[quant][core][performance] Changed cudnn quantized conv2d impl to use inplace operations #73857
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
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
CI Flow Status⚛️ CI FlowRuleset - Version:
|
Contributor
🔗 Helpful links
💊 CI failures summary and remediationsAs of commit 9dc0452 (more details on the Dr. CI page):
1 failure not recognized by patterns:
This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
dzdang
added a commit
that referenced
this pull request
Mar 7, 2022
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. ghstack-source-id: 579184b Pull Request resolved: #73857
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Mar 7, 2022
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. ghstack-source-id: 1168e3b Pull Request resolved: #73857
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Mar 7, 2022
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. ghstack-source-id: 5021156 Pull Request resolved: #73857
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Mar 8, 2022
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. ghstack-source-id: e8e1fd2 Pull Request resolved: #73857
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
This was referenced Mar 9, 2022
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
jerryzh168
approved these changes
Mar 11, 2022
Contributor
jerryzh168
left a comment
jerryzh168
left a comment
There was a problem hiding this comment.
great! merge conflict should be resolved in the previous PR I think.
you can use git rebase -i origin/master and edit the commit history, use e or edit for the PR that you want to edit. (previous PR)
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. [ghstack-poisoned]
Contributor
Author
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Differential Revision: [D34824250](https://our.internmc.facebook.com/intern/diff/D34824250) [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Differential Revision: [D34824250](https://our.internmc.facebook.com/intern/diff/D34824250) [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Differential Revision: [D34824250](https://our.internmc.facebook.com/intern/diff/D34824250) [ghstack-poisoned]
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Differential Revision: [D34824250](https://our.internmc.facebook.com/intern/diff/D34824250) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Mar 17, 2022
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. ghstack-source-id: e85ca45 Pull Request resolved: #73857
…impl to use inplace operations" Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Differential Revision: [D34824250](https://our.internmc.facebook.com/intern/diff/D34824250) [ghstack-poisoned]
dzdang
added a commit
that referenced
this pull request
Mar 17, 2022
… inplace operations Summary: This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. ghstack-source-id: d381df7 Pull Request resolved: #73857
Contributor
Author
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
facebook-github-bot
pushed a commit
that referenced
this pull request
Mar 18, 2022
… inplace operations (#73857) Summary: Pull Request resolved: #73857 This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test Plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Reviewed By: ezyang Differential Revision: D34824250 Pulled By: dzdang fbshipit-source-id: 4d0d2fd61245d4a2cbbdffb910eb73a5807237fd
Contributor
|
Hey @dzdang. |
shahofblah
pushed a commit
that referenced
this pull request
Mar 25, 2022
… inplace operations (#73857) Summary: Pull Request resolved: #73857 This PR changed the implementation for the conv2d cudnn operator to use inplace ops. This increases the quantized conv operator's efficiency when bias and/or relu is used. Based on discussions, to support inplace operations, unique uids need to be assigned to the input and output even if it is stored at the same memory address. e.g., see the different uids in the current implementation assigned to conv_output.data_ptr Test Plan: In pytorch main directory, execute ``` python test/test_quantization.py TestQuantizedConv.test_qconv2d_cudnn ``` for accuracy testing and ``` python test/test_quantization.py TestQuantizedConv.test_benchmark ``` for benchmark testing. Reviewed By: ezyang Differential Revision: D34824250 Pulled By: dzdang fbshipit-source-id: 4d0d2fd61245d4a2cbbdffb910eb73a5807237fd (cherry picked from commit fe21915)
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:
This PR changed the implementation for the conv2d cudnn operator to use inplace ops.
This increases the quantized conv operator's efficiency when bias and/or relu is used.
Based on discussions, to support inplace operations, unique uids need to be assigned
to the input and output even if it is stored at the same memory address.
e.g., see the different uids in the current implementation assigned to conv_output.data_ptr
Test plan:
In pytorch main directory, execute
for accuracy testing and
for benchmark testing.
Differential Revision: D34824250