[quant][core][gpu][improvement] Removed conv_output and set output tensors as virtual in quantized cudnn conv2d op#76787
Closed
dzdang wants to merge 5 commits intogh/dzdang/104/basefrom
Closed
[quant][core][gpu][improvement] Removed conv_output and set output tensors as virtual in quantized cudnn conv2d op#76787dzdang wants to merge 5 commits intogh/dzdang/104/basefrom
dzdang wants to merge 5 commits intogh/dzdang/104/basefrom
Conversation
…nsors as virtual in quantized cudnn conv2d op Summary: With support for virtual tensors in cudnn, we no longer have to allocate conv_output. Test plan: ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` [ghstack-poisoned]
Contributor
🔗 Helpful links
✅ No Failures (0 Pending)As of commit 2d2ffc3 (more details on the Dr. CI page): Expand to see more💚 💚 Looks good so far! There are no failures yet. 💚 💚 This comment was automatically generated by Dr. CI (expand for details).Please report bugs/suggestions to the (internal) Dr. CI Users group. |
Contributor
Author
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
jerryzh168
approved these changes
May 10, 2022
jerryzh168
reviewed
May 10, 2022
| .setxDesc(cudnn_utils::getTensorDescriptor(input.sizes(), input.strides(), CUDNN_DATA_INT8, 'x', key.input_alignment)) | ||
| .setyDesc(cudnn_utils::getTensorDescriptor(conv_output, 'y', key.output_alignment)) | ||
| // for virtual tensors, the alignment is not used, so we can just put an arbitrary value here, e.g., key.output_alignment | ||
| .setyDesc(cudnn_utils::getTensorDescriptor(quantized_output.sizes(), quantized_output.strides(), CUDNN_DATA_FLOAT, 'y', key.output_alignment, true)) |
Contributor
There was a problem hiding this comment.
should we use a constant here so that it is the same for all calls?
Contributor
There was a problem hiding this comment.
this setyDesc is not really used since the output is a virtual tensor, is that corrrect?
Contributor
Author
There was a problem hiding this comment.
@jerryzh168 no. setyDesc is still used. we still need to provide the tensor size, stride, and dtype for cudNN (I don't think they have the support that allows them to determine the output shape and dtype based on the input and weight). the alignment and uid are not used.
jerryzh168
reviewed
May 10, 2022
…t output tensors as virtual in quantized cudnn conv2d op" Summary: With support for virtual tensors in cudnn, we no longer have to allocate conv_output. Test plan: ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` Differential Revision: [D36121583](https://our.internmc.facebook.com/intern/diff/D36121583) [ghstack-poisoned]
Contributor
Author
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
…t output tensors as virtual in quantized cudnn conv2d op" Summary: With support for virtual tensors in cudnn, we no longer have to allocate conv_output. Test plan: ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` Differential Revision: [D36121583](https://our.internmc.facebook.com/intern/diff/D36121583) [ghstack-poisoned]
Contributor
Author
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
…t output tensors as virtual in quantized cudnn conv2d op" Summary: With support for virtual tensors in cudnn, we no longer have to allocate conv_output. Test plan: ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` Differential Revision: [D36121583](https://our.internmc.facebook.com/intern/diff/D36121583) [ghstack-poisoned]
…t output tensors as virtual in quantized cudnn conv2d op" Summary: With support for virtual tensors in cudnn, we no longer have to allocate conv_output. Test plan: ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` Differential Revision: [D36121583](https://our.internmc.facebook.com/intern/diff/D36121583) [ghstack-poisoned]
Contributor
Author
|
@dzdang has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Contributor
|
@pytorchbot merge (Initiating merge automatically since Phabricator Diff has merged) |
facebook-github-bot
pushed a commit
that referenced
this pull request
May 25, 2022
…nsors as virtual in quantized cudnn conv2d op (#76787) Summary: Pull Request resolved: #76787 With support for virtual tensors in cudnn, we no longer have to allocate conv_output. Test Plan: ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` ``` python test/test_quantization.py -k test_qconv2d_cudnn ``` Differential Revision: D36121583 D36121583 Reviewed By: jerryzh168 Pulled By: dzdang fbshipit-source-id: 7269fd4eaaad5ae6faf711add99b58731efb717a
pytorchmergebot
pushed a commit
that referenced
this pull request
May 25, 2022
…tensors as virtual in quantized cudnn linear op Summary: See #76787. Same idea applied here but for `linear_output`. Test plan: ``` python test/test_quantization.py --k test_qlinear_cudnn ``` Pull Request resolved: #77518 Approved by: https://github.com/jerryzh168
facebook-github-bot
pushed a commit
that referenced
this pull request
May 25, 2022
…tensors as virtual in quantized cudnn linear op (#77518) Summary: Pull Request resolved: #77518 See #76787. Same idea applied here but for `linear_output`. Test Plan: ``` python test/test_quantization.py --k test_qlinear_cudnn ``` Reviewed By: jerryzh168 Differential Revision: D36403832 Pulled By: dzdang fbshipit-source-id: 4ec3bab6a9d82a58fecd38bc943b2137a4f4157e
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:
With support for virtual tensors in cudnn, we no longer have to allocate
conv_output.
Test plan:
Differential Revision: D36121583