[llvm-branch-commits] [clang] clang/AMDGPU: Emit atomicrmw for flat/global atomic min/max f64 builtins (PR #96876)

[Matt Arsenault via llvm-branch-commits]

arsenm wrote:

### Merge activity

* **Aug 20, 2:53 PM EDT**: @arsenm started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/96876).


https://github.com/llvm/llvm-project/pull/96876