Handle passing an allocaed sret arg directly to a callee that expects a pointer to the default AS.

Author: AlexVlx

clang/lib/CodeGen/CGCall.cpp

@@ -5391,11 +5391,19 @@ RValue CodeGenFunction::EmitCall(const CGFunctionInfo &CallInfo,
             V->getType()->isIntegerTy())
           V = Builder.CreateZExt(V, ArgInfo.getCoerceToType());
 
-        // If the argument doesn't match, perform a bitcast to coerce it.  This
-        // can happen due to trivial type mismatches.
+        // If the argument doesn't match, we are either trying to pass an
+        // alloca-ed sret argument directly, and the alloca AS does not match
+        // the default AS, case in which we AS cast it, or we have a trivial
+        // type mismatch, and thus perform a bitcast to coerce it.
         if (FirstIRArg < IRFuncTy->getNumParams() &&
-            V->getType() != IRFuncTy->getParamType(FirstIRArg))
-          V = Builder.CreateBitCast(V, IRFuncTy->getParamType(FirstIRArg));
+            V->getType() != IRFuncTy->getParamType(FirstIRArg)) {
+          auto IRTy = IRFuncTy->getParamType(FirstIRArg);
+          auto MaybeSRetArg = dyn_cast_or_null<llvm::Argument>(V);
+          if (MaybeSRetArg && MaybeSRetArg->hasStructRetAttr())
+            V = Builder.CreateAddrSpaceCast(V, IRTy);
+          else
+            V = Builder.CreateBitCast(V, IRTy);
+        }
 
         if (ArgHasMaybeUndefAttr)
           V = Builder.CreateFreeze(V);

clang/test/CodeGenCXX/no-elide-constructors.cpp

@@ -1,7 +1,9 @@
 // RUN: %clang_cc1 -std=c++98 -triple i386-unknown-unknown -fno-elide-constructors -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CXX98
 // RUN: %clang_cc1 -std=c++11 -triple i386-unknown-unknown -fno-elide-constructors -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CXX11
+// RUN: %clang_cc1 -std=c++11 -triple amdgcn-amd-amdhsa -fno-elide-constructors -emit-llvm -o - %s | FileCheck %s --check-prefixes=CHECK --check-prefix=CHECK-CXX11-NONZEROALLOCAAS
 // RUN: %clang_cc1 -std=c++98 -triple i386-unknown-unknown -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CXX98-ELIDE
 // RUN: %clang_cc1 -std=c++11 -triple i386-unknown-unknown -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CXX11-ELIDE
+// RUN: %clang_cc1 -std=c++11 -triple amdgcn-amd-amdhsa -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-CXX11-NONZEROALLOCAAS-ELIDE
 
 // Reduced from PR12208
 class X {
@@ -23,8 +25,10 @@ X Test()
   // sret argument.
   // CHECK-CXX98: call void @_ZN1XC1ERKS_(
   // CHECK-CXX11: call void @_ZN1XC1EOS_(
+  // CHECK-CXX11-NONZEROALLOCAAS: call void @_ZN1XC1EOS_(
   // CHECK-CXX98-ELIDE-NOT: call void @_ZN1XC1ERKS_(
   // CHECK-CXX11-ELIDE-NOT: call void @_ZN1XC1EOS_(
+  // CHECK-CXX11-NONZEROALLOCAAS-ELIDE-NOT: call void @_ZN1XC1EOS_(
 
   // Make sure that the destructor for X is called.
   // FIXME: This call is present even in the -ELIDE runs, but is guarded by a