[llvm] [AMDGPU] Convert ds_bpermute/wave_shuffle XOR patterns to DPP row_xmask and permlanex16 (PR #194565)

[Pankaj Dwivedi via llvm-commits]

PankajDwivedi-25 wrote:

@arsenm we are continuing with single patch mentioned above. will drop this as our focus is now only https://github.com/llvm/llvm-project/pull/192246

https://github.com/llvm/llvm-project/pull/194565