[CK_TILE] Generate random tensor values with multiple threads

[DDEle]

Proposed changes

ck_tile version of f9bf275 (merged with #2297)

Checklist

Please put an x into the boxes that apply. You can also fill these out after creating the PR. If you're not sure, please don't hesitate to ask.

• I have added tests relevant to the introduced functionality, and the unit tests are passing locally
• I have added the test to REGRESSION_TESTS list defined at the top of CMakeLists.txt in tests/CMakeLists.txt, IF the test takes more than 30 seconds to run.
• I have added inline documentation which enables the maintainers with understanding the motivation
• I have removed the stale documentation which is no longer relevant after this pull request
• (If this change is user-facing) I have added release notes which provide the end users with a brief summary of the improvement from this pull request
• I have run clang-format on all changed files
• Any dependent changes have been merged

[Copilot]

Pull request overview

This PR introduces multi-threaded random tensor value generation for the ck_tile library, replacing the previous single-threaded or opt-in multi-threaded approach with an always-on deterministic multi-threaded implementation. The changes ensure reproducible results across different thread counts by using a block-based distribution strategy with RNG state management via discard().

Key Changes

• Refactored FillUniformDistribution to always use multi-threading with deterministic block-based random number generation
• Added CPU core management utilities (get_available_cpu_cores() and cpu_core_guard) for testing different thread configurations
• Updated the template parameter to allow type deduction (T = void)

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 8 comments.

Show a summary per file

File	Description
include/ck_tile/host/fill.hpp	Replaced opt-in multi-threading with always-on deterministic block-based multi-threaded filling; changed template parameter to support type deduction
include/ck_tile/host/joinable_thread.hpp	Added get_available_cpu_cores() function and cpu_core_guard class for CPU affinity management in tests
test/ck_tile/utility/test_fill.cpp	New comprehensive test suite validating deterministic behavior across different sizes and thread counts
test/ck_tile/utility/CMakeLists.txt	Registered the new test executable
example/ck_tile/18_flatmm/mxgemm/run_mx_flatmm.inc	Updated to use new template syntax with type deduction

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.