raghuramank100
approved these changes
Apr 12, 2020
Summary: Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D20955589](https://our.internmc.facebook.com/intern/diff/D20955589) [ghstack-poisoned]
Contributor
|
This pull request has been merged in 16e90eb. |
laurentdupin
pushed a commit
to laurentdupin/pytorch
that referenced
this pull request
Apr 24, 2026
Summary: Pull Request resolved: pytorch#36351 Adds CUDA kernels for hardsigmoid, to enable its use in training. Note: the update to the cpu backward pass is to keep the cpu vs cuda logic consistent, no change in functionality. Test Plan: add CI for the forward pass run this for the backward pass: https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a Imported from OSS Differential Revision: D20955589 fbshipit-source-id: dc198aa6a58e1a7996e1831f1e479c398ffcbc90
laurentdupin
pushed a commit
to laurentdupin/pytorch
that referenced
this pull request
Apr 24, 2026
Summary: pytorch#36351 make `hardsigmoid_backward` use tensoriterator but that can be done only after proper device dispatch. Pull Request resolved: pytorch#36704 Differential Revision: D21068126 Pulled By: ailzhang fbshipit-source-id: 6a6a74216f2b50fa7d15f692cd1583d3d233580a
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
4 participants
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:
Summary:
Adds CUDA kernels for hardsigmoid, to enable its use in training.
Note: the update to the cpu backward pass is to keep the cpu vs cuda
logic consistent, no change in functionality.
Test Plan:
add CI for the forward pass
run this for the backward pass:
https://gist.github.com/vkuzo/95957d365600f9ad10d25bd20f58cc1a
Reviewers:
Subscribers:
Tasks:
Tags:
Differential Revision: D20955589