Skip to content

[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp #3030

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
vivekkhandelwal1 merged 3 commits into from
Jun 4, 2024
Merged

[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp #3030

vivekkhandelwal1 merged 3 commits into from
Jun 4, 2024

Conversation

@vivekkhandelwal1
Copy link
Collaborator

@vivekkhandelwal1 vivekkhandelwal1 commented Mar 15, 2024

This commit also fixes the average pool op' test failing for OnnxToLinalg lowering.

Signed-Off By: Vivek Khandelwal vivekkhandelwal1424@gmail.com

@vivekkhandelwal1 vivekkhandelwal1 force-pushed the fix-avgpool branch 3 times, most recently from 45fa4c0 to f569d31 Compare March 18, 2024 16:28
rsuderman
rsuderman requested changes Mar 20, 2024
View reviewed changes
@AmosLewis AmosLewis mentioned this pull request Apr 30, 2024
Closed
@vivekkhandelwal1 vivekkhandelwal1 force-pushed the fix-avgpool branch 2 times, most recently from 6bd1c5a to b1aa443 Compare May 15, 2024 16:24
@AmosLewis
Copy link
Collaborator

AmosLewis commented May 15, 2024

You will need this commit to
[ONNX] Fix padding attributes for onnx.AveragePool eb3b62f

@AmosLewis
Copy link
Collaborator

AmosLewis commented May 15, 2024

Could you also test with model nod-ai/AMD-SHARK-TestSuite#185 in shark-testsuites with --torchtolinag flag before iree bump:
python ./run.py --torchmlirbuild ../../torch-mlir/build --tolerance 0.001 0.001 --cachedir ./huggingface_cache --ireebuild ../../iree-build -f onnx -g models --mode onnx --report --tests onnx/models/VideoResNet_vaiq_int8 --torchtolinalg

@vivekkhandelwal1
Copy link
Collaborator Author

vivekkhandelwal1 commented May 15, 2024

Could you also test with model nod-ai/SHARK-TestSuite#185 in shark-testsuites with --torchtolinag flag before iree bump: python ./run.py --torchmlirbuild ../../torch-mlir/build --tolerance 0.001 0.001 --cachedir ./huggingface_cache --ireebuild ../../iree-build -f onnx -g models --mode onnx --report --tests onnx/models/VideoResNet_vaiq_int8 --torchtolinalg

It fails during iree-compile with failure for 3d conv but passed for torch-mlir.

@vivekkhandelwal1
Copy link
Collaborator Author

vivekkhandelwal1 commented May 15, 2024

You will need this commit to [ONNX] Fix padding attributes for onnx.AveragePool eb3b62f

We can do this in a seperate PR, since the current PR doesn't make any change in the Onnx implementation. Or, you can create a PR with your commit for the same.

@vivekkhandelwal1
Copy link
Collaborator Author

vivekkhandelwal1 commented May 16, 2024 •
edited
Loading

Could you also test with model nod-ai/SHARK-TestSuite#185 in shark-testsuites with --torchtolinag flag before iree bump: python ./run.py --torchmlirbuild ../../torch-mlir/build --tolerance 0.001 0.001 --cachedir ./huggingface_cache --ireebuild ../../iree-build -f onnx -g models --mode onnx --report --tests onnx/models/VideoResNet_vaiq_int8 --torchtolinalg

I'm getting this:

Status report for run: test-onnx using mode:onnx todtype:default backend:llvm-cpu

| tests                             | model-run   | onnx-import   | torch-mlir   | iree-compile   | inference   |
|:----------------------------------|:------------|:--------------|:-------------|:---------------|:------------|
| onnx/models/VideoResNet_vaiq_int8 | passed      | passed        | passed       | passed         | mismatch    |

rsuderman
rsuderman requested changes May 17, 2024
View reviewed changes
@vivekkhandelwal1
Copy link
Collaborator Author

vivekkhandelwal1 commented May 23, 2024

Hi @rsuderman, can you please re-review this PR?

rsuderman
rsuderman requested changes May 30, 2024
View reviewed changes
@vivekkhandelwal1
Copy link
Collaborator Author

vivekkhandelwal1 commented May 31, 2024

Hi @rsuderman, can you please re-review this?

@vivekkhandelwal1 vivekkhandelwal1 force-pushed the fix-avgpool branch 2 times, most recently from b685a32 to c1121a7 Compare May 31, 2024 16:14
@vivekkhandelwal1
[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp
ee912e4 
This commit also fixes the average pool op' test failing for
OnnxToLinalg lowering.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
@vivekkhandelwal1
Address PR comments
daa048a
@vivekkhandelwal1
Address PR comments
9903711
@vivekkhandelwal1
Copy link
Collaborator Author

vivekkhandelwal1 commented Jun 3, 2024

Hi @rsuderman, can you please re-review this?

Hi @rsuderman, just a gentle reminder to review this PR.

@vivekkhandelwal1 vivekkhandelwal1 merged commit 661be2d into llvm:main Jun 4, 2024
sjarus pushed a commit to sjarus/torch-mlir that referenced this pull request Jun 6, 2024
@vivekkhandelwal1 @sjarus
[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp (llvm#3030)
a10f1cb 
This commit also fixes the average pool op' test failing for
OnnxToLinalg lowering.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
josel-amd pushed a commit to Xilinx/torch-mlir that referenced this pull request Jun 7, 2024
@vivekkhandelwal1 @josel-amd
[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp (llvm#3030)
7bfc292 
This commit also fixes the average pool op' test failing for
OnnxToLinalg lowering.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
@josel-amd josel-amd mentioned this pull request Jun 7, 2024
Merged
josel-amd pushed a commit to Xilinx/torch-mlir that referenced this pull request Jun 10, 2024
@vivekkhandelwal1 @josel-amd
[MLIR][Torch] Add TorchToLinalg lowering for AtenAvgPool3dOp (llvm#3030)
ce7d715 
This commit also fixes the average pool op' test failing for
OnnxToLinalg lowering.

Signed-Off By: Vivek Khandelwal <vivekkhandelwal1424@gmail.com>
@vivekkhandelwal1 vivekkhandelwal1 mentioned this pull request Aug 14, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@rsuderman rsuderman rsuderman approved these changes

@ramiro050 ramiro050 Awaiting requested review from ramiro050

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@vivekkhandelwal1 @AmosLewis @rsuderman