DirectML GEMM broken in opset 11 and 13 when optional tensor C not provided #12568
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
…l, so last tensor must be specified.
sumitsays
reviewed
Aug 11, 2022
| ML_CHECK_VALID_ARGUMENT(kernelInfo.GetInputCount() >= 2); | ||
| ML_CHECK_VALID_ARGUMENT(kernelInfo.GetOutputCount() == 1); | ||
| DmlOperator::Initialize(kernelInfo); | ||
| auto kernelInputIndices = std::vector<std::optional<uint32_t>> { 0, 1, 2 }; |
There was a problem hiding this comment.
Thank you for pointing this out. I think we need to enhance our ONNXConformance Test to test each operator with/without the graph. Right now OnnxConformance test, executes the GEMM as a graph node. And the Compute method is different for an individual operator and a DML Graph. I will discuss this with the team in more detail.
sumitsays
approved these changes
Aug 11, 2022
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Outdated suggestions cannot be applied.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.
DirectML GEMM broken in opset 11 and 13 when optional tensor C not provided
In opset 11, GEMM's input C became optional. This was not accounted for in DML.