[llvm] [AMDGPU] Support divergent sized dynamic alloca (PR #121148)

[Jay Foad via llvm-commits]

jayfoad wrote:

> Currently, AMDGPU backend supports static sized allocas.
> This patch extends support for truly dynamic sized allocas.

Update this description as well as the title.

https://github.com/llvm/llvm-project/pull/121148