Skip to content
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

Add new kernels #23220

Merged
merged 12 commits into from
Feb 14, 2025
Merged

Add new kernels #23220

merged 12 commits into from
Feb 14, 2025

Conversation

bili2002
Copy link
Contributor

Description

This PR adds the kernels for int8_t, int16_t, and unsigned int inputs for Mul, Div, Add, Sub, Greater, Less, Equal, LessOrEqual, and GreaterOrEqual. The new kernels have been added for all versions of these operators that are supported by the ONNX standard.

Motivation and Context

Similarly to #15358, this change eliminates the need for intermediate type casting for these data types.

@bili2002 bili2002 marked this pull request as ready for review January 8, 2025 06:44
@snnn
Copy link
Member

snnn commented Jan 8, 2025

/azp run Big Models, Linux Android Emulator QNN CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline

@snnn
Copy link
Member

snnn commented Jan 8, 2025

/azp run Linux OpenVINO CI Pipeline, Linux QNN CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline, Windows GPU CUDA CI Pipeline

@snnn
Copy link
Member

snnn commented Jan 8, 2025

/azp run Windows GPU DML CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows x64 QNN CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 6 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 5 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 7 pipeline(s).

@snnn
Copy link
Member

snnn commented Jan 9, 2025

You may need to disable the tests for TensorRT EP and DNNL EP.

@bili2002 bili2002 mentioned this pull request Feb 1, 2025
Merged
@snnn
Copy link
Member

snnn commented Feb 6, 2025

Could you please resolve the conflicts?

@snnn
Copy link
Member

snnn commented Feb 7, 2025

/azp run Big Models, Linux Android Emulator QNN CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline

@snnn
Copy link
Member

snnn commented Feb 7, 2025

/azp run Linux OpenVINO CI Pipeline, Linux QNN CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline

@snnn
Copy link
Member

snnn commented Feb 7, 2025

/azp run Windows GPU CUDA CI Pipeline, Windows GPU DML CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows x64 QNN CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline,

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 6 pipeline(s).

1 similar comment
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 6 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 7 pipeline(s).

@snnn
Copy link
Member

snnn commented Feb 11, 2025

/azp run Big Models, Linux Android Emulator QNN CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline

@snnn
Copy link
Member

snnn commented Feb 11, 2025

/azp run Linux OpenVINO CI Pipeline, Linux QNN CI Pipeline, MacOS CI Pipeline, ONNX Runtime Web CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows CPU CI Pipeline

@snnn
Copy link
Member

snnn commented Feb 11, 2025

/azp run Windows GPU CUDA CI Pipeline, Windows GPU DML CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows GPU TensorRT CI Pipeline, Windows x64 QNN CI Pipeline, onnxruntime-binary-size-checks-ci-pipeline,

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 6 pipeline(s).

1 similar comment
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 6 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 7 pipeline(s).

@snnn snnn merged commit 36231ec into microsoft:main Feb 14, 2025
76 checks passed
@snnn
Copy link
Member

snnn commented Feb 14, 2025

Thank you!

@bili2002 bili2002 deleted the add-new-kernels branch February 18, 2025 07:52
github-merge-queue bot pushed a commit to onnx/onnx that referenced this pull request Feb 18, 2025
@bili2002 @andife @justinchuby
Add dtype tests for various operators (#6687)
471e50e 
### Description
This PR adds tests for `int8_t`, `int16_t`, and unsigned int inputs for
`Mul`, `Div`, `Add`, `Sub`, `Greater`, `Less`, `Equal`, `LessOrEqual`,
and `GreaterOrEqual`.

### Motivation and Context
This was suggested in a
[PR](microsoft/onnxruntime#23220) in the
`onnxruntime`. It will additionally improve the test coverage for
varying data types.

---------

Signed-off-by: Bilyana Indzheva <[email protected]>
Co-authored-by: Andreas Fehlner <[email protected]>
Co-authored-by: Justin Chu <[email protected]>
guschmue pushed a commit that referenced this pull request Mar 6, 2025
@bili2002 @guschmue
Add new kernels (#23220)
5fa89ec 
### Description
This PR adds the kernels for `int8_t`, `int16_t`, and unsigned int
inputs for `Mul`, `Div`, `Add`, `Sub`, `Greater`, `Less`, `Equal`,
`LessOrEqual`, and `GreaterOrEqual`. The new kernels have been added for
all versions of these operators that are supported by the `ONNX`
standard.


### Motivation and Context
Similarly to #15358, this
change eliminates the need for intermediate type casting for these data
types.
ashrit-ms pushed a commit that referenced this pull request Mar 17, 2025
@bili2002 @ashrit-ms
Add new kernels (#23220)
069750d 
### Description
This PR adds the kernels for `int8_t`, `int16_t`, and unsigned int
inputs for `Mul`, `Div`, `Add`, `Sub`, `Greater`, `Less`, `Equal`,
`LessOrEqual`, and `GreaterOrEqual`. The new kernels have been added for
all versions of these operators that are supported by the `ONNX`
standard.


### Motivation and Context
Similarly to #15358, this
change eliminates the need for intermediate type casting for these data
types.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@snnn snnn snnn left review comments

@justinchuby justinchuby justinchuby approved these changes

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
@bili2002 @snnn @justinchuby