microsoft / microsoft/onnxruntime

[Feature Request] Increase type-support for comparison operators in the CPUExecutionProvider

Open
#16,428 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

feature request
Dominant language
C++
Stars
21.9k
Forks
4.2k
Avg merge
4d 11h
Merged PRs (30d)
184

Description

### Describe the feature request

[Currently](https://github.com/microsoft/onnxruntime/blob/main/docs/OperatorKernels.md) type support for ```Equal```, ```Less```, ```Greater```, ```LessOrEqual``` and ```GreaterOrEqual``` is really limited in the ```CPUExecutionProvider```. Some of the types that are missing are ```uint```-s, ```int8``` and ```int16```.

### Describe scenario use case

This feature is part of the onnx specs, and some of the types are only missing in the ```CPUExecutionProvider```. In addition, operators returning ```Tensor(bool)``` are important in mask-indexing.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with docs/OperatorKernels.md and the CPUExecutionProvider entry point to compare the documented type support for Equal, Less, Greater, LessOrEqual, and GreaterOrEqual. Done means the missing unsigned integer, int8, and int16 cases are supported by the provider and boolean tensor results work for mask-indexing; the issue does not name implementation files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
backend, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.