diff --git a/clang/docs/LanguageExtensions.rst b/clang/docs/LanguageExtensions.rst
--- a/clang/docs/LanguageExtensions.rst
+++ b/clang/docs/LanguageExtensions.rst
@@ -514,8 +514,8 @@
 Half-Precision Floating Point
 =============================
 
-Clang supports two half-precision (16-bit) floating point types: ``__fp16`` and
-``_Float16``.  These types are supported in all language modes.
+Clang supports three half-precision (16-bit) floating point types: ``__fp16``,
+``_Float16`` and ``__bf16``.  These types are supported in all language modes.
 
 ``__fp16`` is supported on every target, as it is purely a storage format; see below.
 ``_Float16`` is currently only supported on the following targets, with further
@@ -527,6 +527,10 @@
 
 ``_Float16`` will be supported on more targets as they define ABIs for it.
 
+``__bf16`` is purely a storage format; it is currently only supported on the following targets:
+* 32-bit ARM
+* 64-bit ARM (AArch64)
+
 ``__fp16`` is a storage and interchange format only.  This means that values of
 ``__fp16`` are immediately promoted to (at least) ``float`` when used in arithmetic
 operations, so that e.g. the result of adding two ``__fp16`` values has type ``float``.
diff --git a/clang/include/clang-c/Index.h b/clang/include/clang-c/Index.h
--- a/clang/include/clang-c/Index.h
+++ b/clang/include/clang-c/Index.h
@@ -3253,8 +3253,9 @@
   CXType_UShortAccum = 36,
   CXType_UAccum = 37,
   CXType_ULongAccum = 38,
+  CXType_BFloat16 = 39,
   CXType_FirstBuiltin = CXType_Void,
-  CXType_LastBuiltin = CXType_ULongAccum,
+  CXType_LastBuiltin = CXType_BFloat16,
 
   CXType_Complex = 100,
   CXType_Pointer = 101,
diff --git a/clang/include/clang/AST/ASTContext.h b/clang/include/clang/AST/ASTContext.h
--- a/clang/include/clang/AST/ASTContext.h
+++ b/clang/include/clang/AST/ASTContext.h
@@ -964,6 +964,7 @@
   CanQualType SatUnsignedShortFractTy, SatUnsignedFractTy,
       SatUnsignedLongFractTy;
   CanQualType HalfTy; // [OpenCL 6.1.1.1], ARM NEON
+  CanQualType BFloat16Ty;
   CanQualType Float16Ty; // C11 extension ISO/IEC TS 18661-3
   CanQualType FloatComplexTy, DoubleComplexTy, LongDoubleComplexTy;
   CanQualType Float128ComplexTy;
diff --git a/clang/include/clang/AST/BuiltinTypes.def b/clang/include/clang/AST/BuiltinTypes.def
--- a/clang/include/clang/AST/BuiltinTypes.def
+++ b/clang/include/clang/AST/BuiltinTypes.def
@@ -212,6 +212,9 @@
 // '_Float16'
 FLOATING_TYPE(Float16, HalfTy)
 
+// '__bf16'
+FLOATING_TYPE(BFloat16, BFloat16Ty)
+
 // '__float128'
 FLOATING_TYPE(Float128, Float128Ty)
 
diff --git a/clang/include/clang/AST/Type.h b/clang/include/clang/AST/Type.h
--- a/clang/include/clang/AST/Type.h
+++ b/clang/include/clang/AST/Type.h
@@ -2008,6 +2008,7 @@
   bool isFloatingType() const;     // C99 6.2.5p11 (real floating + complex)
   bool isHalfType() const;         // OpenCL 6.1.1.1, NEON (IEEE 754-2008 half)
   bool isFloat16Type() const;      // C11 extension ISO/IEC TS 18661
+  bool isBFloat16Type() const;
   bool isFloat128Type() const;
   bool isRealType() const;         // C99 6.2.5p17 (real floating + integer)
   bool isArithmeticType() const;   // C99 6.2.5p18 (integer + floating)
@@ -6926,6 +6927,10 @@
   return isSpecificBuiltinType(BuiltinType::Float16);
 }
 
+inline bool Type::isBFloat16Type() const {
+  return isSpecificBuiltinType(BuiltinType::BFloat16);
+}
+
 inline bool Type::isFloat128Type() const {
   return isSpecificBuiltinType(BuiltinType::Float128);
 }
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -8115,6 +8115,8 @@
   InGroup<BadFunctionCast>, DefaultIgnore;
 def err_cast_pointer_to_non_pointer_int : Error<
   "pointer cannot be cast to type %0">;
+def err_cast_to_bfloat16 : Error<"cannot type-cast to __bf16">;
+def err_cast_from_bfloat16 : Error<"cannot type-cast from __bf16">;
 def err_typecheck_expect_scalar_operand : Error<
   "operand of type %0 where arithmetic or pointer type is required">;
 def err_typecheck_cond_incompatible_operands : Error<
diff --git a/clang/include/clang/Basic/Specifiers.h b/clang/include/clang/Basic/Specifiers.h
--- a/clang/include/clang/Basic/Specifiers.h
+++ b/clang/include/clang/Basic/Specifiers.h
@@ -72,6 +72,7 @@
     TST_Float16,      // C11 extension ISO/IEC TS 18661-3
     TST_Accum,        // ISO/IEC JTC1 SC22 WG14 N1169 Extension
     TST_Fract,
+    TST_BFloat16,
     TST_float,
     TST_double,
     TST_float128,
diff --git a/clang/include/clang/Basic/TargetBuiltins.h b/clang/include/clang/Basic/TargetBuiltins.h
--- a/clang/include/clang/Basic/TargetBuiltins.h
+++ b/clang/include/clang/Basic/TargetBuiltins.h
@@ -142,7 +142,8 @@
       Poly128,
       Float16,
       Float32,
-      Float64
+      Float64,
+      BFloat16
     };
 
     NeonTypeFlags(unsigned F) : Flags(F) {}
diff --git a/clang/include/clang/Basic/TargetInfo.h b/clang/include/clang/Basic/TargetInfo.h
--- a/clang/include/clang/Basic/TargetInfo.h
+++ b/clang/include/clang/Basic/TargetInfo.h
@@ -59,6 +59,7 @@
   unsigned char BoolWidth, BoolAlign;
   unsigned char IntWidth, IntAlign;
   unsigned char HalfWidth, HalfAlign;
+  unsigned char BFloat16Width, BFloat16Align;
   unsigned char FloatWidth, FloatAlign;
   unsigned char DoubleWidth, DoubleAlign;
   unsigned char LongDoubleWidth, LongDoubleAlign, Float128Align;
@@ -100,8 +101,8 @@
   unsigned short MaxVectorAlign;
   unsigned short MaxTLSAlign;
 
-  const llvm::fltSemantics *HalfFormat, *FloatFormat, *DoubleFormat,
-    *LongDoubleFormat, *Float128Format;
+  const llvm::fltSemantics *HalfFormat, *BFloat16Format, *FloatFormat,
+    *DoubleFormat, *LongDoubleFormat, *Float128Format;
 
   ///===---- Target Data Type Query Methods -------------------------------===//
   enum IntType {
@@ -188,6 +189,7 @@
                          // LLVM IR type.
   bool HasFloat128;
   bool HasFloat16;
+  bool HasBFloat16;
 
   unsigned char MaxAtomicPromoteWidth, MaxAtomicInlineWidth;
   unsigned short SimdDefaultAlign;
@@ -562,6 +564,9 @@
   /// Determine whether the _Float16 type is supported on this target.
   virtual bool hasFloat16Type() const { return HasFloat16; }
 
+  /// Determine whether the _BFloat16 type is supported on this target.
+  virtual bool hasBFloat16Type() const { return HasBFloat16; }
+
   /// Return the alignment that is suitable for storing any
   /// object with a fundamental alignment requirement.
   unsigned getSuitableAlign() const { return SuitableAlign; }
@@ -610,6 +615,11 @@
   unsigned getFloatAlign() const { return FloatAlign; }
   const llvm::fltSemantics &getFloatFormat() const { return *FloatFormat; }
 
+  /// getBFloat16Width/Align/Format - Return the size/align/format of '__bf16'.
+  unsigned getBFloat16Width() const { return BFloat16Width; }
+  unsigned getBFloat16Align() const { return BFloat16Align; }
+  const llvm::fltSemantics &getBFloat16Format() const { return *BFloat16Format; }
+
   /// getDoubleWidth/Align/Format - Return the size/align/format of 'double'.
   unsigned getDoubleWidth() const { return DoubleWidth; }
   unsigned getDoubleAlign() const { return DoubleAlign; }
@@ -637,6 +647,11 @@
   /// Return the mangled code of __float128.
   virtual const char *getFloat128Mangling() const { return "g"; }
 
+  /// Return the mangled code of bfloat.
+  virtual const char *getBFloat16Mangling() const {
+    llvm_unreachable("bfloat not implemented on this target");
+  }
+
   /// Return the value for the C99 FLT_EVAL_METHOD macro.
   virtual unsigned getFloatEvalMethod() const { return 0; }
 
diff --git a/clang/include/clang/Basic/TokenKinds.def b/clang/include/clang/Basic/TokenKinds.def
--- a/clang/include/clang/Basic/TokenKinds.def
+++ b/clang/include/clang/Basic/TokenKinds.def
@@ -591,6 +591,7 @@
 
 // ARM NEON extensions.
 ALIAS("__fp16", half                , KEYALL)
+KEYWORD(__bf16                      , KEYALL)
 
 // OpenCL Extension.
 KEYWORD(half                        , HALFSUPPORT)
diff --git a/clang/include/clang/Sema/DeclSpec.h b/clang/include/clang/Sema/DeclSpec.h
--- a/clang/include/clang/Sema/DeclSpec.h
+++ b/clang/include/clang/Sema/DeclSpec.h
@@ -281,6 +281,7 @@
   static const TST TST_int128 = clang::TST_int128;
   static const TST TST_extint = clang::TST_extint;
   static const TST TST_half = clang::TST_half;
+  static const TST TST_BFloat16 = clang::TST_BFloat16;
   static const TST TST_float = clang::TST_float;
   static const TST TST_double = clang::TST_double;
   static const TST TST_float16 = clang::TST_Float16;
diff --git a/clang/include/clang/Serialization/ASTBitCodes.h b/clang/include/clang/Serialization/ASTBitCodes.h
--- a/clang/include/clang/Serialization/ASTBitCodes.h
+++ b/clang/include/clang/Serialization/ASTBitCodes.h
@@ -1057,6 +1057,9 @@
       /// The placeholder type for OpenMP iterator expression.
       PREDEF_TYPE_OMP_ITERATOR = 71,
 
+      /// \brief The '__bf16' type
+      PREDEF_TYPE_BFLOAT16_ID = 72,
+
       /// OpenCL image types with auto numeration
 #define IMAGE_TYPE(ImgType, Id, SingletonId, Access, Suffix) \
       PREDEF_TYPE_##Id##_ID,
diff --git a/clang/lib/AST/ASTContext.cpp b/clang/lib/AST/ASTContext.cpp
--- a/clang/lib/AST/ASTContext.cpp
+++ b/clang/lib/AST/ASTContext.cpp
@@ -100,7 +100,7 @@
 using namespace clang;
 
 enum FloatingRank {
-  Float16Rank, HalfRank, FloatRank, DoubleRank, LongDoubleRank, Float128Rank
+  BFloat16Rank, Float16Rank, HalfRank, FloatRank, DoubleRank, LongDoubleRank, Float128Rank
 };
 
 /// \returns location that is relevant when searching for Doc comments related
@@ -1446,6 +1446,8 @@
   // half type (OpenCL 6.1.1.1) / ARM NEON __fp16
   InitBuiltinType(HalfTy, BuiltinType::Half);
 
+  InitBuiltinType(BFloat16Ty, BuiltinType::BFloat16);
+
   // Builtin type used to help define __builtin_va_list.
   VaListTagDecl = nullptr;
 
@@ -1649,6 +1651,8 @@
   switch (T->castAs<BuiltinType>()->getKind()) {
   default:
     llvm_unreachable("Not a floating point type!");
+  case BuiltinType::BFloat16:
+    return Target->getBFloat16Format();
   case BuiltinType::Float16:
   case BuiltinType::Half:
     return Target->getHalfFormat();
@@ -2043,6 +2047,10 @@
       Width = Target->getLongFractWidth();
       Align = Target->getLongFractAlign();
       break;
+    case BuiltinType::BFloat16:
+      Width = Target->getBFloat16Width();
+      Align = Target->getBFloat16Align();
+      break;
     case BuiltinType::Float16:
     case BuiltinType::Half:
       if (Target->hasFloat16Type() || !getLangOpts().OpenMP ||
@@ -5982,6 +5990,7 @@
   case BuiltinType::Double:     return DoubleRank;
   case BuiltinType::LongDouble: return LongDoubleRank;
   case BuiltinType::Float128:   return Float128Rank;
+  case BuiltinType::BFloat16:   return BFloat16Rank;
   }
 }
 
@@ -5994,6 +6003,7 @@
   FloatingRank EltRank = getFloatingRank(Size);
   if (Domain->isComplexType()) {
     switch (EltRank) {
+    case BFloat16Rank: llvm_unreachable("Complex bfloat16 is not supported");
     case Float16Rank:
     case HalfRank: llvm_unreachable("Complex half is not supported");
     case FloatRank:      return FloatComplexTy;
@@ -6006,6 +6016,7 @@
   assert(Domain->isRealFloatingType() && "Unknown domain!");
   switch (EltRank) {
   case Float16Rank:    return HalfTy;
+  case BFloat16Rank:   return BFloat16Ty;
   case HalfRank:       return HalfTy;
   case FloatRank:      return FloatTy;
   case DoubleRank:     return DoubleTy;
@@ -6983,6 +6994,7 @@
     case BuiltinType::LongDouble: return 'D';
     case BuiltinType::NullPtr:    return '*'; // like char*
 
+    case BuiltinType::BFloat16:
     case BuiltinType::Float16:
     case BuiltinType::Float128:
     case BuiltinType::Half:
@@ -9890,6 +9902,11 @@
   // Read the base type.
   switch (*Str++) {
   default: llvm_unreachable("Unknown builtin type letter!");
+  case 'y':
+    assert(HowLong == 0 && !Signed && !Unsigned &&
+           "Bad modifiers used with 'y'!");
+    Type = Context.BFloat16Ty;
+    break;
   case 'v':
     assert(HowLong == 0 && !Signed && !Unsigned &&
            "Bad modifiers used with 'v'!");
diff --git a/clang/lib/AST/ItaniumMangle.cpp b/clang/lib/AST/ItaniumMangle.cpp
--- a/clang/lib/AST/ItaniumMangle.cpp
+++ b/clang/lib/AST/ItaniumMangle.cpp
@@ -2764,6 +2764,11 @@
     Out << TI->getFloat128Mangling();
     break;
   }
+  case BuiltinType::BFloat16: {
+    const TargetInfo *TI = &getASTContext().getTargetInfo();
+    Out << TI->getBFloat16Mangling();
+    break;
+  }
   case BuiltinType::NullPtr:
     Out << "Dn";
     break;
@@ -3179,7 +3184,8 @@
     case BuiltinType::ULongLong: EltName = "uint64_t"; break;
     case BuiltinType::Double:    EltName = "float64_t"; break;
     case BuiltinType::Float:     EltName = "float32_t"; break;
-    case BuiltinType::Half:      EltName = "float16_t";break;
+    case BuiltinType::Half:      EltName = "float16_t"; break;
+    case BuiltinType::BFloat16:  EltName = "bfloat16_t"; break;
     default:
       llvm_unreachable("unexpected Neon vector element type");
     }
@@ -3231,6 +3237,8 @@
     return "Float32";
   case BuiltinType::Double:
     return "Float64";
+  case BuiltinType::BFloat16:
+    return "BFloat16";
   default:
     llvm_unreachable("Unexpected vector element base type");
   }
diff --git a/clang/lib/AST/MicrosoftMangle.cpp b/clang/lib/AST/MicrosoftMangle.cpp
--- a/clang/lib/AST/MicrosoftMangle.cpp
+++ b/clang/lib/AST/MicrosoftMangle.cpp
@@ -2114,6 +2114,7 @@
   case BuiltinType::SatUShortFract:
   case BuiltinType::SatUFract:
   case BuiltinType::SatULongFract:
+  case BuiltinType::BFloat16:
   case BuiltinType::Float128: {
     DiagnosticsEngine &Diags = Context.getDiags();
     unsigned DiagID = Diags.getCustomDiagID(
diff --git a/clang/lib/AST/NSAPI.cpp b/clang/lib/AST/NSAPI.cpp
--- a/clang/lib/AST/NSAPI.cpp
+++ b/clang/lib/AST/NSAPI.cpp
@@ -485,6 +485,7 @@
   case BuiltinType::OMPArraySection:
   case BuiltinType::OMPArrayShaping:
   case BuiltinType::OMPIterator:
+  case BuiltinType::BFloat16:
     break;
   }
 
diff --git a/clang/lib/AST/PrintfFormatString.cpp b/clang/lib/AST/PrintfFormatString.cpp
--- a/clang/lib/AST/PrintfFormatString.cpp
+++ b/clang/lib/AST/PrintfFormatString.cpp
@@ -752,6 +752,7 @@
   case BuiltinType::UInt128:
   case BuiltinType::Int128:
   case BuiltinType::Half:
+  case BuiltinType::BFloat16:
   case BuiltinType::Float16:
   case BuiltinType::Float128:
   case BuiltinType::ShortAccum:
diff --git a/clang/lib/AST/Type.cpp b/clang/lib/AST/Type.cpp
--- a/clang/lib/AST/Type.cpp
+++ b/clang/lib/AST/Type.cpp
@@ -2137,7 +2137,8 @@
 bool Type::isArithmeticType() const {
   if (const auto *BT = dyn_cast<BuiltinType>(CanonicalType))
     return BT->getKind() >= BuiltinType::Bool &&
-           BT->getKind() <= BuiltinType::Float128;
+           BT->getKind() <= BuiltinType::Float128 &&
+           BT->getKind() != BuiltinType::BFloat16;
   if (const auto *ET = dyn_cast<EnumType>(CanonicalType))
     // GCC allows forward declaration of enum types (forbid by C99 6.7.2.3p2).
     // If a body isn't seen by the time we get here, return false.
@@ -2922,6 +2923,8 @@
     return "unsigned __int128";
   case Half:
     return Policy.Half ? "half" : "__fp16";
+  case BFloat16:
+    return "__bf16";
   case Float:
     return "float";
   case Double:
diff --git a/clang/lib/AST/TypeLoc.cpp b/clang/lib/AST/TypeLoc.cpp
--- a/clang/lib/AST/TypeLoc.cpp
+++ b/clang/lib/AST/TypeLoc.cpp
@@ -375,6 +375,7 @@
   case BuiltinType::SatUShortFract:
   case BuiltinType::SatUFract:
   case BuiltinType::SatULongFract:
+  case BuiltinType::BFloat16:
     llvm_unreachable("Builtin type needs extra local data!");
     // Fall through, if the impossible happens.
 
diff --git a/clang/lib/Basic/TargetInfo.cpp b/clang/lib/Basic/TargetInfo.cpp
--- a/clang/lib/Basic/TargetInfo.cpp
+++ b/clang/lib/Basic/TargetInfo.cpp
@@ -36,6 +36,7 @@
   HasLegalHalfType = false;
   HasFloat128 = false;
   HasFloat16 = false;
+  HasBFloat16 = false;
   PointerWidth = PointerAlign = 32;
   BoolWidth = BoolAlign = 8;
   IntWidth = IntAlign = 32;
diff --git a/clang/lib/Basic/Targets/AArch64.h b/clang/lib/Basic/Targets/AArch64.h
--- a/clang/lib/Basic/Targets/AArch64.h
+++ b/clang/lib/Basic/Targets/AArch64.h
@@ -119,6 +119,7 @@
 
   int getEHDataRegisterNumber(unsigned RegNo) const override;
 
+  const char *getBFloat16Mangling() const override { return "u6__bf16"; };
   bool hasInt128Type() const override;
 
   bool hasExtIntType() const override { return true; }
diff --git a/clang/lib/Basic/Targets/AArch64.cpp b/clang/lib/Basic/Targets/AArch64.cpp
--- a/clang/lib/Basic/Targets/AArch64.cpp
+++ b/clang/lib/Basic/Targets/AArch64.cpp
@@ -70,6 +70,9 @@
   LongDoubleWidth = LongDoubleAlign = SuitableAlign = 128;
   LongDoubleFormat = &llvm::APFloat::IEEEquad();
 
+  BFloat16Width = BFloat16Align = 16;
+  BFloat16Format = &llvm::APFloat::BFloat();
+
   // Make __builtin_ms_va_list available.
   HasBuiltinMSVaList = true;
 
@@ -360,6 +363,7 @@
   HasMTE = false;
   HasTME = false;
   HasMatMul = false;
+  HasBFloat16 = false;
   ArchKind = llvm::AArch64::ArchKind::ARMV8A;
 
   for (const auto &Feature : Features) {
@@ -397,6 +401,8 @@
       HasTME = true;
     if (Feature == "+i8mm")
       HasMatMul = true;
+    if (Feature == "+bf16")
+      HasBFloat16 = true;
   }
 
   setDataLayout();
diff --git a/clang/lib/Basic/Targets/ARM.h b/clang/lib/Basic/Targets/ARM.h
--- a/clang/lib/Basic/Targets/ARM.h
+++ b/clang/lib/Basic/Targets/ARM.h
@@ -184,6 +184,8 @@
   bool hasSjLjLowering() const override;
 
   bool hasExtIntType() const override { return true; }
+  
+  const char *getBFloat16Mangling() const override { return "u6__bf16"; };
 };
 
 class LLVM_LIBRARY_VISIBILITY ARMleTargetInfo : public ARMTargetInfo {
diff --git a/clang/lib/Basic/Targets/ARM.cpp b/clang/lib/Basic/Targets/ARM.cpp
--- a/clang/lib/Basic/Targets/ARM.cpp
+++ b/clang/lib/Basic/Targets/ARM.cpp
@@ -25,6 +25,9 @@
   IsAAPCS = true;
 
   DoubleAlign = LongLongAlign = LongDoubleAlign = SuitableAlign = 64;
+  BFloat16Width = BFloat16Align = 16;
+  BFloat16Format = &llvm::APFloat::BFloat();
+
   const llvm::Triple &T = getTriple();
 
   bool IsNetBSD = T.isOSNetBSD();
@@ -74,6 +77,8 @@
     DoubleAlign = LongLongAlign = LongDoubleAlign = SuitableAlign = 64;
   else
     DoubleAlign = LongLongAlign = LongDoubleAlign = SuitableAlign = 32;
+  BFloat16Width = BFloat16Align = 16;
+  BFloat16Format = &llvm::APFloat::BFloat();
 
   WCharType = SignedInt;
 
@@ -428,6 +433,7 @@
   HasMatMul = 0;
   HasFloat16 = true;
   ARMCDECoprocMask = 0;
+  HasBFloat16 = false;
 
   // This does not diagnose illegal cases like having both
   // "+vfpv2" and "+vfpv3" or having "+neon" and "-fp64".
@@ -498,6 +504,8 @@
                Feature <= "+cdecp7") {
       unsigned Coproc = Feature.back() - '0';
       ARMCDECoprocMask |= (1U << Coproc);
+    } else if (Feature == "+bf16") {
+      HasBFloat16 = true;
     }
   }
 
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -4479,7 +4479,8 @@
 static llvm::VectorType *GetNeonType(CodeGenFunction *CGF,
                                      NeonTypeFlags TypeFlags,
                                      bool HasLegalHalfType=true,
-                                     bool V1Ty=false) {
+                                     bool V1Ty=false,
+                                     bool HasBFloat16Type=true) {
   int IsQuad = TypeFlags.isQuad();
   switch (TypeFlags.getEltType()) {
   case NeonTypeFlags::Int8:
@@ -4488,6 +4489,11 @@
   case NeonTypeFlags::Int16:
   case NeonTypeFlags::Poly16:
     return llvm::VectorType::get(CGF->Int16Ty, V1Ty ? 1 : (4 << IsQuad));
+  case NeonTypeFlags::BFloat16:
+    if (HasBFloat16Type)
+      return llvm::VectorType::get(CGF->BFloatTy, V1Ty ? 1 : (4 << IsQuad));
+    else
+      return llvm::VectorType::get(CGF->Int16Ty, V1Ty ? 1 : (4 << IsQuad));
   case NeonTypeFlags::Float16:
     if (HasLegalHalfType)
       return llvm::VectorType::get(CGF->HalfTy, V1Ty ? 1 : (4 << IsQuad));
@@ -5503,8 +5509,9 @@
   bool Usgn = Type.isUnsigned();
   bool Quad = Type.isQuad();
   const bool HasLegalHalfType = getTarget().hasLegalHalfType();
+  const bool HasBFloat16Type = getTarget().hasBFloat16Type();
 
-  llvm::VectorType *VTy = GetNeonType(this, Type, HasLegalHalfType);
+  llvm::VectorType *VTy = GetNeonType(this, Type, HasLegalHalfType, false, HasBFloat16Type);
   llvm::Type *Ty = VTy;
   if (!Ty)
     return nullptr;
@@ -6973,7 +6980,9 @@
   bool rightShift = false;
 
   llvm::VectorType *VTy = GetNeonType(this, Type,
-                                      getTarget().hasLegalHalfType());
+                                      getTarget().hasLegalHalfType(),
+                                      false,
+                                      getTarget().hasBFloat16Type());
   llvm::Type *Ty = VTy;
   if (!Ty)
     return nullptr;
diff --git a/clang/lib/CodeGen/CGDebugInfo.cpp b/clang/lib/CodeGen/CGDebugInfo.cpp
--- a/clang/lib/CodeGen/CGDebugInfo.cpp
+++ b/clang/lib/CodeGen/CGDebugInfo.cpp
@@ -768,6 +768,7 @@
   case BuiltinType::Float:
   case BuiltinType::LongDouble:
   case BuiltinType::Float16:
+  case BuiltinType::BFloat16:
   case BuiltinType::Float128:
   case BuiltinType::Double:
     // FIXME: For targets where long double and __float128 have the same size,
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -112,6 +112,7 @@
   Int32Ty = llvm::Type::getInt32Ty(LLVMContext);
   Int64Ty = llvm::Type::getInt64Ty(LLVMContext);
   HalfTy = llvm::Type::getHalfTy(LLVMContext);
+  BFloatTy = llvm::Type::getBFloatTy(LLVMContext);
   FloatTy = llvm::Type::getFloatTy(LLVMContext);
   DoubleTy = llvm::Type::getDoubleTy(LLVMContext);
   PointerWidthInBits = C.getTargetInfo().getPointerWidth(0);
diff --git a/clang/lib/CodeGen/CodeGenTypeCache.h b/clang/lib/CodeGen/CodeGenTypeCache.h
--- a/clang/lib/CodeGen/CodeGenTypeCache.h
+++ b/clang/lib/CodeGen/CodeGenTypeCache.h
@@ -35,8 +35,8 @@
 
   /// i8, i16, i32, and i64
   llvm::IntegerType *Int8Ty, *Int16Ty, *Int32Ty, *Int64Ty;
-  /// float, double
-  llvm::Type *HalfTy, *FloatTy, *DoubleTy;
+  /// half, bfloat, float, double
+  llvm::Type *HalfTy, *BFloatTy, *FloatTy, *DoubleTy;
 
   /// int
   llvm::IntegerType *IntTy;
diff --git a/clang/lib/CodeGen/CodeGenTypes.cpp b/clang/lib/CodeGen/CodeGenTypes.cpp
--- a/clang/lib/CodeGen/CodeGenTypes.cpp
+++ b/clang/lib/CodeGen/CodeGenTypes.cpp
@@ -300,6 +300,8 @@
     else
       return llvm::Type::getInt16Ty(VMContext);
   }
+  if (&format == &llvm::APFloat::BFloat())
+    return llvm::Type::getBFloatTy(VMContext);
   if (&format == &llvm::APFloat::IEEEsingle())
     return llvm::Type::getFloatTy(VMContext);
   if (&format == &llvm::APFloat::IEEEdouble())
@@ -498,6 +500,7 @@
           Context.getLangOpts().NativeHalfType ||
               !Context.getTargetInfo().useFP16ConversionIntrinsics());
       break;
+    case BuiltinType::BFloat16:
     case BuiltinType::Float:
     case BuiltinType::Double:
     case BuiltinType::LongDouble:
diff --git a/clang/lib/CodeGen/ItaniumCXXABI.cpp b/clang/lib/CodeGen/ItaniumCXXABI.cpp
--- a/clang/lib/CodeGen/ItaniumCXXABI.cpp
+++ b/clang/lib/CodeGen/ItaniumCXXABI.cpp
@@ -3027,6 +3027,7 @@
     case BuiltinType::SatUShortFract:
     case BuiltinType::SatUFract:
     case BuiltinType::SatULongFract:
+    case BuiltinType::BFloat16:
       return false;
 
     case BuiltinType::Dependent:
diff --git a/clang/lib/CodeGen/TargetInfo.cpp b/clang/lib/CodeGen/TargetInfo.cpp
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -5979,11 +5979,14 @@
 
 private:
   ABIKind Kind;
+  bool IsFloatABISoftFP;
 
 public:
   ARMABIInfo(CodeGenTypes &CGT, ABIKind _Kind)
       : SwiftABIInfo(CGT), Kind(_Kind) {
     setCCs();
+    IsFloatABISoftFP = CGT.getCodeGenOpts().FloatABI == "softfp" ||
+        CGT.getCodeGenOpts().FloatABI == ""; // default
   }
 
   bool isEABI() const {
@@ -6253,9 +6256,9 @@
   if (isIllegalVectorType(Ty))
     return coerceIllegalVector(Ty);
 
-  // _Float16 and __fp16 get passed as if it were an int or float, but with
-  // the top 16 bits unspecified. This is not done for OpenCL as it handles the
-  // half type natively, and does not need to interwork with AAPCS code.
+  // _Float16 and __fp16 get passed as if it were an int or float, but
+  // with the top 16 bits unspecified. This is not done for OpenCL as it handles
+  // the half type natively, and does not need to interwork with AAPCS code.
   if ((Ty->isFloat16Type() || Ty->isHalfType()) &&
       !getContext().getLangOpts().NativeHalfArgsAndReturns) {
     llvm::Type *ResType = IsAAPCS_VFP ?
@@ -6264,6 +6267,13 @@
     return ABIArgInfo::getDirect(ResType);
   }
 
+  // __bf16  get passed using the bfloat ir type, or using i32 but
+  // with the top 16 bits unspecified.
+  if (Ty->isBFloat16Type() && IsFloatABISoftFP) {
+    llvm::Type *ResType = llvm::Type::getInt32Ty(getVMContext());
+    return ABIArgInfo::getDirect(ResType);
+  }
+
   if (!isAggregateTypeForABI(Ty)) {
     // Treat an enum type as its underlying type.
     if (const EnumType *EnumTy = Ty->getAs<EnumType>()) {
@@ -6457,10 +6467,13 @@
     // Large vector types should be returned via memory.
     if (getContext().getTypeSize(RetTy) > 128)
       return getNaturalAlignIndirect(RetTy);
-    // FP16 vectors should be converted to integer vectors
-    if (!getTarget().hasLegalHalfType() &&
+    // FP16/BF16 vectors should be converted to integer vectors
+    // This check is similar  to isIllegalVectorType - refactor?
+    if ((!getTarget().hasLegalHalfType() &&
         (VT->getElementType()->isFloat16Type() ||
-         VT->getElementType()->isHalfType()))
+         VT->getElementType()->isHalfType())) ||
+        (IsFloatABISoftFP &&
+         VT->getElementType()->isBFloat16Type()))
       return coerceIllegalVector(RetTy);
   }
 
@@ -6475,6 +6488,15 @@
     return ABIArgInfo::getDirect(ResType);
   }
 
+  // if we're using the softfp float abi, __bf16 get returned as if it were an
+  // int but with the top 16 bits unspecified.
+  if (RetTy->isBFloat16Type()) {
+    llvm::Type *ResType = IsAAPCS_VFP ?
+      llvm::Type::getBFloatTy(getVMContext()) :
+      llvm::Type::getInt32Ty(getVMContext());
+    return ABIArgInfo::getDirect(ResType);
+  }
+
   if (!isAggregateTypeForABI(RetTy)) {
     // Treat an enum type as its underlying type.
     if (const EnumType *EnumTy = RetTy->getAs<EnumType>())
@@ -6561,12 +6583,17 @@
 /// isIllegalVector - check whether Ty is an illegal vector type.
 bool ARMABIInfo::isIllegalVectorType(QualType Ty) const {
   if (const VectorType *VT = Ty->getAs<VectorType> ()) {
-    // On targets that don't support FP16, FP16 is expanded into float, and we
-    // don't want the ABI to depend on whether or not FP16 is supported in
-    // hardware. Thus return false to coerce FP16 vectors into integer vectors.
-    if (!getTarget().hasLegalHalfType() &&
+    // On targets that don't support half, fp16 or bfloat, they are expanded
+    // into float, and we don't want the ABI to depend on whether or not they
+    // are supported in hardware. Thus return false to coerce vectors of these
+    // types into integer vectors.
+    // We do not depend on hasLegalHalfType for bfloat as it is a
+    // separate IR type.
+    if ((!getTarget().hasLegalHalfType() &&
         (VT->getElementType()->isFloat16Type() ||
-         VT->getElementType()->isHalfType()))
+         VT->getElementType()->isHalfType())) ||
+        (IsFloatABISoftFP &&
+         VT->getElementType()->isBFloat16Type()))
       return true;
     if (isAndroid()) {
       // Android shipped using Clang 3.1, which supported a slightly different
@@ -6618,6 +6645,7 @@
   } else {
     if (const VectorType *VT = Ty->getAs<VectorType>())
       return (VT->getElementType()->isFloat16Type() ||
+              VT->getElementType()->isBFloat16Type() ||
               VT->getElementType()->isHalfType());
     return false;
   }
diff --git a/clang/lib/Format/FormatToken.cpp b/clang/lib/Format/FormatToken.cpp
--- a/clang/lib/Format/FormatToken.cpp
+++ b/clang/lib/Format/FormatToken.cpp
@@ -50,6 +50,7 @@
   case tok::kw_half:
   case tok::kw_float:
   case tok::kw_double:
+  case tok::kw___bf16:
   case tok::kw__Float16:
   case tok::kw___float128:
   case tok::kw_wchar_t:
diff --git a/clang/lib/Index/USRGeneration.cpp b/clang/lib/Index/USRGeneration.cpp
--- a/clang/lib/Index/USRGeneration.cpp
+++ b/clang/lib/Index/USRGeneration.cpp
@@ -753,6 +753,7 @@
         case BuiltinType::SatUShortFract:
         case BuiltinType::SatUFract:
         case BuiltinType::SatULongFract:
+        case BuiltinType::BFloat16:
           IgnoreResults = true;
           return;
         case BuiltinType::ObjCId:
diff --git a/clang/lib/Parse/ParseDecl.cpp b/clang/lib/Parse/ParseDecl.cpp
--- a/clang/lib/Parse/ParseDecl.cpp
+++ b/clang/lib/Parse/ParseDecl.cpp
@@ -3842,6 +3842,10 @@
       isInvalid = DS.SetTypeSpecType(DeclSpec::TST_half, Loc, PrevSpec,
                                      DiagID, Policy);
       break;
+    case tok::kw___bf16:
+      isInvalid = DS.SetTypeSpecType(DeclSpec::TST_BFloat16, Loc, PrevSpec,
+                                     DiagID, Policy);
+      break;
     case tok::kw_float:
       isInvalid = DS.SetTypeSpecType(DeclSpec::TST_float, Loc, PrevSpec,
                                      DiagID, Policy);
@@ -4942,6 +4946,7 @@
   case tok::kw_char32_t:
   case tok::kw_int:
   case tok::kw__ExtInt:
+  case tok::kw___bf16:
   case tok::kw_half:
   case tok::kw_float:
   case tok::kw_double:
@@ -5023,6 +5028,7 @@
   case tok::kw_int:
   case tok::kw__ExtInt:
   case tok::kw_half:
+  case tok::kw___bf16:
   case tok::kw_float:
   case tok::kw_double:
   case tok::kw__Accum:
@@ -5190,6 +5196,7 @@
   case tok::kw_int:
   case tok::kw__ExtInt:
   case tok::kw_half:
+  case tok::kw___bf16:
   case tok::kw_float:
   case tok::kw_double:
   case tok::kw__Accum:
diff --git a/clang/lib/Parse/ParseExpr.cpp b/clang/lib/Parse/ParseExpr.cpp
--- a/clang/lib/Parse/ParseExpr.cpp
+++ b/clang/lib/Parse/ParseExpr.cpp
@@ -1499,6 +1499,7 @@
   case tok::kw_half:
   case tok::kw_float:
   case tok::kw_double:
+  case tok::kw___bf16:
   case tok::kw__Float16:
   case tok::kw___float128:
   case tok::kw_void:
diff --git a/clang/lib/Parse/ParseExprCXX.cpp b/clang/lib/Parse/ParseExprCXX.cpp
--- a/clang/lib/Parse/ParseExprCXX.cpp
+++ b/clang/lib/Parse/ParseExprCXX.cpp
@@ -2201,6 +2201,9 @@
   case tok::kw___int128:
     DS.SetTypeSpecType(DeclSpec::TST_int128, Loc, PrevSpec, DiagID, Policy);
     break;
+  case tok::kw___bf16:
+    DS.SetTypeSpecType(DeclSpec::TST_BFloat16, Loc, PrevSpec, DiagID, Policy);
+    break;
   case tok::kw_half:
     DS.SetTypeSpecType(DeclSpec::TST_half, Loc, PrevSpec, DiagID, Policy);
     break;
diff --git a/clang/lib/Parse/ParseTentative.cpp b/clang/lib/Parse/ParseTentative.cpp
--- a/clang/lib/Parse/ParseTentative.cpp
+++ b/clang/lib/Parse/ParseTentative.cpp
@@ -1631,6 +1631,7 @@
   case tok::kw_half:
   case tok::kw_float:
   case tok::kw_double:
+  case tok::kw___bf16:
   case tok::kw__Float16:
   case tok::kw___float128:
   case tok::kw_void:
@@ -1744,6 +1745,7 @@
   case tok::kw_half:
   case tok::kw_float:
   case tok::kw_double:
+  case tok::kw___bf16:
   case tok::kw__Float16:
   case tok::kw___float128:
   case tok::kw_void:
diff --git a/clang/lib/Sema/DeclSpec.cpp b/clang/lib/Sema/DeclSpec.cpp
--- a/clang/lib/Sema/DeclSpec.cpp
+++ b/clang/lib/Sema/DeclSpec.cpp
@@ -368,6 +368,7 @@
     case TST_unspecified:
     case TST_void:
     case TST_wchar:
+    case TST_BFloat16:
 #define GENERIC_IMAGE_TYPE(ImgType, Id) case TST_##ImgType##_t:
 #include "clang/Basic/OpenCLImageTypes.def"
       return false;
@@ -566,6 +567,7 @@
   case DeclSpec::TST_underlyingType: return "__underlying_type";
   case DeclSpec::TST_unknown_anytype: return "__unknown_anytype";
   case DeclSpec::TST_atomic: return "_Atomic";
+  case DeclSpec::TST_BFloat16: return "__bf16";
 #define GENERIC_IMAGE_TYPE(ImgType, Id) \
   case DeclSpec::TST_##ImgType##_t: \
     return #ImgType "_t";
diff --git a/clang/lib/Sema/SemaCast.cpp b/clang/lib/Sema/SemaCast.cpp
--- a/clang/lib/Sema/SemaCast.cpp
+++ b/clang/lib/Sema/SemaCast.cpp
@@ -2786,6 +2786,20 @@
     return;
   }
 
+  // Can't cast to or from bfloat
+  if (DestType->isBFloat16Type() && !SrcType->isBFloat16Type()) {
+    Self.Diag(SrcExpr.get()->getExprLoc(), diag::err_cast_to_bfloat16)
+        << SrcExpr.get()->getSourceRange();
+    SrcExpr = ExprError();
+    return;
+  }
+  if (SrcType->isBFloat16Type() && !DestType->isBFloat16Type()) {
+    Self.Diag(SrcExpr.get()->getExprLoc(), diag::err_cast_from_bfloat16)
+        << SrcExpr.get()->getSourceRange();
+    SrcExpr = ExprError();
+    return;
+  }
+
   // If either type is a pointer, the other type has to be either an
   // integer or a pointer.
   if (!DestType->isArithmeticType()) {
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -1961,6 +1961,9 @@
   case NeonTypeFlags::Float64:
     assert(!shift && "cannot shift float types!");
     return (1 << IsQuad) - 1;
+  case NeonTypeFlags::BFloat16:
+    assert(!shift && "cannot shift float types!");
+    return (4 << IsQuad) - 1;
   }
   llvm_unreachable("Invalid NeonTypeFlag!");
 }
@@ -2000,6 +2003,8 @@
     return Context.FloatTy;
   case NeonTypeFlags::Float64:
     return Context.DoubleTy;
+  case NeonTypeFlags::BFloat16:
+    return Context.BFloat16Ty;
   }
   llvm_unreachable("Invalid NeonTypeFlag!");
 }
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -138,6 +138,7 @@
   case tok::kw_half:
   case tok::kw_float:
   case tok::kw_double:
+  case tok::kw___bf16:
   case tok::kw__Float16:
   case tok::kw___float128:
   case tok::kw_wchar_t:
diff --git a/clang/lib/Sema/SemaExpr.cpp b/clang/lib/Sema/SemaExpr.cpp
--- a/clang/lib/Sema/SemaExpr.cpp
+++ b/clang/lib/Sema/SemaExpr.cpp
@@ -7996,6 +7996,11 @@
     return ResTy;
   }
 
+  // And if they're both bfloat (which isn't arithmetic), that's fine too.
+  if (LHSTy->isBFloat16Type() && RHSTy->isBFloat16Type()) {
+    return LHSTy;
+  }
+
   // If both operands are the same structure or union type, the result is that
   // type.
   if (const RecordType *LHSRT = LHSTy->getAs<RecordType>()) {    // C99 6.5.15p3
diff --git a/clang/lib/Sema/SemaOverload.cpp b/clang/lib/Sema/SemaOverload.cpp
--- a/clang/lib/Sema/SemaOverload.cpp
+++ b/clang/lib/Sema/SemaOverload.cpp
@@ -1870,6 +1870,10 @@
     // FIXME: disable conversions between long double and __float128 if
     // their representation is different until there is back end support
     // We of course allow this conversion if long double is really double.
+
+    // conversions between bfloat and other floats are not permitted
+    if (FromType == S.Context.BFloat16Ty || ToType == S.Context.BFloat16Ty)
+      return false;
     if (&S.Context.getFloatTypeSemantics(FromType) !=
         &S.Context.getFloatTypeSemantics(ToType)) {
       bool Float128AndLongDouble = ((FromType == S.Context.Float128Ty &&
@@ -1888,6 +1892,10 @@
               ToType->isIntegralType(S.Context)) ||
              (FromType->isIntegralOrUnscopedEnumerationType() &&
               ToType->isRealFloatingType())) {
+    // conversions between bfloat and int are not permitted
+    if (FromType->isBFloat16Type() || ToType->isBFloat16Type())
+      return false;
+
     // Floating-integral conversions (C++ 4.9).
     SCS.Second = ICK_Floating_Integral;
     FromType = ToType.getUnqualifiedType();
diff --git a/clang/lib/Sema/SemaTemplateVariadic.cpp b/clang/lib/Sema/SemaTemplateVariadic.cpp
--- a/clang/lib/Sema/SemaTemplateVariadic.cpp
+++ b/clang/lib/Sema/SemaTemplateVariadic.cpp
@@ -881,6 +881,7 @@
   case TST_auto:
   case TST_auto_type:
   case TST_decltype_auto:
+  case TST_BFloat16:
 #define GENERIC_IMAGE_TYPE(ImgType, Id) case TST_##ImgType##_t:
 #include "clang/Basic/OpenCLImageTypes.def"
   case TST_unknown_anytype:
diff --git a/clang/lib/Sema/SemaType.cpp b/clang/lib/Sema/SemaType.cpp
--- a/clang/lib/Sema/SemaType.cpp
+++ b/clang/lib/Sema/SemaType.cpp
@@ -1521,6 +1521,12 @@
     Result = Context.Float16Ty;
     break;
   case DeclSpec::TST_half:    Result = Context.HalfTy; break;
+  case DeclSpec::TST_BFloat16:
+    if (!S.Context.getTargetInfo().hasBFloat16Type())
+      S.Diag(DS.getTypeSpecTypeLoc(), diag::err_type_unsupported)
+        << "__bf16";
+    Result = Context.BFloat16Ty;
+    break;
   case DeclSpec::TST_float:   Result = Context.FloatTy; break;
   case DeclSpec::TST_double:
     if (DS.getTypeSpecWidth() == DeclSpec::TSW_long)
@@ -7672,7 +7678,8 @@
          BTy->getKind() == BuiltinType::LongLong ||
          BTy->getKind() == BuiltinType::ULongLong ||
          BTy->getKind() == BuiltinType::Float ||
-         BTy->getKind() == BuiltinType::Half;
+         BTy->getKind() == BuiltinType::Half ||
+         BTy->getKind() == BuiltinType::BFloat16;
 }
 
 /// HandleNeonVectorTypeAttr - The "neon_vector_type" and
diff --git a/clang/lib/Serialization/ASTCommon.cpp b/clang/lib/Serialization/ASTCommon.cpp
--- a/clang/lib/Serialization/ASTCommon.cpp
+++ b/clang/lib/Serialization/ASTCommon.cpp
@@ -249,6 +249,9 @@
   case BuiltinType::OMPIterator:
     ID = PREDEF_TYPE_OMP_ITERATOR;
     break;
+  case BuiltinType::BFloat16:
+    ID = PREDEF_TYPE_BFLOAT16_ID;
+    break;
   }
 
   return TypeIdx(ID);
diff --git a/clang/lib/Serialization/ASTReader.cpp b/clang/lib/Serialization/ASTReader.cpp
--- a/clang/lib/Serialization/ASTReader.cpp
+++ b/clang/lib/Serialization/ASTReader.cpp
@@ -6844,6 +6844,9 @@
     case PREDEF_TYPE_INT128_ID:
       T = Context.Int128Ty;
       break;
+    case PREDEF_TYPE_BFLOAT16_ID:
+      T = Context.BFloat16Ty;
+      break;
     case PREDEF_TYPE_HALF_ID:
       T = Context.HalfTy;
       break;
diff --git a/clang/test/CodeGen/arm-bf16-params-returns.c b/clang/test/CodeGen/arm-bf16-params-returns.c
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGen/arm-bf16-params-returns.c
@@ -0,0 +1,18 @@
+// RUN: %clang_cc1 -triple armv8.6a-arm-none-eabi -target-abi aapcs -mfloat-abi hard -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK32-HARD
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -mfloat-abi hard -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64-HARD
+// RUN: %clang_cc1 -triple armv8.6a-arm-none-eabi -target-abi aapcs -mfloat-abi softfp -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK32-SOFTFP
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-abi aapcs -mfloat-abi softfp -target-feature +bf16 -target-feature +neon -emit-llvm -O2 -o - %s | opt -S -mem2reg -sroa | FileCheck %s --check-prefix=CHECK64-SOFTFP
+
+// function return types
+__bf16 test_ret_bf16(__bf16 v) {
+  return v;
+}
+// CHECK32-HARD: define arm_aapcs_vfpcc bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
+// CHECK32-HARD: ret bfloat %v
+// CHECK64-HARD: define bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
+// CHECK64-HARD: ret bfloat %v
+// CHECK32-SOFTFP: define i32 @test_ret_bf16(i32 [[V0:.*]]) {{.*}} {
+// CHECK32-SOFTFP: %tmp2.0.insert.ext = and i32 [[V0]], 65535
+// CHECK32-SOFTFP: ret i32 %tmp2.0.insert.ext
+// CHECK64-SOFTFP: define bfloat @test_ret_bf16(bfloat returned %v) {{.*}} {
+// CHECK64-SOFTFP: ret bfloat %v
diff --git a/clang/test/CodeGen/arm-mangle-16bit-float.cpp b/clang/test/CodeGen/arm-mangle-16bit-float.cpp
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGen/arm-mangle-16bit-float.cpp
@@ -0,0 +1,6 @@
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -fallow-half-arguments-and-returns -target-feature +fullfp16 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK64
+// RUN: %clang_cc1 -triple arm-arm-none-eabi -fallow-half-arguments-and-returns -target-feature +fullfp16 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK32
+
+// CHECK64: define {{.*}}void @_Z3barDh(half %b)
+// CHECK32: define {{.*}}void @_Z3barDh(i32 %b.coerce)
+void bar(__fp16 b) {}
diff --git a/clang/test/CodeGen/arm-mangle-bf16.cpp b/clang/test/CodeGen/arm-mangle-bf16.cpp
new file mode 100644
--- /dev/null
+++ b/clang/test/CodeGen/arm-mangle-bf16.cpp
@@ -0,0 +1,8 @@
+// RUN: %clang_cc1 -triple aarch64-arm-none-eabi -target-feature +bf16 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK64
+// RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi hard -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK32-HARD
+// RUN: %clang_cc1 -triple arm-arm-none-eabi -target-feature +bf16 -mfloat-abi softfp -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK32-SOFTFP
+
+// CHECK64: define {{.*}}void @_Z3foou6__bf16(bfloat %b)
+// CHECK32-HARD: define {{.*}}void @_Z3foou6__bf16(bfloat %b)
+// CHECK32-SOFTFP: define {{.*}}void @_Z3foou6__bf16(i32 %b.coerce)
+void foo(__bf16 b) {}
diff --git a/clang/test/Sema/arm-bf16-forbidden-ops.c b/clang/test/Sema/arm-bf16-forbidden-ops.c
new file mode 100644
--- /dev/null
+++ b/clang/test/Sema/arm-bf16-forbidden-ops.c
@@ -0,0 +1,71 @@
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64 -target-feature +bf16 %s
+
+__bf16 test_cast_from_float(float in) {
+  return (__bf16)in; // expected-error {{cannot type-cast to __bf16}}
+}
+
+__bf16 test_cast_from_float_literal(void) {
+  return (__bf16)1.0f; // expected-error {{cannot type-cast to __bf16}}
+}
+
+__bf16 test_cast_from_int(int in) {
+  return (__bf16)in; // expected-error {{cannot type-cast to __bf16}}
+}
+
+__bf16 test_cast_from_int_literal(void) {
+  return (__bf16)1; // expected-error {{cannot type-cast to __bf16}}
+}
+
+__bf16 test_cast_bfloat(__bf16 in) {
+  return (__bf16)in; // this one should work
+}
+
+float test_cast_to_float(__bf16 in) {
+  return (float)in; // expected-error {{cannot type-cast from __bf16}}
+}
+
+int test_cast_to_int(__bf16 in) {
+  return (int)in; // expected-error {{cannot type-cast from __bf16}}
+}
+
+__bf16 test_implicit_from_float(float in) {
+  return in; // expected-error {{returning 'float' from a function with incompatible result type '__bf16'}}
+}
+
+__bf16 test_implicit_from_float_literal(void) {
+  return 1.0f; // expected-error {{returning 'float' from a function with incompatible result type '__bf16'}}
+}
+
+__bf16 test_implicit_from_int(int in) {
+  return in; // expected-error {{returning 'int' from a function with incompatible result type '__bf16'}}
+}
+
+__bf16 test_implicit_from_int_literal(void) {
+  return 1; // expected-error {{returning 'int' from a function with incompatible result type '__bf16'}}
+}
+
+__bf16 test_implicit_bfloat(__bf16 in) {
+  return in; // this one should work
+}
+
+float test_implicit_to_float(__bf16 in) {
+  return in; // expected-error {{returning '__bf16' from a function with incompatible result type 'float'}}
+}
+
+int test_implicit_to_int(__bf16 in) {
+  return in; // expected-error {{returning '__bf16' from a function with incompatible result type 'int'}}
+}
+
+__bf16 test_cond(__bf16 a, __bf16 b, _Bool which) {
+  // Conditional operator _should_ be supported, without nonsense
+  // complaints like 'types __bf16 and __bf16 are not compatible'
+  return which ? a : b;
+}
+
+__bf16 test_cond_float(__bf16 a, __bf16 b, _Bool which) {
+  return which ? a : 1.0f; // expected-error {{incompatible operand types ('__bf16' and 'float')}}
+}
+
+__bf16 test_cond_int(__bf16 a, __bf16 b, _Bool which) {
+  return which ? a : 1; // expected-error {{incompatible operand types ('__bf16' and 'int')}}
+}
diff --git a/clang/test/Sema/arm-bf16-forbidden-ops.cpp b/clang/test/Sema/arm-bf16-forbidden-ops.cpp
new file mode 100644
--- /dev/null
+++ b/clang/test/Sema/arm-bf16-forbidden-ops.cpp
@@ -0,0 +1,71 @@
+// RUN: %clang_cc1 -fsyntax-only -verify -triple aarch64 -target-feature +bf16 %s
+
+__bf16 test_static_cast_from_float(float in) {
+  return static_cast<__bf16>(in); // expected-error {{static_cast from 'float' to '__bf16' is not allowed}}
+}
+
+__bf16 test_static_cast_from_float_literal(void) {
+  return static_cast<__bf16>(1.0f); // expected-error {{static_cast from 'float' to '__bf16' is not allowed}}
+}
+
+__bf16 test_static_cast_from_int(int in) {
+  return static_cast<__bf16>(in); // expected-error {{static_cast from 'int' to '__bf16' is not allowed}}
+}
+
+__bf16 test_static_cast_from_int_literal(void) {
+  return static_cast<__bf16>(1); // expected-error {{static_cast from 'int' to '__bf16' is not allowed}}
+}
+
+__bf16 test_static_cast_bfloat(__bf16 in) {
+  return static_cast<__bf16>(in); // this one should work
+}
+
+float test_static_cast_to_float(__bf16 in) {
+  return static_cast<float>(in); // expected-error {{static_cast from '__bf16' to 'float' is not allowed}}
+}
+
+int test_static_cast_to_int(__bf16 in) {
+  return static_cast<int>(in); // expected-error {{static_cast from '__bf16' to 'int' is not allowed}}
+}
+
+__bf16 test_implicit_from_float(float in) {
+  return in; // expected-error {{cannot initialize return object of type '__bf16' with an lvalue of type 'float'}}
+}
+
+__bf16 test_implicit_from_float_literal() {
+  return 1.0f; // expected-error {{cannot initialize return object of type '__bf16' with an rvalue of type 'float'}}
+}
+
+__bf16 test_implicit_from_int(int in) {
+  return in; // expected-error {{cannot initialize return object of type '__bf16' with an lvalue of type 'int'}}
+}
+
+__bf16 test_implicit_from_int_literal() {
+  return 1; // expected-error {{cannot initialize return object of type '__bf16' with an rvalue of type 'int'}}
+}
+
+__bf16 test_implicit_bfloat(__bf16 in) {
+  return in; // this one should work
+}
+
+float test_implicit_to_float(__bf16 in) {
+  return in; // expected-error {{cannot initialize return object of type 'float' with an lvalue of type '__bf16'}}
+}
+
+int test_implicit_to_int(__bf16 in) {
+  return in; // expected-error {{cannot initialize return object of type 'int' with an lvalue of type '__bf16'}}
+}
+
+__bf16 test_cond(__bf16 a, __bf16 b, bool which) {
+  // Conditional operator _should_ be supported, without nonsense
+  // complaints like 'types __bf16 and __bf16 are not compatible'
+  return which ? a : b;
+}
+
+__bf16 test_cond_float(__bf16 a, __bf16 b, bool which) {
+  return which ? a : 1.0f; // expected-error {{incompatible operand types ('__bf16' and 'float')}}
+}
+
+__bf16 test_cond_int(__bf16 a, __bf16 b, bool which) {
+  return which ? a : 1; // expected-error {{incompatible operand types ('__bf16' and 'int')}}
+}
diff --git a/clang/test/Sema/arm-bfloat.cpp b/clang/test/Sema/arm-bfloat.cpp
new file mode 100644
--- /dev/null
+++ b/clang/test/Sema/arm-bfloat.cpp
@@ -0,0 +1,29 @@
+// RUN: %clang_cc1 -fsyntax-only -verify -std=c++11 \
+// RUN: -triple aarch64-arm-none-eabi -target-cpu cortex-a75 \
+// RUN: -target-feature +bf16 -target-feature +neon %s
+// RUN: %clang_cc1 -fsyntax-only -verify -std=c++11 \
+// RUN: -triple arm-arm-none-eabi -target-cpu cortex-a53 \
+// RUN: -target-feature +bf16 -target-feature +neon %s
+
+void test(bool b) {
+  __bf16 bf16;
+
+  bf16 + bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 - bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 * bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+  bf16 / bf16; // expected-error {{invalid operands to binary expression ('__bf16' and '__bf16')}}
+
+  __fp16 fp16;
+
+  bf16 + fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 + bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 - fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 - bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 * fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 * bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 / fp16; // expected-error {{invalid operands to binary expression ('__bf16' and '__fp16')}}
+  fp16 / bf16; // expected-error {{invalid operands to binary expression ('__fp16' and '__bf16')}}
+  bf16 = fp16; // expected-error {{assigning to '__bf16' from incompatible type '__fp16'}}
+  fp16 = bf16; // expected-error {{assigning to '__fp16' from incompatible type '__bf16'}}
+  bf16 + (b ? fp16 : bf16); // expected-error {{incompatible operand types ('__fp16' and '__bf16')}}
+}
diff --git a/clang/tools/libclang/CXType.cpp b/clang/tools/libclang/CXType.cpp
--- a/clang/tools/libclang/CXType.cpp
+++ b/clang/tools/libclang/CXType.cpp
@@ -608,6 +608,7 @@
     TKIND(Elaborated);
     TKIND(Pipe);
     TKIND(Attributed);
+    TKIND(BFloat16);
 #define IMAGE_TYPE(ImgType, Id, SingletonId, Access, Suffix) TKIND(Id);
 #include "clang/Basic/OpenCLImageTypes.def"
 #undef IMAGE_TYPE