vendor/clang/clang-trunk-r307894

19 files changed, 242 insertions, 358 deletions

diff --git a/lib/CodeGen/BackendUtil.cpp b/lib/CodeGen/BackendUtil.cpp
index 9b3850abcce7c..513896d986345 100644
--- a/lib/CodeGen/BackendUtil.cpp
+++ b/lib/CodeGen/BackendUtil.cpp
@@ -998,7 +998,7 @@ static void runThinLTOBackend(ModuleSummaryIndex *CombinedIndex, Module *M,
                               std::unique_ptr<raw_pwrite_stream> OS,
                               std::string SampleProfile,
                               BackendAction Action) {
-  StringMap<std::map<GlobalValue::GUID, GlobalValueSummary *>>
+  StringMap<DenseMap<GlobalValue::GUID, GlobalValueSummary *>>
       ModuleToDefinedGVSummaries;
   CombinedIndex->collectDefinedGVSummariesPerModule(ModuleToDefinedGVSummaries);
 
diff --git a/lib/CodeGen/CGBlocks.cpp b/lib/CodeGen/CGBlocks.cpp
index 528a2b33acf86..1810489578798 100644
--- a/lib/CodeGen/CGBlocks.cpp
+++ b/lib/CodeGen/CGBlocks.cpp
@@ -736,9 +736,9 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
   llvm::Constant *isa =
       (!CGM.getContext().getLangOpts().OpenCL)
           ? CGM.getNSConcreteStackBlock()
-          : CGM.getNullPointer(cast<llvm::PointerType>(
-                                   CGM.getNSConcreteStackBlock()->getType()),
-                               QualType(getContext().VoidPtrTy));
+          : CGM.getNullPointer(VoidPtrPtrTy,
+                               CGM.getContext().getPointerType(
+                                   QualType(CGM.getContext().VoidPtrTy)));
   isa = llvm::ConstantExpr::getBitCast(isa, VoidPtrTy);
 
   // Build the block descriptor.
@@ -1141,12 +1141,11 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
   auto fields = builder.beginStruct();
 
   // isa
-  fields.add(
-      (!CGM.getContext().getLangOpts().OpenCL)
-          ? CGM.getNSConcreteGlobalBlock()
-          : CGM.getNullPointer(cast<llvm::PointerType>(
-                                   CGM.getNSConcreteGlobalBlock()->getType()),
-                               QualType(CGM.getContext().VoidPtrTy)));
+  fields.add((!CGM.getContext().getLangOpts().OpenCL)
+                 ? CGM.getNSConcreteGlobalBlock()
+                 : CGM.getNullPointer(CGM.VoidPtrPtrTy,
+                                      CGM.getContext().getPointerType(QualType(
+                                          CGM.getContext().VoidPtrTy))));
 
   // __flags
   BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE;
@@ -1255,7 +1254,7 @@ CodeGenFunction::GenerateBlockFunction(GlobalDecl GD,
 
   // For OpenCL passed block pointer can be private AS local variable or
   // global AS program scope variable (for the case with and without captures).
-  // Generic AS is used therefore to be able to accomodate both private and
+  // Generic AS is used therefore to be able to accommodate both private and
   // generic AS in one implementation.
   if (getLangOpts().OpenCL)
     selfTy = getContext().getPointerType(getContext().getAddrSpaceQualType(
diff --git a/lib/CodeGen/CGBuiltin.cpp b/lib/CodeGen/CGBuiltin.cpp
index 2a6e92e7f3ce9..bc902507c46e5 100644
--- a/lib/CodeGen/CGBuiltin.cpp
+++ b/lib/CodeGen/CGBuiltin.cpp
@@ -1810,12 +1810,12 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
   case Builtin::BI__atomic_signal_fence:
   case Builtin::BI__c11_atomic_thread_fence:
   case Builtin::BI__c11_atomic_signal_fence: {
-    llvm::SynchronizationScope Scope;
+    llvm::SyncScope::ID SSID;
     if (BuiltinID == Builtin::BI__atomic_signal_fence ||
         BuiltinID == Builtin::BI__c11_atomic_signal_fence)
-      Scope = llvm::SingleThread;
+      SSID = llvm::SyncScope::SingleThread;
     else
-      Scope = llvm::CrossThread;
+      SSID = llvm::SyncScope::System;
     Value *Order = EmitScalarExpr(E->getArg(0));
     if (isa<llvm::ConstantInt>(Order)) {
       int ord = cast<llvm::ConstantInt>(Order)->getZExtValue();
@@ -1825,17 +1825,16 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
         break;
       case 1:  // memory_order_consume
       case 2:  // memory_order_acquire
-        Builder.CreateFence(llvm::AtomicOrdering::Acquire, Scope);
+        Builder.CreateFence(llvm::AtomicOrdering::Acquire, SSID);
         break;
       case 3:  // memory_order_release
-        Builder.CreateFence(llvm::AtomicOrdering::Release, Scope);
+        Builder.CreateFence(llvm::AtomicOrdering::Release, SSID);
         break;
       case 4:  // memory_order_acq_rel
-        Builder.CreateFence(llvm::AtomicOrdering::AcquireRelease, Scope);
+        Builder.CreateFence(llvm::AtomicOrdering::AcquireRelease, SSID);
         break;
       case 5:  // memory_order_seq_cst
-        Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent,
-                            Scope);
+        Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent, SSID);
         break;
       }
       return RValue::get(nullptr);
@@ -1852,23 +1851,23 @@ RValue CodeGenFunction::EmitBuiltinExpr(const FunctionDecl *FD,
     llvm::SwitchInst *SI = Builder.CreateSwitch(Order, ContBB);
 
     Builder.SetInsertPoint(AcquireBB);
-    Builder.CreateFence(llvm::AtomicOrdering::Acquire, Scope);
+    Builder.CreateFence(llvm::AtomicOrdering::Acquire, SSID);
     Builder.CreateBr(ContBB);
     SI->addCase(Builder.getInt32(1), AcquireBB);
     SI->addCase(Builder.getInt32(2), AcquireBB);
 
     Builder.SetInsertPoint(ReleaseBB);
-    Builder.CreateFence(llvm::AtomicOrdering::Release, Scope);
+    Builder.CreateFence(llvm::AtomicOrdering::Release, SSID);
     Builder.CreateBr(ContBB);
     SI->addCase(Builder.getInt32(3), ReleaseBB);
 
     Builder.SetInsertPoint(AcqRelBB);
-    Builder.CreateFence(llvm::AtomicOrdering::AcquireRelease, Scope);
+    Builder.CreateFence(llvm::AtomicOrdering::AcquireRelease, SSID);
     Builder.CreateBr(ContBB);
     SI->addCase(Builder.getInt32(4), AcqRelBB);
 
     Builder.SetInsertPoint(SeqCstBB);
-    Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent, Scope);
+    Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent, SSID);
     Builder.CreateBr(ContBB);
     SI->addCase(Builder.getInt32(5), SeqCstBB);
 
@@ -2956,9 +2955,8 @@ static llvm::VectorType *GetNeonType(CodeGenFunction *CGF,
     return llvm::VectorType::get(CGF->Int8Ty, V1Ty ? 1 : (8 << IsQuad));
   case NeonTypeFlags::Int16:
   case NeonTypeFlags::Poly16:
-    return llvm::VectorType::get(CGF->Int16Ty, V1Ty ? 1 : (4 << IsQuad));
   case NeonTypeFlags::Float16:
-    return llvm::VectorType::get(CGF->HalfTy, V1Ty ? 1 : (4 << IsQuad));
+    return llvm::VectorType::get(CGF->Int16Ty, V1Ty ? 1 : (4 << IsQuad));
   case NeonTypeFlags::Int32:
     return llvm::VectorType::get(CGF->Int32Ty, V1Ty ? 1 : (2 << IsQuad));
   case NeonTypeFlags::Int64:
@@ -2981,8 +2979,6 @@ static llvm::VectorType *GetFloatNeonType(CodeGenFunction *CGF,
                                           NeonTypeFlags IntTypeFlags) {
   int IsQuad = IntTypeFlags.isQuad();
   switch (IntTypeFlags.getEltType()) {
-  case NeonTypeFlags::Int16:
-    return llvm::VectorType::get(CGF->HalfTy, (4 << IsQuad));
   case NeonTypeFlags::Int32:
     return llvm::VectorType::get(CGF->FloatTy, (2 << IsQuad));
   case NeonTypeFlags::Int64:
@@ -3130,80 +3126,55 @@ static const NeonIntrinsicInfo ARMSIMDIntrinsicMap [] = {
   NEONMAP1(vcvt_f16_f32, arm_neon_vcvtfp2hf, 0),
   NEONMAP1(vcvt_f32_f16, arm_neon_vcvthf2fp, 0),
   NEONMAP0(vcvt_f32_v),
-  NEONMAP2(vcvt_n_f16_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
   NEONMAP2(vcvt_n_f32_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
-  NEONMAP1(vcvt_n_s16_v, arm_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvt_n_s32_v, arm_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvt_n_s64_v, arm_neon_vcvtfp2fxs, 0),
-  NEONMAP1(vcvt_n_u16_v, arm_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvt_n_u32_v, arm_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvt_n_u64_v, arm_neon_vcvtfp2fxu, 0),
-  NEONMAP0(vcvt_s16_v),
   NEONMAP0(vcvt_s32_v),
   NEONMAP0(vcvt_s64_v),
-  NEONMAP0(vcvt_u16_v),
   NEONMAP0(vcvt_u32_v),
   NEONMAP0(vcvt_u64_v),
-  NEONMAP1(vcvta_s16_v, arm_neon_vcvtas, 0),
   NEONMAP1(vcvta_s32_v, arm_neon_vcvtas, 0),
   NEONMAP1(vcvta_s64_v, arm_neon_vcvtas, 0),
   NEONMAP1(vcvta_u32_v, arm_neon_vcvtau, 0),
   NEONMAP1(vcvta_u64_v, arm_neon_vcvtau, 0),
-  NEONMAP1(vcvtaq_s16_v, arm_neon_vcvtas, 0),
   NEONMAP1(vcvtaq_s32_v, arm_neon_vcvtas, 0),
   NEONMAP1(vcvtaq_s64_v, arm_neon_vcvtas, 0),
-  NEONMAP1(vcvtaq_u16_v, arm_neon_vcvtau, 0),
   NEONMAP1(vcvtaq_u32_v, arm_neon_vcvtau, 0),
   NEONMAP1(vcvtaq_u64_v, arm_neon_vcvtau, 0),
-  NEONMAP1(vcvtm_s16_v, arm_neon_vcvtms, 0),
   NEONMAP1(vcvtm_s32_v, arm_neon_vcvtms, 0),
   NEONMAP1(vcvtm_s64_v, arm_neon_vcvtms, 0),
-  NEONMAP1(vcvtm_u16_v, arm_neon_vcvtmu, 0),
   NEONMAP1(vcvtm_u32_v, arm_neon_vcvtmu, 0),
   NEONMAP1(vcvtm_u64_v, arm_neon_vcvtmu, 0),
-  NEONMAP1(vcvtmq_s16_v, arm_neon_vcvtms, 0),
   NEONMAP1(vcvtmq_s32_v, arm_neon_vcvtms, 0),
   NEONMAP1(vcvtmq_s64_v, arm_neon_vcvtms, 0),
-  NEONMAP1(vcvtmq_u16_v, arm_neon_vcvtmu, 0),
   NEONMAP1(vcvtmq_u32_v, arm_neon_vcvtmu, 0),
   NEONMAP1(vcvtmq_u64_v, arm_neon_vcvtmu, 0),
-  NEONMAP1(vcvtn_s16_v, arm_neon_vcvtns, 0),
   NEONMAP1(vcvtn_s32_v, arm_neon_vcvtns, 0),
   NEONMAP1(vcvtn_s64_v, arm_neon_vcvtns, 0),
-  NEONMAP1(vcvtn_u16_v, arm_neon_vcvtnu, 0),
   NEONMAP1(vcvtn_u32_v, arm_neon_vcvtnu, 0),
   NEONMAP1(vcvtn_u64_v, arm_neon_vcvtnu, 0),
-  NEONMAP1(vcvtnq_s16_v, arm_neon_vcvtns, 0),
   NEONMAP1(vcvtnq_s32_v, arm_neon_vcvtns, 0),
   NEONMAP1(vcvtnq_s64_v, arm_neon_vcvtns, 0),
-  NEONMAP1(vcvtnq_u16_v, arm_neon_vcvtnu, 0),
   NEONMAP1(vcvtnq_u32_v, arm_neon_vcvtnu, 0),
   NEONMAP1(vcvtnq_u64_v, arm_neon_vcvtnu, 0),
-  NEONMAP1(vcvtp_s16_v, arm_neon_vcvtps, 0),
   NEONMAP1(vcvtp_s32_v, arm_neon_vcvtps, 0),
   NEONMAP1(vcvtp_s64_v, arm_neon_vcvtps, 0),
-  NEONMAP1(vcvtp_u16_v, arm_neon_vcvtpu, 0),
   NEONMAP1(vcvtp_u32_v, arm_neon_vcvtpu, 0),
   NEONMAP1(vcvtp_u64_v, arm_neon_vcvtpu, 0),
-  NEONMAP1(vcvtpq_s16_v, arm_neon_vcvtps, 0),
   NEONMAP1(vcvtpq_s32_v, arm_neon_vcvtps, 0),
   NEONMAP1(vcvtpq_s64_v, arm_neon_vcvtps, 0),
-  NEONMAP1(vcvtpq_u16_v, arm_neon_vcvtpu, 0),
   NEONMAP1(vcvtpq_u32_v, arm_neon_vcvtpu, 0),
   NEONMAP1(vcvtpq_u64_v, arm_neon_vcvtpu, 0),
   NEONMAP0(vcvtq_f32_v),
-  NEONMAP2(vcvtq_n_f16_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
   NEONMAP2(vcvtq_n_f32_v, arm_neon_vcvtfxu2fp, arm_neon_vcvtfxs2fp, 0),
-  NEONMAP1(vcvtq_n_s16_v, arm_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvtq_n_s32_v, arm_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvtq_n_s64_v, arm_neon_vcvtfp2fxs, 0),
-  NEONMAP1(vcvtq_n_u16_v, arm_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvtq_n_u32_v, arm_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvtq_n_u64_v, arm_neon_vcvtfp2fxu, 0),
-  NEONMAP0(vcvtq_s16_v),
   NEONMAP0(vcvtq_s32_v),
   NEONMAP0(vcvtq_s64_v),
-  NEONMAP0(vcvtq_u16_v),
   NEONMAP0(vcvtq_u32_v),
   NEONMAP0(vcvtq_u64_v),
   NEONMAP0(vext_v),
@@ -3366,27 +3337,19 @@ static const NeonIntrinsicInfo AArch64SIMDIntrinsicMap[] = {
   NEONMAP1(vcnt_v, ctpop, Add1ArgType),
   NEONMAP1(vcntq_v, ctpop, Add1ArgType),
   NEONMAP1(vcvt_f16_f32, aarch64_neon_vcvtfp2hf, 0),
-  NEONMAP0(vcvt_f16_v),
   NEONMAP1(vcvt_f32_f16, aarch64_neon_vcvthf2fp, 0),
   NEONMAP0(vcvt_f32_v),
-  NEONMAP2(vcvt_n_f16_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
   NEONMAP2(vcvt_n_f32_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
   NEONMAP2(vcvt_n_f64_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
-  NEONMAP1(vcvt_n_s16_v, aarch64_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvt_n_s32_v, aarch64_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvt_n_s64_v, aarch64_neon_vcvtfp2fxs, 0),
-  NEONMAP1(vcvt_n_u16_v, aarch64_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvt_n_u32_v, aarch64_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvt_n_u64_v, aarch64_neon_vcvtfp2fxu, 0),
-  NEONMAP0(vcvtq_f16_v),
   NEONMAP0(vcvtq_f32_v),
-  NEONMAP2(vcvtq_n_f16_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
   NEONMAP2(vcvtq_n_f32_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
   NEONMAP2(vcvtq_n_f64_v, aarch64_neon_vcvtfxu2fp, aarch64_neon_vcvtfxs2fp, 0),
-  NEONMAP1(vcvtq_n_s16_v, aarch64_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvtq_n_s32_v, aarch64_neon_vcvtfp2fxs, 0),
   NEONMAP1(vcvtq_n_s64_v, aarch64_neon_vcvtfp2fxs, 0),
-  NEONMAP1(vcvtq_n_u16_v, aarch64_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvtq_n_u32_v, aarch64_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvtq_n_u64_v, aarch64_neon_vcvtfp2fxu, 0),
   NEONMAP1(vcvtx_f32_v, aarch64_neon_fcvtxn, AddRetType | Add1ArgType),
@@ -3855,20 +3818,9 @@ Value *CodeGenFunction::EmitCommonNeonBuiltinExpr(
   case NEON::BI__builtin_neon_vcageq_v:
   case NEON::BI__builtin_neon_vcagt_v:
   case NEON::BI__builtin_neon_vcagtq_v: {
-    llvm::Type *Ty;
-    switch (VTy->getScalarSizeInBits()) {
-    default: llvm_unreachable("unexpected type");
-    case 32:
-      Ty = FloatTy;
-      break;
-    case 64:
-      Ty = DoubleTy;
-      break;
-    case 16:
-      Ty = HalfTy;
-      break;
-    }
-    llvm::Type *VecFlt = llvm::VectorType::get(Ty, VTy->getNumElements());
+    llvm::Type *VecFlt = llvm::VectorType::get(
+        VTy->getScalarSizeInBits() == 32 ? FloatTy : DoubleTy,
+        VTy->getNumElements());
     llvm::Type *Tys[] = { VTy, VecFlt };
     Function *F = CGM.getIntrinsic(LLVMIntrinsic, Tys);
     return EmitNeonCall(F, Ops, NameHint);
@@ -3885,16 +3837,8 @@ Value *CodeGenFunction::EmitCommonNeonBuiltinExpr(
     Ty = GetNeonType(this, NeonTypeFlags(NeonTypeFlags::Float32, false, Quad));
     return Usgn ? Builder.CreateUIToFP(Ops[0], Ty, "vcvt")
                 : Builder.CreateSIToFP(Ops[0], Ty, "vcvt");
-  case NEON::BI__builtin_neon_vcvt_f16_v:
-  case NEON::BI__builtin_neon_vcvtq_f16_v:
-    Ops[0] = Builder.CreateBitCast(Ops[0], Ty);
-    Ty = GetNeonType(this, NeonTypeFlags(NeonTypeFlags::Float16, false, Quad));
-    return Usgn ? Builder.CreateUIToFP(Ops[0], Ty, "vcvt")
-                : Builder.CreateSIToFP(Ops[0], Ty, "vcvt");
-  case NEON::BI__builtin_neon_vcvt_n_f16_v:
   case NEON::BI__builtin_neon_vcvt_n_f32_v:
   case NEON::BI__builtin_neon_vcvt_n_f64_v:
-  case NEON::BI__builtin_neon_vcvtq_n_f16_v:
   case NEON::BI__builtin_neon_vcvtq_n_f32_v:
   case NEON::BI__builtin_neon_vcvtq_n_f64_v: {
     llvm::Type *Tys[2] = { GetFloatNeonType(this, Type), Ty };
@@ -3902,15 +3846,11 @@ Value *CodeGenFunction::EmitCommonNeonBuiltinExpr(
     Function *F = CGM.getIntrinsic(Int, Tys);
     return EmitNeonCall(F, Ops, "vcvt_n");
   }
-  case NEON::BI__builtin_neon_vcvt_n_s16_v:
   case NEON::BI__builtin_neon_vcvt_n_s32_v:
-  case NEON::BI__builtin_neon_vcvt_n_u16_v:
   case NEON::BI__builtin_neon_vcvt_n_u32_v:
   case NEON::BI__builtin_neon_vcvt_n_s64_v:
   case NEON::BI__builtin_neon_vcvt_n_u64_v:
-  case NEON::BI__builtin_neon_vcvtq_n_s16_v:
   case NEON::BI__builtin_neon_vcvtq_n_s32_v:
-  case NEON::BI__builtin_neon_vcvtq_n_u16_v:
   case NEON::BI__builtin_neon_vcvtq_n_u32_v:
   case NEON::BI__builtin_neon_vcvtq_n_s64_v:
   case NEON::BI__builtin_neon_vcvtq_n_u64_v: {
@@ -3922,63 +3862,44 @@ Value *CodeGenFunction::EmitCommonNeonBuiltinExpr(
   case NEON::BI__builtin_neon_vcvt_u32_v:
   case NEON::BI__builtin_neon_vcvt_s64_v:
   case NEON::BI__builtin_neon_vcvt_u64_v:
-  case NEON::BI__builtin_neon_vcvt_s16_v:
-  case NEON::BI__builtin_neon_vcvt_u16_v:
   case NEON::BI__builtin_neon_vcvtq_s32_v:
   case NEON::BI__builtin_neon_vcvtq_u32_v:
   case NEON::BI__builtin_neon_vcvtq_s64_v:
-  case NEON::BI__builtin_neon_vcvtq_u64_v:
-  case NEON::BI__builtin_neon_vcvtq_s16_v:
-  case NEON::BI__builtin_neon_vcvtq_u16_v: {
+  case NEON::BI__builtin_neon_vcvtq_u64_v: {
     Ops[0] = Builder.CreateBitCast(Ops[0], GetFloatNeonType(this, Type));
     return Usgn ? Builder.CreateFPToUI(Ops[0], Ty, "vcvt")
                 : Builder.CreateFPToSI(Ops[0], Ty, "vcvt");
   }
-  case NEON::BI__builtin_neon_vcvta_s16_v:
   case NEON::BI__builtin_neon_vcvta_s32_v:
   case NEON::BI__builtin_neon_vcvta_s64_v:
   case NEON::BI__builtin_neon_vcvta_u32_v:
   case NEON::BI__builtin_neon_vcvta_u64_v:
-  case NEON::BI__builtin_neon_vcvtaq_s16_v:
   case NEON::BI__builtin_neon_vcvtaq_s32_v:
   case NEON::BI__builtin_neon_vcvtaq_s64_v:
-  case NEON::BI__builtin_neon_vcvtaq_u16_v:
   case NEON::BI__builtin_neon_vcvtaq_u32_v:
   case NEON::BI__builtin_neon_vcvtaq_u64_v:
-  case NEON::BI__builtin_neon_vcvtn_s16_v:
   case NEON::BI__builtin_neon_vcvtn_s32_v:
   case NEON::BI__builtin_neon_vcvtn_s64_v:
-  case NEON::BI__builtin_neon_vcvtn_u16_v:
   case NEON::BI__builtin_neon_vcvtn_u32_v:
   case NEON::BI__builtin_neon_vcvtn_u64_v:
-  case NEON::BI__builtin_neon_vcvtnq_s16_v:
   case NEON::BI__builtin_neon_vcvtnq_s32_v:
   case NEON::BI__builtin_neon_vcvtnq_s64_v:
-  case NEON::BI__builtin_neon_vcvtnq_u16_v:
   case NEON::BI__builtin_neon_vcvtnq_u32_v:
   case NEON::BI__builtin_neon_vcvtnq_u64_v:
-  case NEON::BI__builtin_neon_vcvtp_s16_v:
   case NEON::BI__builtin_neon_vcvtp_s32_v:
   case NEON::BI__builtin_neon_vcvtp_s64_v:
-  case NEON::BI__builtin_neon_vcvtp_u16_v:
   case NEON::BI__builtin_neon_vcvtp_u32_v:
   case NEON::BI__builtin_neon_vcvtp_u64_v:
-  case NEON::BI__builtin_neon_vcvtpq_s16_v:
   case NEON::BI__builtin_neon_vcvtpq_s32_v:
   case NEON::BI__builtin_neon_vcvtpq_s64_v:
-  case NEON::BI__builtin_neon_vcvtpq_u16_v:
   case NEON::BI__builtin_neon_vcvtpq_u32_v:
   case NEON::BI__builtin_neon_vcvtpq_u64_v:
-  case NEON::BI__builtin_neon_vcvtm_s16_v:
   case NEON::BI__builtin_neon_vcvtm_s32_v:
   case NEON::BI__builtin_neon_vcvtm_s64_v:
-  case NEON::BI__builtin_neon_vcvtm_u16_v:
   case NEON::BI__builtin_neon_vcvtm_u32_v:
   case NEON::BI__builtin_neon_vcvtm_u64_v:
-  case NEON::BI__builtin_neon_vcvtmq_s16_v:
   case NEON::BI__builtin_neon_vcvtmq_s32_v:
   case NEON::BI__builtin_neon_vcvtmq_s64_v:
-  case NEON::BI__builtin_neon_vcvtmq_u16_v:
   case NEON::BI__builtin_neon_vcvtmq_u32_v:
   case NEON::BI__builtin_neon_vcvtmq_u64_v: {
     llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
@@ -6188,9 +6109,7 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     Ops[2] = EmitNeonSplat(Ops[2], cast<ConstantInt>(Ops[3]));
     return Builder.CreateCall(F, {Ops[2], Ops[1], Ops[0]});
   }
-  case NEON::BI__builtin_neon_vfmah_lane_f16:
   case NEON::BI__builtin_neon_vfmas_lane_f32:
-  case NEON::BI__builtin_neon_vfmah_laneq_f16:
   case NEON::BI__builtin_neon_vfmas_laneq_f32:
   case NEON::BI__builtin_neon_vfmad_lane_f64:
   case NEON::BI__builtin_neon_vfmad_laneq_f64: {
@@ -6365,25 +6284,18 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
   case NEON::BI__builtin_neon_vcvt_u32_v:
   case NEON::BI__builtin_neon_vcvt_s64_v:
   case NEON::BI__builtin_neon_vcvt_u64_v:
-	case NEON::BI__builtin_neon_vcvt_s16_v:
-	case NEON::BI__builtin_neon_vcvt_u16_v:
   case NEON::BI__builtin_neon_vcvtq_s32_v:
   case NEON::BI__builtin_neon_vcvtq_u32_v:
   case NEON::BI__builtin_neon_vcvtq_s64_v:
-  case NEON::BI__builtin_neon_vcvtq_u64_v:
-	case NEON::BI__builtin_neon_vcvtq_s16_v:
-	case NEON::BI__builtin_neon_vcvtq_u16_v: {
+  case NEON::BI__builtin_neon_vcvtq_u64_v: {
     Ops[0] = Builder.CreateBitCast(Ops[0], GetFloatNeonType(this, Type));
     if (usgn)
       return Builder.CreateFPToUI(Ops[0], Ty);
     return Builder.CreateFPToSI(Ops[0], Ty);
   }
-  case NEON::BI__builtin_neon_vcvta_s16_v:
   case NEON::BI__builtin_neon_vcvta_s32_v:
-  case NEON::BI__builtin_neon_vcvtaq_s16_v:
   case NEON::BI__builtin_neon_vcvtaq_s32_v:
   case NEON::BI__builtin_neon_vcvta_u32_v:
-  case NEON::BI__builtin_neon_vcvtaq_u16_v:
   case NEON::BI__builtin_neon_vcvtaq_u32_v:
   case NEON::BI__builtin_neon_vcvta_s64_v:
   case NEON::BI__builtin_neon_vcvtaq_s64_v:
@@ -6393,13 +6305,9 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
     return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvta");
   }
-  case NEON::BI__builtin_neon_vcvtm_s16_v:
   case NEON::BI__builtin_neon_vcvtm_s32_v:
-  case NEON::BI__builtin_neon_vcvtmq_s16_v:
   case NEON::BI__builtin_neon_vcvtmq_s32_v:
-  case NEON::BI__builtin_neon_vcvtm_u16_v:
   case NEON::BI__builtin_neon_vcvtm_u32_v:
-  case NEON::BI__builtin_neon_vcvtmq_u16_v:
   case NEON::BI__builtin_neon_vcvtmq_u32_v:
   case NEON::BI__builtin_neon_vcvtm_s64_v:
   case NEON::BI__builtin_neon_vcvtmq_s64_v:
@@ -6409,13 +6317,9 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
     return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvtm");
   }
-  case NEON::BI__builtin_neon_vcvtn_s16_v:
   case NEON::BI__builtin_neon_vcvtn_s32_v:
-  case NEON::BI__builtin_neon_vcvtnq_s16_v:
   case NEON::BI__builtin_neon_vcvtnq_s32_v:
-  case NEON::BI__builtin_neon_vcvtn_u16_v:
   case NEON::BI__builtin_neon_vcvtn_u32_v:
-  case NEON::BI__builtin_neon_vcvtnq_u16_v:
   case NEON::BI__builtin_neon_vcvtnq_u32_v:
   case NEON::BI__builtin_neon_vcvtn_s64_v:
   case NEON::BI__builtin_neon_vcvtnq_s64_v:
@@ -6425,13 +6329,9 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     llvm::Type *Tys[2] = { Ty, GetFloatNeonType(this, Type) };
     return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vcvtn");
   }
-  case NEON::BI__builtin_neon_vcvtp_s16_v:
   case NEON::BI__builtin_neon_vcvtp_s32_v:
-  case NEON::BI__builtin_neon_vcvtpq_s16_v:
   case NEON::BI__builtin_neon_vcvtpq_s32_v:
-  case NEON::BI__builtin_neon_vcvtp_u16_v:
   case NEON::BI__builtin_neon_vcvtp_u32_v:
-  case NEON::BI__builtin_neon_vcvtpq_u16_v:
   case NEON::BI__builtin_neon_vcvtpq_u32_v:
   case NEON::BI__builtin_neon_vcvtp_s64_v:
   case NEON::BI__builtin_neon_vcvtpq_s64_v:
@@ -6604,24 +6504,6 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
     return Builder.CreateTrunc(Ops[0], Int16Ty);
   }
-  case NEON::BI__builtin_neon_vmaxv_f16: {
-    Int = Intrinsic::aarch64_neon_fmaxv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 4);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
-  case NEON::BI__builtin_neon_vmaxvq_f16: {
-    Int = Intrinsic::aarch64_neon_fmaxv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 8);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
   case NEON::BI__builtin_neon_vminv_u8: {
     Int = Intrinsic::aarch64_neon_uminv;
     Ty = Int32Ty;
@@ -6694,60 +6576,6 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
     return Builder.CreateTrunc(Ops[0], Int16Ty);
   }
-  case NEON::BI__builtin_neon_vminv_f16: {
-    Int = Intrinsic::aarch64_neon_fminv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 4);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
-  case NEON::BI__builtin_neon_vminvq_f16: {
-    Int = Intrinsic::aarch64_neon_fminv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 8);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
-  case NEON::BI__builtin_neon_vmaxnmv_f16: {
-    Int = Intrinsic::aarch64_neon_fmaxnmv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 4);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxnmv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
-  case NEON::BI__builtin_neon_vmaxnmvq_f16: {
-    Int = Intrinsic::aarch64_neon_fmaxnmv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 8);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vmaxnmv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
-  case NEON::BI__builtin_neon_vminnmv_f16: {
-    Int = Intrinsic::aarch64_neon_fminnmv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 4);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminnmv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
-  case NEON::BI__builtin_neon_vminnmvq_f16: {
-    Int = Intrinsic::aarch64_neon_fminnmv;
-    Ty = HalfTy;
-    VTy = llvm::VectorType::get(HalfTy, 8);
-    llvm::Type *Tys[2] = { Ty, VTy };
-    Ops.push_back(EmitScalarExpr(E->getArg(0)));
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vminnmv");
-    return Builder.CreateTrunc(Ops[0], HalfTy);
-  }
   case NEON::BI__builtin_neon_vmul_n_f64: {
     Ops[0] = Builder.CreateBitCast(Ops[0], DoubleTy);
     Value *RHS = Builder.CreateBitCast(EmitScalarExpr(E->getArg(1)), DoubleTy);
@@ -7506,6 +7334,8 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
       AVX512PF,
       AVX512VBMI,
       AVX512IFMA,
+      AVX5124VNNIW, // TODO implement this fully
+      AVX5124FMAPS, // TODO implement this fully
       AVX512VPOPCNTDQ,
       MAX
     };
@@ -8208,13 +8038,13 @@ Value *CodeGenFunction::EmitX86BuiltinExpr(unsigned BuiltinID,
 
   case X86::BI__faststorefence: {
     return Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent,
-                               llvm::CrossThread);
+                               llvm::SyncScope::System);
   }
   case X86::BI_ReadWriteBarrier:
   case X86::BI_ReadBarrier:
   case X86::BI_WriteBarrier: {
     return Builder.CreateFence(llvm::AtomicOrdering::SequentiallyConsistent,
-                               llvm::SingleThread);
+                               llvm::SyncScope::SingleThread);
   }
   case X86::BI_BitScanForward:
   case X86::BI_BitScanForward64:
diff --git a/lib/CodeGen/CGCall.cpp b/lib/CodeGen/CGCall.cpp
index 13a156c7bbd77..cee656a62fe78 100644
--- a/lib/CodeGen/CGCall.cpp
+++ b/lib/CodeGen/CGCall.cpp
@@ -129,7 +129,7 @@ static void addExtParameterInfosForCall(
   paramInfos.resize(totalArgs);
 }
 
-/// Adds the formal paramaters in FPT to the given prefix. If any parameter in
+/// Adds the formal parameters in FPT to the given prefix. If any parameter in
 /// FPT has pass_object_size attrs, then we'll add parameters for those, too.
 static void appendParameterTypes(const CodeGenTypes &CGT,
                                  SmallVectorImpl<CanQualType> &prefix,
diff --git a/lib/CodeGen/CGClass.cpp b/lib/CodeGen/CGClass.cpp
index 127d7df348ee7..50d702c622688 100644
--- a/lib/CodeGen/CGClass.cpp
+++ b/lib/CodeGen/CGClass.cpp
@@ -2716,88 +2716,6 @@ llvm::Value *CodeGenFunction::EmitVTableTypeCheckedLoad(
       cast<llvm::PointerType>(VTable->getType())->getElementType());
 }
 
-bool
-CodeGenFunction::CanDevirtualizeMemberFunctionCall(const Expr *Base,
-                                                   const CXXMethodDecl *MD) {
-  // When building with -fapple-kext, all calls must go through the vtable since
-  // the kernel linker can do runtime patching of vtables.
-  if (getLangOpts().AppleKext)
-    return false;
-
-  // If the member function is marked 'final', we know that it can't be
-  // overridden and can therefore devirtualize it unless it's pure virtual.
-  if (MD->hasAttr<FinalAttr>())
-    return !MD->isPure();
-
-  // If the base expression (after skipping derived-to-base conversions) is a
-  // class prvalue, then we can devirtualize.
-  Base = Base->getBestDynamicClassTypeExpr();
-  if (Base->isRValue() && Base->getType()->isRecordType())
-    return true;
-
-  // If we don't even know what we would call, we can't devirtualize.
-  const CXXRecordDecl *BestDynamicDecl = Base->getBestDynamicClassType();
-  if (!BestDynamicDecl)
-    return false;
-
-  // There may be a method corresponding to MD in a derived class.
-  const CXXMethodDecl *DevirtualizedMethod =
-      MD->getCorrespondingMethodInClass(BestDynamicDecl);
-
-  // If that method is pure virtual, we can't devirtualize. If this code is
-  // reached, the result would be UB, not a direct call to the derived class
-  // function, and we can't assume the derived class function is defined.
-  if (DevirtualizedMethod->isPure())
-    return false;
-
-  // If that method is marked final, we can devirtualize it.
-  if (DevirtualizedMethod->hasAttr<FinalAttr>())
-    return true;
-
-  // Similarly, if the class itself is marked 'final' it can't be overridden
-  // and we can therefore devirtualize the member function call.
-  if (BestDynamicDecl->hasAttr<FinalAttr>())
-    return true;
-
-  if (const DeclRefExpr *DRE = dyn_cast<DeclRefExpr>(Base)) {
-    if (const VarDecl *VD = dyn_cast<VarDecl>(DRE->getDecl())) {
-      // This is a record decl. We know the type and can devirtualize it.
-      return VD->getType()->isRecordType();
-    }
-
-    return false;
-  }
-
-  // We can devirtualize calls on an object accessed by a class member access
-  // expression, since by C++11 [basic.life]p6 we know that it can't refer to
-  // a derived class object constructed in the same location. However, we avoid
-  // devirtualizing a call to a template function that we could instantiate
-  // implicitly, but have not decided to do so. This is needed because if this
-  // function does not get instantiated, the devirtualization will create a
-  // direct call to a function whose body may not exist. In contrast, calls to
-  // template functions that are not defined in this TU are allowed to be 
-  // devirtualized under assumption that it is user responsibility to
-  // instantiate them in some other TU.
-  if (const MemberExpr *ME = dyn_cast<MemberExpr>(Base))
-    if (const ValueDecl *VD = dyn_cast<ValueDecl>(ME->getMemberDecl()))
-      return VD->getType()->isRecordType() && 
-             (MD->instantiationIsPending() || MD->isDefined() ||
-               !MD->isImplicitlyInstantiable());
-
-  // Likewise for calls on an object accessed by a (non-reference) pointer to
-  // member access.
-  if (auto *BO = dyn_cast<BinaryOperator>(Base)) {
-    if (BO->isPtrMemOp()) {
-      auto *MPT = BO->getRHS()->getType()->castAs<MemberPointerType>();
-      if (MPT->getPointeeType()->isRecordType())
-        return true;
-    }
-  }
-
-  // We can't devirtualize the call.
-  return false;
-}
-
 void CodeGenFunction::EmitForwardingCallToLambda(
                                       const CXXMethodDecl *callOperator,
                                       CallArgList &callArgs) {
diff --git a/lib/CodeGen/CGDecl.cpp b/lib/CodeGen/CGDecl.cpp
index 4b656ea4a8790..23517867437c7 100644
--- a/lib/CodeGen/CGDecl.cpp
+++ b/lib/CodeGen/CGDecl.cpp
@@ -221,8 +221,8 @@ llvm::Constant *CodeGenModule::getOrCreateStaticVarDecl(
     Name = getStaticDeclName(*this, D);
 
   llvm::Type *LTy = getTypes().ConvertTypeForMem(Ty);
-  unsigned AddrSpace =
-      GetGlobalVarAddressSpace(&D, getContext().getTargetAddressSpace(Ty));
+  unsigned AS = GetGlobalVarAddressSpace(&D);
+  unsigned TargetAS = getContext().getTargetAddressSpace(AS);
 
   // Local address space cannot have an initializer.
   llvm::Constant *Init = nullptr;
@@ -231,12 +231,9 @@ llvm::Constant *CodeGenModule::getOrCreateStaticVarDecl(
   else
     Init = llvm::UndefValue::get(LTy);
 
-  llvm::GlobalVariable *GV =
-    new llvm::GlobalVariable(getModule(), LTy,
-                             Ty.isConstant(getContext()), Linkage,
-                             Init, Name, nullptr,
-                             llvm::GlobalVariable::NotThreadLocal,
-                             AddrSpace);
+  llvm::GlobalVariable *GV = new llvm::GlobalVariable(
+      getModule(), LTy, Ty.isConstant(getContext()), Linkage, Init, Name,
+      nullptr, llvm::GlobalVariable::NotThreadLocal, TargetAS);
   GV->setAlignment(getContext().getDeclAlign(&D).getQuantity());
   setGlobalVisibility(GV, &D);
 
@@ -254,11 +251,12 @@ llvm::Constant *CodeGenModule::getOrCreateStaticVarDecl(
   }
 
   // Make sure the result is of the correct type.
-  unsigned ExpectedAddrSpace = getContext().getTargetAddressSpace(Ty);
+  unsigned ExpectedAS = Ty.getAddressSpace();
   llvm::Constant *Addr = GV;
-  if (AddrSpace != ExpectedAddrSpace) {
-    llvm::PointerType *PTy = llvm::PointerType::get(LTy, ExpectedAddrSpace);
-    Addr = llvm::ConstantExpr::getAddrSpaceCast(GV, PTy);
+  if (AS != ExpectedAS) {
+    Addr = getTargetCodeGenInfo().performAddrSpaceCast(
+        *this, GV, AS, ExpectedAS,
+        LTy->getPointerTo(getContext().getTargetAddressSpace(ExpectedAS)));
   }
 
   setStaticLocalDeclAddress(&D, Addr);
diff --git a/lib/CodeGen/CGExpr.cpp b/lib/CodeGen/CGExpr.cpp
index 2ee1c96a66193..9f40ee5a00a3d 100644
--- a/lib/CodeGen/CGExpr.cpp
+++ b/lib/CodeGen/CGExpr.cpp
@@ -338,9 +338,10 @@ pushTemporaryCleanup(CodeGenFunction &CGF, const MaterializeTemporaryExpr *M,
   }
 }
 
-static Address
-createReferenceTemporary(CodeGenFunction &CGF,
-                         const MaterializeTemporaryExpr *M, const Expr *Inner) {
+static Address createReferenceTemporary(CodeGenFunction &CGF,
+                                        const MaterializeTemporaryExpr *M,
+                                        const Expr *Inner) {
+  auto &TCG = CGF.getTargetHooks();
   switch (M->getStorageDuration()) {
   case SD_FullExpression:
   case SD_Automatic: {
@@ -353,13 +354,24 @@ createReferenceTemporary(CodeGenFunction &CGF,
         (Ty->isArrayType() || Ty->isRecordType()) &&
         CGF.CGM.isTypeConstant(Ty, true))
       if (llvm::Constant *Init = CGF.CGM.EmitConstantExpr(Inner, Ty, &CGF)) {
-        auto *GV = new llvm::GlobalVariable(
-            CGF.CGM.getModule(), Init->getType(), /*isConstant=*/true,
-            llvm::GlobalValue::PrivateLinkage, Init, ".ref.tmp");
-        CharUnits alignment = CGF.getContext().getTypeAlignInChars(Ty);
-        GV->setAlignment(alignment.getQuantity());
-        // FIXME: Should we put the new global into a COMDAT?
-        return Address(GV, alignment);
+        if (auto AddrSpace = CGF.getTarget().getConstantAddressSpace()) {
+          auto AS = AddrSpace.getValue();
+          auto *GV = new llvm::GlobalVariable(
+              CGF.CGM.getModule(), Init->getType(), /*isConstant=*/true,
+              llvm::GlobalValue::PrivateLinkage, Init, ".ref.tmp", nullptr,
+              llvm::GlobalValue::NotThreadLocal,
+              CGF.getContext().getTargetAddressSpace(AS));
+          CharUnits alignment = CGF.getContext().getTypeAlignInChars(Ty);
+          GV->setAlignment(alignment.getQuantity());
+          llvm::Constant *C = GV;
+          if (AS != LangAS::Default)
+            C = TCG.performAddrSpaceCast(
+                CGF.CGM, GV, AS, LangAS::Default,
+                GV->getValueType()->getPointerTo(
+                    CGF.getContext().getTargetAddressSpace(LangAS::Default)));
+          // FIXME: Should we put the new global into a COMDAT?
+          return Address(C, alignment);
+        }
       }
     return CGF.CreateMemTemp(Ty, "ref.tmp");
   }
@@ -440,9 +452,11 @@ EmitMaterializeTemporaryExpr(const MaterializeTemporaryExpr *M) {
 
   // Create and initialize the reference temporary.
   Address Object = createReferenceTemporary(*this, M, E);
-  if (auto *Var = dyn_cast<llvm::GlobalVariable>(Object.getPointer())) {
+  if (auto *Var = dyn_cast<llvm::GlobalVariable>(
+          Object.getPointer()->stripPointerCasts())) {
     Object = Address(llvm::ConstantExpr::getBitCast(
-        Var, ConvertTypeForMem(E->getType())->getPointerTo()),
+                         cast<llvm::Constant>(Object.getPointer()),
+                         ConvertTypeForMem(E->getType())->getPointerTo()),
                      Object.getAlignment());
     // If the temporary is a global and has a constant initializer or is a
     // constant temporary that we promoted to a global, we may have already
diff --git a/lib/CodeGen/CGExprCXX.cpp b/lib/CodeGen/CGExprCXX.cpp
index a9865f3703d4a..ab170245284ce 100644
--- a/lib/CodeGen/CGExprCXX.cpp
+++ b/lib/CodeGen/CGExprCXX.cpp
@@ -199,7 +199,8 @@ RValue CodeGenFunction::EmitCXXMemberOrOperatorMemberCallExpr(
   bool CanUseVirtualCall = MD->isVirtual() && !HasQualifier;
 
   const CXXMethodDecl *DevirtualizedMethod = nullptr;
-  if (CanUseVirtualCall && CanDevirtualizeMemberFunctionCall(Base, MD)) {
+  if (CanUseVirtualCall &&
+      MD->getDevirtualizedMethod(Base, getLangOpts().AppleKext)) {
     const CXXRecordDecl *BestDynamicDecl = Base->getBestDynamicClassType();
     DevirtualizedMethod = MD->getCorrespondingMethodInClass(BestDynamicDecl);
     assert(DevirtualizedMethod);
diff --git a/lib/CodeGen/CGOpenMPRuntime.cpp b/lib/CodeGen/CGOpenMPRuntime.cpp
index 3df95a4e9b2a9..a2ea0dec3e9d0 100644
--- a/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -4157,9 +4157,15 @@ void CGOpenMPRuntime::emitTaskLoopCall(CodeGenFunction &CGF, SourceLocation Loc,
                        /*IsInitializer=*/true);
   enum { NoSchedule = 0, Grainsize = 1, NumTasks = 2 };
   llvm::Value *TaskArgs[] = {
-      UpLoc, ThreadID, Result.NewTask, IfVal, LBLVal.getPointer(),
-      UBLVal.getPointer(), CGF.EmitLoadOfScalar(StLVal, SourceLocation()),
-      llvm::ConstantInt::getSigned(CGF.IntTy, Data.Nogroup ? 1 : 0),
+      UpLoc,
+      ThreadID,
+      Result.NewTask,
+      IfVal,
+      LBLVal.getPointer(),
+      UBLVal.getPointer(),
+      CGF.EmitLoadOfScalar(StLVal, SourceLocation()),
+      llvm::ConstantInt::getNullValue(
+          CGF.IntTy), // Always 0 because taskgroup emitted by the compiler
       llvm::ConstantInt::getSigned(
           CGF.IntTy, Data.Schedule.getPointer()
                          ? Data.Schedule.getInt() ? NumTasks : Grainsize
@@ -4168,10 +4174,9 @@ void CGOpenMPRuntime::emitTaskLoopCall(CodeGenFunction &CGF, SourceLocation Loc,
           ? CGF.Builder.CreateIntCast(Data.Schedule.getPointer(), CGF.Int64Ty,
                                       /*isSigned=*/false)
           : llvm::ConstantInt::get(CGF.Int64Ty, /*V=*/0),
-      Result.TaskDupFn
-          ? CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(Result.TaskDupFn,
-                                                            CGF.VoidPtrTy)
-          : llvm::ConstantPointerNull::get(CGF.VoidPtrTy)};
+      Result.TaskDupFn ? CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
+                             Result.TaskDupFn, CGF.VoidPtrTy)
+                       : llvm::ConstantPointerNull::get(CGF.VoidPtrTy)};
   CGF.EmitRuntimeCall(createRuntimeFunction(OMPRTL__kmpc_taskloop), TaskArgs);
 }
 
diff --git a/lib/CodeGen/CGStmtOpenMP.cpp b/lib/CodeGen/CGStmtOpenMP.cpp
index 493cd627e4183..71797e2e6fbe9 100644
--- a/lib/CodeGen/CGStmtOpenMP.cpp
+++ b/lib/CodeGen/CGStmtOpenMP.cpp
@@ -4363,7 +4363,18 @@ void CodeGenFunction::EmitOMPTaskLoopBasedDirective(const OMPLoopDirective &S) {
     CGF.CGM.getOpenMPRuntime().emitInlinedDirective(CGF, OMPD_taskloop,
                                                     CodeGen);
   };
-  EmitOMPTaskBasedDirective(S, BodyGen, TaskGen, Data);
+  if (Data.Nogroup)
+    EmitOMPTaskBasedDirective(S, BodyGen, TaskGen, Data);
+  else {
+    CGM.getOpenMPRuntime().emitTaskgroupRegion(
+        *this,
+        [&S, &BodyGen, &TaskGen, &Data](CodeGenFunction &CGF,
+                                        PrePostActionTy &Action) {
+          Action.Enter(CGF);
+          CGF.EmitOMPTaskBasedDirective(S, BodyGen, TaskGen, Data);
+        },
+        S.getLocStart());
+  }
 }
 
 void CodeGenFunction::EmitOMPTaskLoopDirective(const OMPTaskLoopDirective &S) {
diff --git a/lib/CodeGen/CodeGenABITypes.cpp b/lib/CodeGen/CodeGenABITypes.cpp
index 166f44f816f31..0735a9c3dfbc1 100644
--- a/lib/CodeGen/CodeGenABITypes.cpp
+++ b/lib/CodeGen/CodeGenABITypes.cpp
@@ -64,3 +64,19 @@ CodeGen::arrangeFreeFunctionCall(CodeGenModule &CGM,
       returnType, /*IsInstanceMethod=*/false, /*IsChainCall=*/false, argTypes,
       info, {}, args);
 }
+
+llvm::FunctionType *
+CodeGen::convertFreeFunctionType(CodeGenModule &CGM, const FunctionDecl *FD) {
+  assert(FD != nullptr && "Expected a non-null function declaration!");
+  llvm::Type *T = CGM.getTypes().ConvertFunctionType(FD->getType(), FD);
+
+  if (auto FT = dyn_cast<llvm::FunctionType>(T))
+    return FT;
+
+  return nullptr;
+}
+
+llvm::Type *
+CodeGen::convertTypeForMemory(CodeGenModule &CGM, QualType T) {
+  return CGM.getTypes().ConvertTypeForMem(T);
+}
diff --git a/lib/CodeGen/CodeGenFunction.h b/lib/CodeGen/CodeGenFunction.h
index 6785111bd0528..5933e029be8d3 100644
--- a/lib/CodeGen/CodeGenFunction.h
+++ b/lib/CodeGen/CodeGenFunction.h
@@ -1479,6 +1479,9 @@ public:
 
   const TargetInfo &getTarget() const { return Target; }
   llvm::LLVMContext &getLLVMContext() { return CGM.getLLVMContext(); }
+  const TargetCodeGenInfo &getTargetHooks() const {
+    return CGM.getTargetCodeGenInfo();
+  }
 
   //===--------------------------------------------------------------------===//
   //                                  Cleanups
@@ -1749,11 +1752,6 @@ public:
   llvm::Value *EmitVTableTypeCheckedLoad(const CXXRecordDecl *RD, llvm::Value *VTable,
                                          uint64_t VTableByteOffset);
 
-  /// CanDevirtualizeMemberFunctionCalls - Checks whether virtual calls on given
-  /// expr can be devirtualized.
-  bool CanDevirtualizeMemberFunctionCall(const Expr *Base,
-                                         const CXXMethodDecl *MD);
-
   /// EnterDtorCleanups - Enter the cleanups necessary to complete the
   /// given phase of destruction for a destructor.  The end result
   /// should call destructors on members and base classes in reverse
@@ -3820,10 +3818,6 @@ public:
 private:
   QualType getVarArgType(const Expr *Arg);
 
-  const TargetCodeGenInfo &getTargetHooks() const {
-    return CGM.getTargetCodeGenInfo();
-  }
-
   void EmitDeclMetadata();
 
   BlockByrefHelpers *buildByrefHelpers(llvm::StructType &byrefType,
diff --git a/lib/CodeGen/CodeGenModule.cpp b/lib/CodeGen/CodeGenModule.cpp
index 5319ccec163f7..4b15b8ac4c718 100644
--- a/lib/CodeGen/CodeGenModule.cpp
+++ b/lib/CodeGen/CodeGenModule.cpp
@@ -98,7 +98,6 @@ CodeGenModule::CodeGenModule(ASTContext &C, const HeaderSearchOptions &HSO,
   Int16Ty = llvm::Type::getInt16Ty(LLVMContext);
   Int32Ty = llvm::Type::getInt32Ty(LLVMContext);
   Int64Ty = llvm::Type::getInt64Ty(LLVMContext);
-  HalfTy = llvm::Type::getHalfTy(LLVMContext);
   FloatTy = llvm::Type::getFloatTy(LLVMContext);
   DoubleTy = llvm::Type::getDoubleTy(LLVMContext);
   PointerWidthInBits = C.getTargetInfo().getPointerWidth(0);
@@ -1099,7 +1098,7 @@ static void setLinkageAndVisibilityForGV(llvm::GlobalValue *GV,
                                          const NamedDecl *ND) {
   // Set linkage and visibility in case we never see a definition.
   LinkageInfo LV = ND->getLinkageAndVisibility();
-  if (LV.getLinkage() != ExternalLinkage) {
+  if (!isExternallyVisible(LV.getLinkage())) {
     // Don't set internal linkage on declarations.
   } else {
     if (ND->hasAttr<DLLImportAttr>()) {
@@ -2368,11 +2367,13 @@ CodeGenModule::GetOrCreateLLVMGlobal(StringRef MangledName,
       return llvm::ConstantExpr::getBitCast(Entry, Ty);
   }
 
-  unsigned AddrSpace = GetGlobalVarAddressSpace(D, Ty->getAddressSpace());
+  auto AddrSpace = GetGlobalVarAddressSpace(D);
+  auto TargetAddrSpace = getContext().getTargetAddressSpace(AddrSpace);
+
   auto *GV = new llvm::GlobalVariable(
       getModule(), Ty->getElementType(), false,
       llvm::GlobalValue::ExternalLinkage, nullptr, MangledName, nullptr,
-      llvm::GlobalVariable::NotThreadLocal, AddrSpace);
+      llvm::GlobalVariable::NotThreadLocal, TargetAddrSpace);
 
   // If we already created a global with the same mangled name (but different
   // type) before, take its name and remove it from its parent.
@@ -2429,8 +2430,15 @@ CodeGenModule::GetOrCreateLLVMGlobal(StringRef MangledName,
       GV->setSection(".cp.rodata");
   }
 
-  if (AddrSpace != Ty->getAddressSpace())
-    return llvm::ConstantExpr::getAddrSpaceCast(GV, Ty);
+  auto ExpectedAS =
+      D ? D->getType().getAddressSpace()
+        : static_cast<unsigned>(LangOpts.OpenCL ? LangAS::opencl_global
+                                                : LangAS::Default);
+  assert(getContext().getTargetAddressSpace(ExpectedAS) ==
+         Ty->getPointerAddressSpace());
+  if (AddrSpace != ExpectedAS)
+    return getTargetCodeGenInfo().performAddrSpaceCast(*this, GV, AddrSpace,
+                                                       ExpectedAS, Ty);
 
   return GV;
 }
@@ -2564,18 +2572,28 @@ CharUnits CodeGenModule::GetTargetTypeStoreSize(llvm::Type *Ty) const {
       getDataLayout().getTypeStoreSizeInBits(Ty));
 }
 
-unsigned CodeGenModule::GetGlobalVarAddressSpace(const VarDecl *D,
-                                                 unsigned AddrSpace) {
-  if (D && LangOpts.CUDA && LangOpts.CUDAIsDevice) {
-    if (D->hasAttr<CUDAConstantAttr>())
-      AddrSpace = getContext().getTargetAddressSpace(LangAS::cuda_constant);
-    else if (D->hasAttr<CUDASharedAttr>())
-      AddrSpace = getContext().getTargetAddressSpace(LangAS::cuda_shared);
+unsigned CodeGenModule::GetGlobalVarAddressSpace(const VarDecl *D) {
+  unsigned AddrSpace;
+  if (LangOpts.OpenCL) {
+    AddrSpace = D ? D->getType().getAddressSpace()
+                  : static_cast<unsigned>(LangAS::opencl_global);
+    assert(AddrSpace == LangAS::opencl_global ||
+           AddrSpace == LangAS::opencl_constant ||
+           AddrSpace == LangAS::opencl_local ||
+           AddrSpace >= LangAS::FirstTargetAddressSpace);
+    return AddrSpace;
+  }
+
+  if (LangOpts.CUDA && LangOpts.CUDAIsDevice) {
+    if (D && D->hasAttr<CUDAConstantAttr>())
+      return LangAS::cuda_constant;
+    else if (D && D->hasAttr<CUDASharedAttr>())
+      return LangAS::cuda_shared;
     else
-      AddrSpace = getContext().getTargetAddressSpace(LangAS::cuda_device);
+      return LangAS::cuda_device;
   }
 
-  return AddrSpace;
+  return getTargetCodeGenInfo().getGlobalVarAddressSpace(*this, D);
 }
 
 template<typename SomeDecl>
@@ -2728,10 +2746,9 @@ void CodeGenModule::EmitGlobalVarDefinition(const VarDecl *D,
   // "extern int x[];") and then a definition of a different type (e.g.
   // "int x[10];"). This also happens when an initializer has a different type
   // from the type of the global (this happens with unions).
-  if (!GV ||
-      GV->getType()->getElementType() != InitType ||
+  if (!GV || GV->getType()->getElementType() != InitType ||
       GV->getType()->getAddressSpace() !=
-       GetGlobalVarAddressSpace(D, getContext().getTargetAddressSpace(ASTTy))) {
+          getContext().getTargetAddressSpace(GetGlobalVarAddressSpace(D))) {
 
     // Move the old entry aside so that we'll create a new one.
     Entry->setName(StringRef());
@@ -3740,20 +3757,26 @@ ConstantAddress CodeGenModule::GetAddrOfGlobalTemporary(
       Linkage = llvm::GlobalVariable::InternalLinkage;
     }
   }
-  unsigned AddrSpace = GetGlobalVarAddressSpace(
-      VD, getContext().getTargetAddressSpace(MaterializedType));
+  unsigned AddrSpace =
+      VD ? GetGlobalVarAddressSpace(VD) : MaterializedType.getAddressSpace();
+  auto TargetAS = getContext().getTargetAddressSpace(AddrSpace);
   auto *GV = new llvm::GlobalVariable(
       getModule(), Type, Constant, Linkage, InitialValue, Name.c_str(),
-      /*InsertBefore=*/nullptr, llvm::GlobalVariable::NotThreadLocal,
-      AddrSpace);
+      /*InsertBefore=*/nullptr, llvm::GlobalVariable::NotThreadLocal, TargetAS);
   setGlobalVisibility(GV, VD);
   GV->setAlignment(Align.getQuantity());
   if (supportsCOMDAT() && GV->isWeakForLinker())
     GV->setComdat(TheModule.getOrInsertComdat(GV->getName()));
   if (VD->getTLSKind())
     setTLSMode(GV, *VD);
-  MaterializedGlobalTemporaryMap[E] = GV;
-  return ConstantAddress(GV, Align);
+  llvm::Constant *CV = GV;
+  if (AddrSpace != LangAS::Default)
+    CV = getTargetCodeGenInfo().performAddrSpaceCast(
+        *this, GV, AddrSpace, LangAS::Default,
+        Type->getPointerTo(
+            getContext().getTargetAddressSpace(LangAS::Default)));
+  MaterializedGlobalTemporaryMap[E] = CV;
+  return ConstantAddress(CV, Align);
 }
 
 /// EmitObjCPropertyImplementations - Emit information for synthesized
diff --git a/lib/CodeGen/CodeGenModule.h b/lib/CodeGen/CodeGenModule.h
index c5f1a2b409eef..b162e72d1992f 100644
--- a/lib/CodeGen/CodeGenModule.h
+++ b/lib/CodeGen/CodeGenModule.h
@@ -710,11 +710,15 @@ public:
                                      SourceLocation Loc = SourceLocation(),
                                      bool TLS = false);
 
-  /// Return the address space of the underlying global variable for D, as
+  /// Return the AST address space of the underlying global variable for D, as
   /// determined by its declaration. Normally this is the same as the address
   /// space of D's type, but in CUDA, address spaces are associated with
-  /// declarations, not types.
-  unsigned GetGlobalVarAddressSpace(const VarDecl *D, unsigned AddrSpace);
+  /// declarations, not types. If D is nullptr, return the default address
+  /// space for global variable.
+  ///
+  /// For languages without explicit address spaces, if D has default address
+  /// space, target-specific global or constant address space may be returned.
+  unsigned GetGlobalVarAddressSpace(const VarDecl *D);
 
   /// Return the llvm::Constant for the address of the given global variable.
   /// If Ty is non-null and if the global doesn't exist, then it will be created
diff --git a/lib/CodeGen/CodeGenTypeCache.h b/lib/CodeGen/CodeGenTypeCache.h
index 6910d36733dcb..450eab48a3b41 100644
--- a/lib/CodeGen/CodeGenTypeCache.h
+++ b/lib/CodeGen/CodeGenTypeCache.h
@@ -36,7 +36,7 @@ struct CodeGenTypeCache {
   /// i8, i16, i32, and i64
   llvm::IntegerType *Int8Ty, *Int16Ty, *Int32Ty, *Int64Ty;
   /// float, double
-  llvm::Type *HalfTy, *FloatTy, *DoubleTy;
+  llvm::Type *FloatTy, *DoubleTy;
 
   /// int
   llvm::IntegerType *IntTy;
diff --git a/lib/CodeGen/ItaniumCXXABI.cpp b/lib/CodeGen/ItaniumCXXABI.cpp
index 39efb9f43921b..c82b9677eacfd 100644
--- a/lib/CodeGen/ItaniumCXXABI.cpp
+++ b/lib/CodeGen/ItaniumCXXABI.cpp
@@ -2732,7 +2732,9 @@ static bool ShouldUseExternalRTTIDescriptor(CodeGenModule &CGM,
     // function.
     bool IsDLLImport = RD->hasAttr<DLLImportAttr>();
     if (CGM.getVTables().isVTableExternal(RD))
-      return IsDLLImport ? false : true;
+      return IsDLLImport && !CGM.getTriple().isWindowsItaniumEnvironment()
+                 ? false
+                 : true;
 
     if (IsDLLImport)
       return true;
@@ -2957,6 +2959,8 @@ static llvm::GlobalVariable::LinkageTypes getTypeInfoLinkage(CodeGenModule &CGM,
     return llvm::GlobalValue::InternalLinkage;
 
   case VisibleNoLinkage:
+  case ModuleInternalLinkage:
+  case ModuleLinkage:
   case ExternalLinkage:
     // RTTI is not enabled, which means that this type info struct is going
     // to be used for exception handling. Give it linkonce_odr linkage.
@@ -2968,7 +2972,8 @@ static llvm::GlobalVariable::LinkageTypes getTypeInfoLinkage(CodeGenModule &CGM,
       if (RD->hasAttr<WeakAttr>())
         return llvm::GlobalValue::WeakODRLinkage;
       if (CGM.getTriple().isWindowsItaniumEnvironment())
-        if (RD->hasAttr<DLLImportAttr>())
+        if (RD->hasAttr<DLLImportAttr>() &&
+            ShouldUseExternalRTTIDescriptor(CGM, Ty))
           return llvm::GlobalValue::ExternalLinkage;
       if (RD->isDynamicClass()) {
         llvm::GlobalValue::LinkageTypes LT = CGM.getVTableLinkage(RD);
@@ -3181,7 +3186,8 @@ llvm::Constant *ItaniumRTTIBuilder::BuildTypeInfo(QualType Ty, bool Force,
     if (DLLExport || (RD && RD->hasAttr<DLLExportAttr>())) {
       TypeName->setDLLStorageClass(llvm::GlobalValue::DLLExportStorageClass);
       GV->setDLLStorageClass(llvm::GlobalValue::DLLExportStorageClass);
-    } else if (CGM.getLangOpts().RTTI && RD && RD->hasAttr<DLLImportAttr>()) {
+    } else if (RD && RD->hasAttr<DLLImportAttr>() &&
+               ShouldUseExternalRTTIDescriptor(CGM, Ty)) {
       TypeName->setDLLStorageClass(llvm::GlobalValue::DLLImportStorageClass);
       GV->setDLLStorageClass(llvm::GlobalValue::DLLImportStorageClass);
 
diff --git a/lib/CodeGen/MicrosoftCXXABI.cpp b/lib/CodeGen/MicrosoftCXXABI.cpp
index e68a16e0bd51c..78b510bb46650 100644
--- a/lib/CodeGen/MicrosoftCXXABI.cpp
+++ b/lib/CodeGen/MicrosoftCXXABI.cpp
@@ -3425,6 +3425,8 @@ static llvm::GlobalValue::LinkageTypes getLinkageForRTTI(QualType Ty) {
     return llvm::GlobalValue::InternalLinkage;
 
   case VisibleNoLinkage:
+  case ModuleInternalLinkage:
+  case ModuleLinkage:
   case ExternalLinkage:
     return llvm::GlobalValue::LinkOnceODRLinkage;
   }
diff --git a/lib/CodeGen/TargetInfo.cpp b/lib/CodeGen/TargetInfo.cpp
index 8d00e055306d7..eeebd60a2d20e 100644
--- a/lib/CodeGen/TargetInfo.cpp
+++ b/lib/CodeGen/TargetInfo.cpp
@@ -416,14 +416,34 @@ llvm::Constant *TargetCodeGenInfo::getNullPointer(const CodeGen::CodeGenModule &
   return llvm::ConstantPointerNull::get(T);
 }
 
+unsigned TargetCodeGenInfo::getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                                     const VarDecl *D) const {
+  assert(!CGM.getLangOpts().OpenCL &&
+         !(CGM.getLangOpts().CUDA && CGM.getLangOpts().CUDAIsDevice) &&
+         "Address space agnostic languages only");
+  return D ? D->getType().getAddressSpace()
+           : static_cast<unsigned>(LangAS::Default);
+}
+
 llvm::Value *TargetCodeGenInfo::performAddrSpaceCast(
     CodeGen::CodeGenFunction &CGF, llvm::Value *Src, unsigned SrcAddr,
     unsigned DestAddr, llvm::Type *DestTy, bool isNonNull) const {
   // Since target may map different address spaces in AST to the same address
   // space, an address space conversion may end up as a bitcast.
+  if (auto *C = dyn_cast<llvm::Constant>(Src))
+    return performAddrSpaceCast(CGF.CGM, C, SrcAddr, DestAddr, DestTy);
   return CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(Src, DestTy);
 }
 
+llvm::Constant *
+TargetCodeGenInfo::performAddrSpaceCast(CodeGenModule &CGM, llvm::Constant *Src,
+                                        unsigned SrcAddr, unsigned DestAddr,
+                                        llvm::Type *DestTy) const {
+  // Since target may map different address spaces in AST to the same address
+  // space, an address space conversion may end up as a bitcast.
+  return llvm::ConstantExpr::getPointerCast(Src, DestTy);
+}
+
 static bool isEmptyRecord(ASTContext &Context, QualType T, bool AllowArrays);
 
 /// isEmptyField - Return true iff a the field is "empty", that is it
@@ -7325,6 +7345,8 @@ public:
     return LangAS::FirstTargetAddressSpace +
            getABIInfo().getDataLayout().getAllocaAddrSpace();
   }
+  unsigned getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                    const VarDecl *D) const override;
 };
 }
 
@@ -7408,6 +7430,31 @@ llvm::Constant *AMDGPUTargetCodeGenInfo::getNullPointer(
       llvm::ConstantPointerNull::get(NPT), PT);
 }
 
+unsigned
+AMDGPUTargetCodeGenInfo::getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                                  const VarDecl *D) const {
+  assert(!CGM.getLangOpts().OpenCL &&
+         !(CGM.getLangOpts().CUDA && CGM.getLangOpts().CUDAIsDevice) &&
+         "Address space agnostic languages only");
+  unsigned DefaultGlobalAS =
+      LangAS::FirstTargetAddressSpace +
+      CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+  if (!D)
+    return DefaultGlobalAS;
+
+  unsigned AddrSpace = D->getType().getAddressSpace();
+  assert(AddrSpace == LangAS::Default ||
+         AddrSpace >= LangAS::FirstTargetAddressSpace);
+  if (AddrSpace != LangAS::Default)
+    return AddrSpace;
+
+  if (CGM.isTypeConstant(D->getType(), false)) {
+    if (auto ConstAS = CGM.getTarget().getConstantAddressSpace())
+      return ConstAS.getValue();
+  }
+  return DefaultGlobalAS;
+}
+
 //===----------------------------------------------------------------------===//
 // SPARC v8 ABI Implementation.
 // Based on the SPARC Compliance Definition version 2.4.1.
diff --git a/lib/CodeGen/TargetInfo.h b/lib/CodeGen/TargetInfo.h
index 247d01dcb0861..952ef96c4aef7 100644
--- a/lib/CodeGen/TargetInfo.h
+++ b/lib/CodeGen/TargetInfo.h
@@ -229,6 +229,13 @@ public:
   virtual llvm::Constant *getNullPointer(const CodeGen::CodeGenModule &CGM,
       llvm::PointerType *T, QualType QT) const;
 
+  /// Get target favored AST address space of a global variable for languages
+  /// other than OpenCL and CUDA.
+  /// If \p D is nullptr, returns the default target favored address space
+  /// for global variable.
+  virtual unsigned getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                            const VarDecl *D) const;
+
   /// Get the AST address space for alloca.
   virtual unsigned getASTAllocaAddressSpace() const { return LangAS::Default; }
 
@@ -243,6 +250,15 @@ public:
                                             unsigned DestAddr,
                                             llvm::Type *DestTy,
                                             bool IsNonNull = false) const;
+
+  /// Perform address space cast of a constant expression of pointer type.
+  /// \param V is the LLVM constant to be casted to another address space.
+  /// \param SrcAddr is the language address space of \p V.
+  /// \param DestAddr is the targeted language address space.
+  /// \param DestTy is the destination LLVM pointer type.
+  virtual llvm::Constant *
+  performAddrSpaceCast(CodeGenModule &CGM, llvm::Constant *V, unsigned SrcAddr,
+                       unsigned DestAddr, llvm::Type *DestTy) const;
 };
 
 } // namespace CodeGen