[clang] [llvm] AMDGPU: Define v_mfma_f32_{16x16x128|32x32x64}_f8f6f4 instructions (PR #116723)

[Matt Arsenault via cfe-commits]

arsenm wrote:

### Merge activity

* **Nov 21, 11:47 AM EST**: A user started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/116723).


https://github.com/llvm/llvm-project/pull/116723