[Akshay Sonawane (apsonawane)]

This pull request introduces improvements to the handling and testing of string data in the ScatterND operator. The main changes include a fix to disable parallelization for string data types and the addition of new test cases to verify correct behavior with duplicate indices and string concatenation.

Improvements to string data handling:

• Disabled parallel execution (tp = nullptr) for std::string data types in the ScatterNDDispatchTarget struct to prevent potential issues with concurrent string operations.

Expanded test coverage:

• Added ScatterND_string_duplicate_indices test to verify that when duplicate indices are present, the last update value is used for string data.
• Added ScatterND_string_add_duplicate_indices test to verify that when the reduction attribute is set to "add", updates to the same string index are concatenated in order.

[Copilot]

Pull request overview

This PR improves CPU ScatterND behavior for string tensors by ensuring updates are applied serially (avoiding concurrent std::string mutation) and adds tests that validate deterministic behavior with duplicate indices, including "add" reduction concatenation order.

Changes:

• Disable TryParallelFor parallelism for std::string in the CPU ScatterND dispatch path by setting tp = nullptr.
• Add a test that validates “last update wins” for duplicate indices with string data.
• Add a test that validates "add" reduction concatenates strings in update order for duplicate indices.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
onnxruntime/core/providers/cpu/tensor/scatter_nd.cc	Disables parallel execution for string updates in ScatterNDDispatchTarget to avoid unsafe concurrent string operations.
onnxruntime/test/providers/cpu/tensor/scatter_nd_op_test.cc	Adds new string-focused tests covering duplicate indices with default reduction and "add" reduction.

---

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