[Mlir-commits] [mlir] [MLIR][ROCDL] Add conversion for gpu.subgroup_id to ROCDL (PR #136405)

[Jakub Kuderski]

================
@@ -204,6 +204,15 @@ def ROCDL_ReadlaneOp : ROCDL_IntrOp<"readlane", [], [0], [AllTypesMatch<["res",
    }];
 }
 
+// The LLVM intrinsic function name is rather mouthful,
+// so here we opt to use a shorter rocdl name.
+def ROCDL_WaveIdOp :  LLVM_IntrOpBase<ROCDL_Dialect, "wave_id",
+                        "amdgcn_s_get_waveid_in_workgroup", [], [], [], 1>,
----------------
kuhar wrote:

If it was pure, you would be able to hoist it out of parallel loops before distribution to subgroups. I suspect it may be `IntrNoMem` in llvm because they can't represent higher-level programs

https://github.com/llvm/llvm-project/pull/136405