[Quant] Add fused linear-tanh op for onednn backend #88879
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
[ghstack-poisoned]
Xia-Weiwen
requested review from
digantdesai,
jerryzh168,
jianyuh,
kimishpatel,
salilsdesai and
z-a-f
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/88879
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit fc5ce60: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Nov 11, 2022
github-actions
bot
added
module: cpu
jgong5
approved these changes
Nov 12, 2022
jerryzh168
approved these changes
Nov 12, 2022
Contributor
jerryzh168
left a comment
jerryzh168
left a comment
There was a problem hiding this comment.
lg, please add "Summary" and "Test Plan" as well
Contributor
|
what is the motivation behind tanh linear fusion? |
Collaborator
Author
Fusing activations with root ops can reduce overhead and improve inference performance. Linear-tanh is found in models like CGAN. |
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
jerryzh168
approved these changes
Dec 14, 2022
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused `linear-tanh` op for `onednn` backend, which will be used for int8 inference with `onednn` backend. Linear-tanh is found in models like CGAN. Cannot call this op with other quantization backends otherwise an error is thrown. **Test Plan** python test_quantization.py TestQuantizedLinear cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 leslie-fang-intel VitalyFedyunin mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
Collaborator
Author
|
@pytorchbot merge |
Collaborator
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
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.
Stack from ghstack (oldest at bottom):
Summary
Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused
linear-tanhop foronednnbackend, which will be used for int8 inference withonednnbackend. Linear-tanh is found in models like CGAN.Cannot call this op with other quantization backends otherwise an error is thrown.
Test Plan
python test_quantization.py TestQuantizedLinear
cc @jerryzh168 @jianyuh @raghuramank100 @jamesr66a @vkuzo @jgong5 @leslie-fang-intel @VitalyFedyunin @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10