gemini-code-assist[bot] commented on PR #18879: URL: https://github.com/apache/tvm/pull/18879#issuecomment-4009303355
## Summary of Changes Hello, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request enhances the robustness of TVM's Tensor IR (TIR) by enforcing type constraints on unary mathematical operations, specifically trigonometric and hyperbolic functions. By rejecting non-floating-point inputs at an earlier stage, it prevents potential runtime errors and provides clearer error messages to developers, streamlining the development process and improving the overall stability of the system. ### Highlights * **Type Checking for Trigonometric Operations**: Introduced strict type checking for trigonometric and hyperbolic unary operations (e.g., `tan`, `sin`, `cos`, `tanh`) in TVM's TIR, ensuring they only accept floating-point or bfloat16 inputs. * **Early Error Detection in Python**: Implemented an early type check in the Python TIR wrappers for these operations, causing `TypeError` to be raised immediately if a non-floating-point input is provided, improving user feedback. * **Regression Tests**: Added new regression tests to validate that both `tvm.tir` and `topi` versions of these operations correctly reject integer inputs. 🧠**New Feature in Public Preview:** You can now enable **Memory** to help **Gemini Code Assist** learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. **Click [here](https://codeassist.google/code-review/login) to enable Memory in your admin console.** <details> <summary><b>Changelog</b></summary> * **include/tvm/tir/op.h** * Added a new helper function `CheckMathUnaryOpInputDType` to verify if a given `DataType` is floating-point or bfloat16. * Refactored the `TVM_DECLARE_INTRIN_UNARY` macro into `TVM_DECLARE_FLOAT_INTRIN_UNARY` for math operations that require float inputs, integrating the new type check. * Applied `TVM_DECLARE_FLOAT_INTRIN_UNARY` to `tanh`, `tan`, `cos`, `cosh`, `sin`, `sinh`, `asin`, `acos`, `atan`, `acosh`, `asinh`, and `atanh`. * **python/tvm/tir/op.py** * Introduced a Python helper function `_require_float_arg` to perform early type checking for floating-point inputs. * Integrated `_require_float_arg` into the Python wrappers for `tanh`, `tan`, `cos`, `cosh`, `acos`, `acosh`, `sin`, `sinh`, `asin`, `asinh`, `atan`, and `atanh`. * **tests/python/tir-base/test_tir_constructor.py** * Imported `te` and `topi` modules for testing. * Added `test_math_unary_constructor_requires_float_dtype` to confirm `tvm.tir.tan` and `tvm.tir.sin` raise `TypeError` for integer inputs. * Added `test_topi_tan_requires_float_dtype` to verify `topi.tan` also raises `TypeError` for integer inputs. </details> <details> <summary><b>Activity</b></summary> * Local validation tests were executed, specifically targeting `test_tir_constructor.py` with relevant keywords to confirm the new type checking behavior. * The original issue (Fixes #18769) where `tan(int32)` would previously fail silently or with less clear errors, now fails early with a `TypeError` as intended. * Confirmed that `topi.tan(float32)` continues to build successfully with `target="llvm"`. </details> <details> <summary><b>Using Gemini Code Assist</b></summary> <br> The full guide for Gemini Code Assist can be found on our [documentation page](https://developers.google.com/gemini-code-assist/docs/review-github-code), here are some quick tips. <b>Invoking Gemini</b> You can request assistance from Gemini at any point by creating a comment using either `/gemini <command>` or `@gemini-code-assist <command>`. Below is a summary of the supported commands on the current page. Feature | Command | Description --- | --- | --- Code Review | `/gemini review` | Performs a code review for the current pull request in its current state. Pull Request Summary | `/gemini summary` | Provides a summary of the current pull request in its current state. Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in pull request comments and review comments. Help | `/gemini help` | Displays a list of available commands. <b>Customization</b> To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a `.gemini/` folder in the base of the repository. Detailed instructions can be found [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). <b>Limitations & Feedback</b> Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up [here](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG). <b>You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the [Gemini Code Assist IDE Extension](https://cloud.google.com/products/gemini/code-assist).</b> </details> [^1]: Review the [Privacy Notices](https://policies.google.com/privacy), [Generative AI Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of Service](https://policies.google.com/terms), and learn how to configure Gemini Code Assist in GitHub [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). Gemini can make mistakes, so double check it and [use code with caution](https://support.google.com/legal/answer/13505487). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
