[llvm] [WIP][AMDGPU] Support the RF inline asm constraint (PR #195123)

[Jun Wang via llvm-commits]

================
@@ -10502,8 +10502,13 @@ static bool prepareDAGLevelOperands(ConstraintDecisionInfo &Info,
         assert((OpInfo.isIndirect ||
                 OpInfo.ConstraintType != TargetLowering::C_Memory) &&
                "Operand must be indirect to be a mem!");
+        unsigned AddrSpace = 0;
+        const Value *Ptr = OpInfo.CallOperandVal;
+        if (Ptr && Ptr->getType()->getTypeID() == Type::PointerTyID)
+          AddrSpace = cast<PointerType>(Ptr->getType())->getAddressSpace();
----------------
jwanggit86 wrote:

Fixed.

https://github.com/llvm/llvm-project/pull/195123