================
@@ -1660,7 +2003,24 @@ static bool runImpl(Module &M, AnalysisGetter &AG,
TargetMachine &TM,
}
}
- return A.run() == ChangeStatus::CHANGED;
+ bool Changed = A.run() == ChangeStatus::CHANGED;
+
+ // Kernel attribute lowering (merged from AMDGPULowerKernelAttributesPass)
+ bool IsV5OrAbove =
+ AMDGPU::getAMDHSACodeObjectVersion(M) >= AMDGPU::AMDHSA_COV5;
----------------
shiltian wrote:
I still don't think this two should be merged, unless it can demonstrate how it
benefits from iterative running instead of just doing an update once and done.
https://github.com/llvm/llvm-project/pull/177432
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
