[Mlir-commits] [mlir] [AMDGPU] Implement gpu.subgroup_reduce with DPP intrinsics on AMD GPUs (PR #133204)

[llvmlistbot at llvm.org]

Muzammiluddin-Syed-ECE wrote:

> I think you're in a good position to mark this for review, though I'd do some surgery to make `rocdl.permlanex16` a separate PR (leave it in this one temporarily though, unless you can make a stacked branch on llvm/llvm-project

I've made a [stacked branch](https://github.com/Muzammiluddin-Syed-ECE/llvm-project/pull/1) where I've moved the Permlanex16Op changes.

https://github.com/llvm/llvm-project/pull/133204