[Mlir-commits] [mlir] [MLIR][AMDGPU] Add amdgpu.sched_barrier (PR #98911)

[Lei Zhang]

================
@@ -433,6 +433,47 @@ def AMDGPU_LDSBarrierOp : AMDGPU_Op<"lds_barrier"> {
   let assemblyFormat = "attr-dict";
 }
 
+def AMDGPU_SchedBarrierOpOpt : I32EnumAttr<"sched_barrier_opt_enum",
----------------
antiagainst wrote:

I think we can use `I32BitEnumAttrCase` here? With that we can avoid the array in the below and it also have better direct assembly/parse/print support via the infra.

https://github.com/llvm/llvm-project/pull/98911