[Quant] Add fused ConvAddReLU2d module for onednn backend #91154
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]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/91154
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 0c6e824: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Dec 20, 2022
leslie-fang-intel
changed the title
leslie-fang-intel
added
ciflow/trunk
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
…kend" cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
jerryzh168
reviewed
Jan 9, 2023
| def __init__(self, in_channels, out_channels, kernel_size, stride=1, | ||
| padding=0, dilation=1, groups=1, bias=True, | ||
| padding_mode='zeros', device=None, dtype=None): | ||
| super(ConvAddReLU2d, self).__init__( |
Contributor
There was a problem hiding this comment.
nit: super(...) -> super()
Collaborator
Author
There was a problem hiding this comment.
Thanks and changed.
jerryzh168
approved these changes
Jan 9, 2023
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Jan 13, 2023
ghstack-source-id: 1a39904 Pull Request resolved: pytorch#91154
leslie-fang-intel
added a commit
to leslie-fang-intel/pytorch
that referenced
this pull request
Jan 26, 2023
ghstack-source-id: 1a39904 Pull Request resolved: pytorch#91154
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
jerryzh168
reviewed
Jan 31, 2023
Comment on lines
852
to
880
| batch_size = 2 | ||
| in_channels_per_group = 2 | ||
| H = 8 | ||
| W = 8 | ||
| out_channels_per_group = 2 | ||
| groups = 3 | ||
| kernel_h = 3 | ||
| kernel_w = 3 | ||
| stride_h = 2 | ||
| stride_w = 2 | ||
| pad_h = 1 | ||
| pad_w = 1 | ||
| dilation = 1 | ||
| # Tests the correctness of the conv2d module. | ||
| in_channels = in_channels_per_group * groups | ||
| out_channels = out_channels_per_group * groups | ||
| input_feature_map_size = (H, W) | ||
| kernel_size = (kernel_h, kernel_w) | ||
| stride = (stride_h, stride_w) | ||
| padding = (pad_h, pad_w) | ||
| dilation = (dilation, dilation) | ||
| X_scale = 1.3 | ||
| X_zero_point = 2 | ||
| X2_scale = 1.2 | ||
| X2_zero_point = 1 | ||
| W_scale = [0.5] | ||
| W_zero_point = [0] if qengine_is_onednn() else [3] | ||
| Y_scale = 5.0 | ||
| Y_zero_point = 4 |
Contributor
There was a problem hiding this comment.
nit: please move these outside of the loop
Collaborator
Author
There was a problem hiding this comment.
Thanks and changed.
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add_relu ``` cc jgong5 mingfeima XiaobingSuper sanchitintel ashokei jingxu10 [ghstack-poisoned]
**Summary** Post op fusion can reduce data movement overhead and improve inference performance. This PR adds fused ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown. **Test plan** ``` python -m pytest test_quantization.py -k test_conv2d_add_relu ``` cc jgong5 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 ConvAddReLU2d module for onednn backend, which will be used for int8 inference with onednn backend. Cannot call this module with other quantization backends otherwise an error is thrown.
Test plan
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10