Handle empty CPU LpNormalization inputs

[Akshay Sonawane (apsonawane)]

This pull request adds handling and tests for cases where the LpNormalization operator receives input tensors with zero elements along the normalization axis. The main changes include an early return in the implementation to avoid unnecessary computation and a new test to verify correct behavior for zero-extent axes.

LpNormalization operator improvements:

• Added an early return in LpNorm<T>::Compute to immediately return success when the input tensor has zero elements, preventing unnecessary computation for empty inputs.

Testing enhancements:

• Introduced the LpNormalizationZeroExtentAxis test, which checks that the operator correctly handles input tensors with a zero-extent axis for both p=1 and p=2, and for both float and double types.

[Copilot]

Pull request overview

This pull request updates the CPU implementation of the LpNormalization operator to correctly handle empty inputs (zero total elements due to a zero-extent dimension), avoiding invalid normalization math (e.g., division by zero) and adding a regression test to ensure the behavior remains correct.

Changes:

• Added an early return in LpNorm<T>::Compute when input_shape.Size() == 0 to safely bypass normalization work for empty tensors.
• Added a CPU-only unit test covering a zero-extent normalization axis for p = 1 and p = 2, for both float and double.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
onnxruntime/core/providers/cpu/nn/lp_norm.cc	Early-return for empty tensors to prevent invalid normalization computations and unnecessary work.
onnxruntime/test/providers/cpu/nn/lp_norm_op_test.cc	Adds a regression test ensuring LpNormalization succeeds with a zero-extent axis (empty tensor) on CPU.

---

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