[llvm] [AMDGPU] DAG Mutation to solve load bunching in outer product matrix multiplications (PR #203095)

[Zeng Wu via llvm-commits]

zwu-2025 wrote:

Please make sure 
clang-format is applied and a simple input MIR file with expected output MIR added in the patch, 
as discussed offline.

https://github.com/llvm/llvm-project/pull/203095