[rocm-libraries] ROCm/rocm-libraries#5921 (commit 032ac1b)

[CK] fix clang lifetimebound errors with staging compiler
 (#5921)

## Motivation

The ROCm staging compiler (newer Clang) enforces
`[[clang::lifetimebound]]` annotations on methods that return references
or pointers to internal object data. Without these annotations, the
staging compiler emits compilation errors for container accessor methods
across the CK and CK Tile namespaces.

  ## Technical Details

Adds `[[clang::lifetimebound]]` to all reference/pointer-returning
accessors in core container types:

  **`ck::` namespace:**
  - `Array` -- `At()`, `operator[]`, `operator()`, `begin()`, `end()`
  - `index_array` -- `operator[]`
  - `StaticallyIndexedArray_v2` -- `At()`, `operator[]`, `operator()`
  - `IndexLookupTable` -- `operator[]`

  **`ck_tile::` namespace:**
  - `array` -- `get(i)`, `at()`, `operator[]`, `operator()`
  - `static_array` -- `operator[]`
  - `thread_buffer` -- `get(i)`, `at()`, `operator[]`, `operator()`
  - `make_kernel()` -- parameter pack

Also removes the unused `instance_index` variable from
`batched_gemm_reduce_fp16.cpp` and simplifies its argument parsing
  accordingly.

  ## Test Plan

- Compile with the staging compiler to verify all lifetimebound errors
are resolved
- Existing tests pass unchanged -- the attribute is a compile-time
annotation with no runtime effect

 ## Test Result

<!-- Briefly summarize test outcomes. -->

## Submission Checklist

- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

include/ck_tile/host/kernel_launch.hpp

@@ -87,8 +87,11 @@ template <int MinBlockPerCu = CK_TILE_MIN_BLOCK_PER_CU,
           typename Attr     = void,
           typename KernelImpl,
           typename... Args>
-CK_TILE_HOST auto
-make_kernel(KernelImpl /*f*/, dim3 grid_dim, dim3 block_dim, std::size_t lds_byte, Args... args)
+CK_TILE_HOST auto make_kernel(KernelImpl /*f*/,
+                              dim3 grid_dim,
+                              dim3 block_dim,
+                              std::size_t lds_byte,
+                              [[clang::lifetimebound]] Args... args)
 {
     const auto kernel = []() {
         if constexpr(std::is_void_v<Attr>)