Fix/pool negative pad validation

[Akshay Sonawane (apsonawane)]

This pull request strengthens validation for padding values in pooling operations to ensure they are non-negative, preventing invalid configurations and potential runtime errors. It also adds unit tests to verify that negative padding values are correctly rejected, both at the ONNX operator level and in the underlying MLAS pooling implementation.

Validation improvements:

• Added explicit checks in pool_attributes.h to enforce that all padding values (pads) are non-negative when auto_pad is not set, raising an error if this condition is violated.
• Updated pooling.cpp to throw a std::invalid_argument exception if any padding value is negative, providing an additional safeguard at the MLAS pooling layer.

Testing enhancements:

• Added new unit tests in pool_op_test.cc to verify that negative padding values cause the expected errors, both for the ONNX MaxPool operator and for the MLAS pooling backend.

[Copilot]

Pull request overview

This PR strengthens pooling padding validation across the CPU provider and MLAS to reject negative pad values (when auto_pad is not set), and adds targeted unit tests to ensure invalid configurations fail early with clear errors.

Changes:

• Add PoolAttributes validation to enforce non-negative pads when auto_pad == NOTSET.
• Add an MLAS-layer guard that throws std::invalid_argument when any padding value is negative.
• Add unit tests covering both the ORT MaxPool operator path and the MLAS MlasPool backend.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
onnxruntime/test/providers/cpu/nn/pool_op_test.cc	Adds regression tests ensuring negative pads are rejected at the ORT op level and (when exceptions are enabled) at the MLAS level.
onnxruntime/core/providers/cpu/nn/pool_attributes.h	Enforces non-negative pads for explicit padding to prevent invalid pooling configurations from reaching execution.
onnxruntime/core/mlas/lib/pooling.cpp	Adds a low-level validation check to reject negative padding values before MLAS pooling proceeds.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.