[Mlir-commits] [mlir] [mlir][amdgpu] Add `rocdl.s.waitcnt` wrapper (PR #149670)

[Ivan Butygin]

================
@@ -419,6 +419,52 @@ struct RawBufferOpLowering : public ConvertOpToLLVMPattern<GpuOp> {
   }
 };
 
+// TODO: AMDGPU backend already have all this bitpacking logic, we should move
+// it to some common place.
+static FailureOr<unsigned> encodeWaitcnt(Chipset chipset, unsigned vmcnt,
+                                         unsigned expcnt, unsigned lgkmcnt) {
+  if (chipset.majorVersion == 9) {
----------------
Hardcode84 wrote:

done (and also added all other chisets)

https://github.com/llvm/llvm-project/pull/149670