[PyTorch] Add efficient isnan for NEON float #139082
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
Just test x != x rather than applying element-by-element scalar isnan. Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) [ghstack-poisoned]
pytorch-bot
bot
added
the
module: cpu
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/139082
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 05a9e2d with merge base 86602a6 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
This was referenced Oct 28, 2024
Closed
Just test x != x rather than applying element-by-element scalar isnan. Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
Just test x != x rather than applying element-by-element scalar isnan. Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
Just test x != x rather than applying element-by-element scalar isnan. Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
This was referenced Oct 29, 2024
malfet
approved these changes
Oct 31, 2024
Just test x != x rather than applying element-by-element scalar isnan. Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
Just test x != x rather than applying element-by-element scalar isnan. Testing: vec_test_all_types checks IsNan Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
Just test x != x rather than applying element-by-element scalar isnan. Testing: vec_test_all_types checks IsNan Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D65001633 |
pytorchmergebot
pushed a commit
that referenced
this pull request
Nov 1, 2024
Same as the efficient one for float when f16 hardware support is available. Testing: Added exhaustive isnan test coverage Differential Revision: [D65003321](https://our.internmc.facebook.com/intern/diff/D65003321/) Pull Request resolved: #139083 Approved by: https://github.com/malfet ghstack dependencies: #139082
pytorchmergebot
pushed a commit
that referenced
this pull request
Nov 1, 2024
This is the first big milestone we've been building towards! (Following rev also hooks this up to actual gemv.) Testing: To check perf, I ran python torchchat.py generate stories110M --dtype fp16 --device cpu on an x86 machine without AVX512FP16. Observed roughly 5x tokens/sec increase. Differential Revision: [D64280688](https://our.internmc.facebook.com/intern/diff/D64280688/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D64280688/)! Pull Request resolved: #137918 Approved by: https://github.com/malfet ghstack dependencies: #139082, #139083
pytorchmergebot
pushed a commit
that referenced
this pull request
Nov 1, 2024
…rchitectures (#138005) Following up on previous rev to use fp16_gemv_trans in gemv, not just gemm-used-for-gemv. Differential Revision: [D64351092](https://our.internmc.facebook.com/intern/diff/D64351092/) Pull Request resolved: #138005 Approved by: https://github.com/malfet ghstack dependencies: #139082, #139083, #137918
pytorchmergebot
pushed a commit
that referenced
this pull request
Nov 1, 2024
No real reason to have the zero-beta restriction, so let's lift it. Testing: intentionally broke new paths locally to verify test coverage existed Differential Revision: [D64407752](https://our.internmc.facebook.com/intern/diff/D64407752/) Pull Request resolved: #138275 Approved by: https://github.com/malfet ghstack dependencies: #139082, #139083, #137918, #138005
rahulsingh-intel
pushed a commit
to rahulsingh-intel/pytorch
that referenced
this pull request
Nov 5, 2024
Just test x != x rather than applying element-by-element scalar isnan. Testing: vec_test_all_types checks IsNan Differential Revision: [D65001633](https://our.internmc.facebook.com/intern/diff/D65001633/) Pull Request resolved: pytorch#139082 Approved by: https://github.com/malfet
rahulsingh-intel
pushed a commit
to rahulsingh-intel/pytorch
that referenced
this pull request
Nov 5, 2024
Same as the efficient one for float when f16 hardware support is available. Testing: Added exhaustive isnan test coverage Differential Revision: [D65003321](https://our.internmc.facebook.com/intern/diff/D65003321/) Pull Request resolved: pytorch#139083 Approved by: https://github.com/malfet ghstack dependencies: pytorch#139082
rahulsingh-intel
pushed a commit
to rahulsingh-intel/pytorch
that referenced
this pull request
Nov 5, 2024
This is the first big milestone we've been building towards! (Following rev also hooks this up to actual gemv.) Testing: To check perf, I ran python torchchat.py generate stories110M --dtype fp16 --device cpu on an x86 machine without AVX512FP16. Observed roughly 5x tokens/sec increase. Differential Revision: [D64280688](https://our.internmc.facebook.com/intern/diff/D64280688/) **NOTE FOR REVIEWERS**: This PR has internal Meta-specific changes or comments, please review them on [Phabricator](https://our.internmc.facebook.com/intern/diff/D64280688/)! Pull Request resolved: pytorch#137918 Approved by: https://github.com/malfet ghstack dependencies: pytorch#139082, pytorch#139083
rahulsingh-intel
pushed a commit
to rahulsingh-intel/pytorch
that referenced
this pull request
Nov 5, 2024
…rchitectures (pytorch#138005) Following up on previous rev to use fp16_gemv_trans in gemv, not just gemm-used-for-gemv. Differential Revision: [D64351092](https://our.internmc.facebook.com/intern/diff/D64351092/) Pull Request resolved: pytorch#138005 Approved by: https://github.com/malfet ghstack dependencies: pytorch#139082, pytorch#139083, pytorch#137918
rahulsingh-intel
pushed a commit
to rahulsingh-intel/pytorch
that referenced
this pull request
Nov 5, 2024
No real reason to have the zero-beta restriction, so let's lift it. Testing: intentionally broke new paths locally to verify test coverage existed Differential Revision: [D64407752](https://our.internmc.facebook.com/intern/diff/D64407752/) Pull Request resolved: pytorch#138275 Approved by: https://github.com/malfet ghstack dependencies: pytorch#139082, pytorch#139083, pytorch#137918, pytorch#138005
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 (oldest at bottom):
Just test x != x rather than applying element-by-element scalar isnan.
Testing: vec_test_all_types checks IsNan
Differential Revision: D65001633
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10