CodeGen: Emit string literal in constant address space

Some targets have constant address space (e.g. amdgcn). For them string literal should be
emitted in constant address space then casted to default address space.

Differential Revision: https://reviews.llvm.org/D46643

llvm-svn: 332279

4 files changed, 81 insertions, 12 deletions

diff --git a/clang/lib/CodeGen/CGDecl.cpp b/clang/lib/CodeGen/CGDecl.cpp
index 8c7bf882e7c..38282163eca 100644
--- a/clang/lib/CodeGen/CGDecl.cpp
+++ b/clang/lib/CodeGen/CGDecl.cpp
@@ -1374,7 +1374,7 @@ void CodeGenFunction::EmitAutoVarInit(const AutoVarEmission &emission) {
     llvm::ConstantInt::get(IntPtrTy,
                            getContext().getTypeSizeInChars(type).getQuantity());
 
-  llvm::Type *BP = AllocaInt8PtrTy;
+  llvm::Type *BP = CGM.Int8Ty->getPointerTo(Loc.getAddressSpace());
   if (Loc.getType() != BP)
     Loc = Builder.CreateBitCast(Loc, BP);
 
@@ -1395,11 +1395,10 @@ void CodeGenFunction::EmitAutoVarInit(const AutoVarEmission &emission) {
     // Otherwise, create a temporary global with the initializer then
     // memcpy from the global to the alloca.
     std::string Name = getStaticDeclName(CGM, D);
-    unsigned AS = 0;
-    if (getLangOpts().OpenCL) {
-      AS = CGM.getContext().getTargetAddressSpace(LangAS::opencl_constant);
-      BP = llvm::PointerType::getInt8PtrTy(getLLVMContext(), AS);
-    }
+    unsigned AS = CGM.getContext().getTargetAddressSpace(
+        CGM.getStringLiteralAddressSpace());
+    BP = llvm::PointerType::getInt8PtrTy(getLLVMContext(), AS);
+
     llvm::GlobalVariable *GV =
       new llvm::GlobalVariable(CGM.getModule(), constant->getType(), true,
                                llvm::GlobalValue::PrivateLinkage,
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index 3a27d999352..50b653c70ff 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -3044,6 +3044,39 @@ LangAS CodeGenModule::GetGlobalVarAddressSpace(const VarDecl *D) {
   return getTargetCodeGenInfo().getGlobalVarAddressSpace(*this, D);
 }
 
+LangAS CodeGenModule::getStringLiteralAddressSpace() const {
+  // OpenCL v1.2 s6.5.3: a string literal is in the constant address space.
+  if (LangOpts.OpenCL)
+    return LangAS::opencl_constant;
+  if (auto AS = getTarget().getConstantAddressSpace())
+    return AS.getValue();
+  return LangAS::Default;
+}
+
+// In address space agnostic languages, string literals are in default address
+// space in AST. However, certain targets (e.g. amdgcn) request them to be
+// emitted in constant address space in LLVM IR. To be consistent with other
+// parts of AST, string literal global variables in constant address space
+// need to be casted to default address space before being put into address
+// map and referenced by other part of CodeGen.
+// In OpenCL, string literals are in constant address space in AST, therefore
+// they should not be casted to default address space.
+static llvm::Constant *
+castStringLiteralToDefaultAddressSpace(CodeGenModule &CGM,
+                                       llvm::GlobalVariable *GV) {
+  llvm::Constant *Cast = GV;
+  if (!CGM.getLangOpts().OpenCL) {
+    if (auto AS = CGM.getTarget().getConstantAddressSpace()) {
+      if (AS != LangAS::Default)
+        Cast = CGM.getTargetCodeGenInfo().performAddrSpaceCast(
+            CGM, GV, AS.getValue(), LangAS::Default,
+            GV->getValueType()->getPointerTo(
+                CGM.getContext().getTargetAddressSpace(LangAS::Default)));
+    }
+  }
+  return Cast;
+}
+
 template<typename SomeDecl>
 void CodeGenModule::MaybeHandleStaticInExternC(const SomeDecl *D,
                                                llvm::GlobalValue *GV) {
@@ -4039,10 +4072,8 @@ static llvm::GlobalVariable *
 GenerateStringLiteral(llvm::Constant *C, llvm::GlobalValue::LinkageTypes LT,
                       CodeGenModule &CGM, StringRef GlobalName,
                       CharUnits Alignment) {
-  // OpenCL v1.2 s6.5.3: a string literal is in the constant address space.
-  unsigned AddrSpace = 0;
-  if (CGM.getLangOpts().OpenCL)
-    AddrSpace = CGM.getContext().getTargetAddressSpace(LangAS::opencl_constant);
+  unsigned AddrSpace = CGM.getContext().getTargetAddressSpace(
+      CGM.getStringLiteralAddressSpace());
 
   llvm::Module &M = CGM.getModule();
   // Create a global variable for this string
@@ -4104,7 +4135,9 @@ CodeGenModule::GetAddrOfConstantStringFromLiteral(const StringLiteral *S,
 
   SanitizerMD->reportGlobalToASan(GV, S->getStrTokenLoc(0), "<string literal>",
                                   QualType());
-  return ConstantAddress(GV, Alignment);
+
+  return ConstantAddress(castStringLiteralToDefaultAddressSpace(*this, GV),
+                         Alignment);
 }
 
 /// GetAddrOfConstantStringFromObjCEncode - Return a pointer to a constant
@@ -4148,7 +4181,9 @@ ConstantAddress CodeGenModule::GetAddrOfConstantCString(
                                   GlobalName, Alignment);
   if (Entry)
     *Entry = GV;
-  return ConstantAddress(GV, Alignment);
+
+  return ConstantAddress(castStringLiteralToDefaultAddressSpace(*this, GV),
+                         Alignment);
 }
 
 ConstantAddress CodeGenModule::GetAddrOfGlobalTemporary(
diff --git a/clang/lib/CodeGen/CodeGenModule.h b/clang/lib/CodeGen/CodeGenModule.h
index 04a9f64e60e..961bae324d3 100644
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/lib/CodeGen/CodeGenModule.h
@@ -785,6 +785,13 @@ public:
                                      ForDefinition_t IsForDefinition
                                        = NotForDefinition);
 
+  /// Return the AST address space of string literal, which is used to emit
+  /// the string literal as global variable in LLVM IR.
+  /// Note: This is not necessarily the address space of the string literal
+  /// in AST. For address space agnostic language, e.g. C++, string literal
+  /// in AST is always in default address space.
+  LangAS getStringLiteralAddressSpace() const;
+
   /// Return the address of the given function. If Ty is non-null, then this
   /// function will use the specified type if it has to create it.
   llvm::Constant *GetAddrOfFunction(GlobalDecl GD, llvm::Type *Ty = nullptr,
diff --git a/clang/test/CodeGenCXX/amdgcn-string-literal.cpp b/clang/test/CodeGenCXX/amdgcn-string-literal.cpp
new file mode 100644
index 00000000000..7fd05351c86
--- /dev/null
+++ b/clang/test/CodeGenCXX/amdgcn-string-literal.cpp
@@ -0,0 +1,28 @@
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm %s -o - | FileCheck %s
+
+// CHECK: @.str = private unnamed_addr addrspace(4) constant [6 x i8] c"g_str\00", align 1
+// CHECK: @g_str = addrspace(1) global i8* addrspacecast (i8 addrspace(4)* getelementptr inbounds ([6 x i8], [6 x i8] addrspace(4)* @.str, i32 0, i32 0) to i8*), align 8
+// CHECK: @g_array = addrspace(1) global [8 x i8] c"g_array\00", align 1
+// CHECK: @.str.1 = private unnamed_addr addrspace(4) constant [6 x i8] c"l_str\00", align 1
+// CHECK: @_ZZ1fvE7l_array = private unnamed_addr addrspace(4) constant [8 x i8] c"l_array\00", align 1
+
+const char* g_str = "g_str";
+char g_array[] = "g_array";
+
+void g(const char* p);
+
+// CHECK-LABEL: define void @_Z1fv()
+void f() {
+  const char* l_str = "l_str";
+  
+  // CHECK: call void @llvm.memcpy.p0i8.p4i8.i64
+  char l_array[] = "l_array";
+
+  g(g_str);
+  g(g_array);
+  g(l_str);
+  g(l_array);
+
+  const char* p = g_str;
+  g(p);
+}