diff --git a/clang/include/clang/Basic/arm_bf16.td b/clang/include/clang/Basic/arm_bf16.td
new file mode 100644
--- /dev/null
+++ b/clang/include/clang/Basic/arm_bf16.td
@@ -0,0 +1,14 @@
+//===--- arm_fp16.td - ARM FP16 compiler interface ------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+//  This file defines the TableGen definitions from which the ARM FP16 header
+//  file will be generated.
+//
+//===----------------------------------------------------------------------===//
+
+include "arm_neon_incl.td"
diff --git a/clang/include/clang/Basic/arm_neon_incl.td b/clang/include/clang/Basic/arm_neon_incl.td
--- a/clang/include/clang/Basic/arm_neon_incl.td
+++ b/clang/include/clang/Basic/arm_neon_incl.td
@@ -215,6 +215,7 @@
 // f: float
 // h: half-float
 // d: double
+// b: bfloat
 //
 // Typespec modifiers
 // ------------------
@@ -236,6 +237,7 @@
 // S: change to signed integer category.
 // U: change to unsigned integer category.
 // F: change to floating category.
+// B: change to BFloat
 // P: change to polynomial category.
 // p: change polynomial to equivalent integer category. Otherwise nop.
 //
@@ -287,6 +289,8 @@
   // this. Ex: vset_lane which outputs vmov instructions.
   bit isHiddenWInst = 0;
   bit isHiddenLInst = 0;
+
+  string CartesianProductWith = "";
 }
 
 // The following instruction classes are implemented via builtins.
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
@@ -286,6 +286,12 @@
   if (HasMatMul)
     Builder.defineMacro("__ARM_FEATURE_MATMUL_INT8", "1");
 
+  if (HasBFloat16) {
+    Builder.defineMacro("__ARM_FEATURE_BF16", "1");
+    Builder.defineMacro("__ARM_FEATURE_BF16_VECTOR_ARITHMETIC", "1");
+    Builder.defineMacro("__ARM_BF16_FORMAT_ALTERNATIVE", "1");
+  }
+
   if ((FPU & NeonMode) && HasFP16FML)
     Builder.defineMacro("__ARM_FEATURE_FP16FML", "1");
 
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
@@ -834,6 +834,12 @@
   if (HasMatMul)
     Builder.defineMacro("__ARM_FEATURE_MATMUL_INT8", "1");
 
+  if (HasBFloat16) {
+    Builder.defineMacro("__ARM_FEATURE_BF16", "1");
+    Builder.defineMacro("__ARM_FEATURE_BF16_VECTOR_ARITHMETIC", "1");
+    Builder.defineMacro("__ARM_BF16_FORMAT_ALTERNATIVE", "1");
+  }
+
   switch (ArchKind) {
   default:
     break;
diff --git a/clang/lib/Headers/CMakeLists.txt b/clang/lib/Headers/CMakeLists.txt
--- a/clang/lib/Headers/CMakeLists.txt
+++ b/clang/lib/Headers/CMakeLists.txt
@@ -189,6 +189,8 @@
 clang_generate_header(-gen-arm-fp16 arm_fp16.td arm_fp16.h)
 # Generate arm_sve.h
 clang_generate_header(-gen-arm-sve-header arm_sve.td arm_sve.h)
+# Generate arm_bf16.h
+clang_generate_header(-gen-arm-bf16 arm_bf16.td arm_bf16.h)
 # Generate arm_mve.h
 clang_generate_header(-gen-arm-mve-header arm_mve.td arm_mve.h)
 # Generate arm_cde.h
diff --git a/clang/test/Preprocessor/aarch64-target-features.c b/clang/test/Preprocessor/aarch64-target-features.c
--- a/clang/test/Preprocessor/aarch64-target-features.c
+++ b/clang/test/Preprocessor/aarch64-target-features.c
@@ -41,6 +41,12 @@
 // CHECK-NOT: __ARM_FEATURE_DOTPROD
 // CHECK-NOT: __ARM_FEATURE_PAC_DEFAULT
 // CHECK-NOT: __ARM_FEATURE_BTI_DEFAULT
+// CHECK-NOT: __ARM_BF16_FORMAT_ALTERNATIVE 1
+// CHECK-NOT: __ARM_FEATURE_BF16 1
+// CHECK-NOT: __ARM_FEATURE_BF16_VECTOR_ARITHMETIC 1
+
+// RUN: %clang -target aarch64_be-eabi -x c -E -dM %s -o - | FileCheck %s -check-prefix CHECK-BIGENDIAN
+// CHECK-BIGENDIAN: __ARM_BIG_ENDIAN 1
 
 // RUN: %clang -target aarch64-none-linux-gnu -march=armv8-a+crypto -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-CRYPTO %s
 // RUN: %clang -target arm64-none-linux-gnu -march=armv8-a+crypto -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-CRYPTO %s
@@ -368,3 +374,10 @@
 // RUN: %clang -target arm64-none-linux-gnu -march=armv8-a -mbranch-protection=pac-ret+bti -x c -E -dM %s -o - | FileCheck -check-prefix=CHECK-BTI %s
 // CHECK-BTI-OFF-NOT: __ARM_FEATURE_BTI_DEFAULT
 // CHECK-BTI:         #define __ARM_FEATURE_BTI_DEFAULT 1
+
+// ================== Check BFloat Extensions.
+// RUN: %clang -target aarch64-arm-none-eabi -march=armv8.6-a+bf16 -x c -E -dM %s -o - 2>&1 | FileCheck -check-prefix=CHECK-BFLOAT %s
+// CHECK-BFLOAT: __ARM_BF16_FORMAT_ALTERNATIVE 1
+// CHECK-BFLOAT: __ARM_FEATURE_BF16 1
+// CHECK-BFLOAT: __ARM_FEATURE_BF16_VECTOR_ARITHMETIC 1
+
diff --git a/clang/test/Preprocessor/arm-target-features.c b/clang/test/Preprocessor/arm-target-features.c
--- a/clang/test/Preprocessor/arm-target-features.c
+++ b/clang/test/Preprocessor/arm-target-features.c
@@ -7,6 +7,9 @@
 // CHECK-V8A: #define __ARM_FEATURE_NUMERIC_MAXMIN 1
 // CHECK-V8A-NOT: #define __ARM_FP 0x
 // CHECK-V8A-NOT: #define __ARM_FEATURE_DOTPROD
+// CHECK-V8A-NOT: #define __ARM_BF16_FORMAT_ALTERNATIVE
+// CHECK-V8A-NOT: #define __ARM_FEATURE_BF16
+// CHECK-V8A-NOT: #define __ARM_FEATURE_BF16_VECTOR_ARITHMETIC
 
 // RUN: %clang -target armv8a-none-linux-gnueabi -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V8A-ALLOW-FP-INSTR %s
 // RUN: %clang -target armv8a-none-linux-gnueabihf -x c -E -dM %s -o - | FileCheck -match-full-lines --check-prefix=CHECK-V8A-ALLOW-FP-INSTR %s
@@ -848,3 +851,9 @@
 
 // RUN: %clang -target arm-none-none-eabi -march=armv7-m -mfpu=softvfp -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SOFTVFP %s
 // CHECK-SOFTVFP-NOT: #define __ARM_FP 0x
+
+// ================== Check BFloat Extensions.
+// RUN: %clang -target arm-arm-none-eabi -march=armv8.6-a+bf16 -x c -E -dM %s -o - 2>&1 | FileCheck -check-prefix=CHECK-BFLOAT %s
+// CHECK-BFLOAT: #define __ARM_BF16_FORMAT_ALTERNATIVE 1
+// CHECK-BFLOAT: #define __ARM_FEATURE_BF16 1
+// CHECK-BFLOAT: #define __ARM_FEATURE_BF16_VECTOR_ARITHMETIC 1
diff --git a/clang/utils/TableGen/NeonEmitter.cpp b/clang/utils/TableGen/NeonEmitter.cpp
--- a/clang/utils/TableGen/NeonEmitter.cpp
+++ b/clang/utils/TableGen/NeonEmitter.cpp
@@ -99,7 +99,8 @@
   Poly128,
   Float16,
   Float32,
-  Float64
+  Float64,
+  BFloat16
 };
 
 } // end namespace NeonTypeFlags
@@ -147,6 +148,7 @@
     SInt,
     UInt,
     Poly,
+    BFloat16,
   };
   TypeKind Kind;
   bool Immediate, Constant, Pointer;
@@ -199,6 +201,7 @@
   bool isInt() const { return isInteger() && ElementBitwidth == 32; }
   bool isLong() const { return isInteger() && ElementBitwidth == 64; }
   bool isVoid() const { return Kind == Void; }
+  bool isBFloat16() const { return Kind == BFloat16; }
   unsigned getNumElements() const { return Bitwidth / ElementBitwidth; }
   unsigned getSizeInBits() const { return Bitwidth; }
   unsigned getElementSizeInBits() const { return ElementBitwidth; }
@@ -585,8 +588,11 @@
   // runFP16 - Emit arm_fp16.h.inc
   void runFP16(raw_ostream &o);
 
-  // runHeader - Emit all the __builtin prototypes used in arm_neon.h
-	// and arm_fp16.h
+  // runBF16 - Emit arm_bf16.h.inc
+  void runBF16(raw_ostream &o);
+
+  // runHeader - Emit all the __builtin prototypes used in arm_neon.h,
+  // arm_fp16.h and arm_bf16.h
   void runHeader(raw_ostream &o);
 
   // runTests - Emit tests for all the Neon intrinsics.
@@ -611,12 +617,15 @@
     S += "poly";
   else if (isFloating())
     S += "float";
+  else if (isBFloat16())
+    S += "bfloat";
   else
     S += "int";
 
   S += utostr(ElementBitwidth);
   if (isVector())
     S += "x" + utostr(getNumElements());
+
   if (NumVectors > 1)
     S += "x" + utostr(NumVectors);
   S += "_t";
@@ -650,7 +659,10 @@
     case 128: S += "LLLi"; break;
     default: llvm_unreachable("Unhandled case!");
     }
-  else
+  else if (isBFloat16()) {
+    assert(ElementBitwidth == 16 && "BFloat16 can only be 16 bits");
+    S += "y";
+  } else
     switch (ElementBitwidth) {
     case 16: S += "h"; break;
     case 32: S += "f"; break;
@@ -704,6 +716,11 @@
     Base = (unsigned)NeonTypeFlags::Float16 + (Addend - 1);
   }
 
+  if (isBFloat16()) {
+    assert(Addend == 1 && "BFloat16 is only 16 bit");
+    Base = (unsigned)NeonTypeFlags::BFloat16;
+  }
+
   if (Bitwidth == 128)
     Base |= (unsigned)NeonTypeFlags::QuadFlag;
   if (isInteger() && !isSigned())
@@ -727,6 +744,9 @@
   } else if (Name.startswith("poly")) {
     T.Kind = Poly;
     Name = Name.drop_front(4);
+  } else if (Name.startswith("bfloat")) {
+    T.Kind = BFloat16;
+    Name = Name.drop_front(6);
   } else {
     assert(Name.startswith("int"));
     Name = Name.drop_front(3);
@@ -825,6 +845,10 @@
       if (isPoly())
         NumVectors = 0;
       break;
+    case 'b':
+      Kind = BFloat16;
+      ElementBitwidth = 16;
+      break;
     default:
       llvm_unreachable("Unhandled type code!");
     }
@@ -851,6 +875,10 @@
     case 'U':
       Kind = UInt;
       break;
+    case 'B':
+      Kind = BFloat16;
+      ElementBitwidth = 16;
+      break;
     case 'F':
       Kind = Float;
       break;
@@ -932,6 +960,9 @@
   if (CK == ClassB)
     return "";
 
+  if (T.isBFloat16())
+    return "bf16";
+
   if (T.isPoly())
     typeCode = 'p';
   else if (T.isInteger())
@@ -969,7 +1000,7 @@
 
   Type RetT = getReturnType();
   if ((LocalCK == ClassI || LocalCK == ClassW) && RetT.isScalar() &&
-      !RetT.isFloating())
+      !RetT.isFloating() && !RetT.isBFloat16())
     RetT.makeInteger(RetT.getElementSizeInBits(), false);
 
   // Since the return value must be one type, return a vector type of the
@@ -2164,6 +2195,74 @@
   genIntrinsicRangeCheckCode(OS, Defs);
 }
 
+static void emitNeonTypeDefs(const std::string& types, raw_ostream &OS) {
+  std::string TypedefTypes(types);
+  std::vector<TypeSpec> TDTypeVec = TypeSpec::fromTypeSpecs(TypedefTypes);
+
+  // Emit vector typedefs.
+  bool InIfdef = false;
+  for (auto &TS : TDTypeVec) {
+    bool IsA64 = false;
+    Type T(TS, ".");
+    if (T.isDouble())
+      IsA64 = true;
+
+    if (InIfdef && !IsA64) {
+      OS << "#endif\n";
+      InIfdef = false;
+    }
+    if (!InIfdef && IsA64) {
+      OS << "#ifdef __aarch64__\n";
+      InIfdef = true;
+    }
+
+    if (T.isPoly())
+      OS << "typedef __attribute__((neon_polyvector_type(";
+    else
+      OS << "typedef __attribute__((neon_vector_type(";
+
+    Type T2 = T;
+    T2.makeScalar();
+    OS << T.getNumElements() << "))) ";
+    OS << T2.str();
+    OS << " " << T.str() << ";\n";
+  }
+  if (InIfdef)
+    OS << "#endif\n";
+  OS << "\n";
+
+  // Emit struct typedefs.
+  InIfdef = false;
+  for (unsigned NumMembers = 2; NumMembers <= 4; ++NumMembers) {
+    for (auto &TS : TDTypeVec) {
+      bool IsA64 = false;
+      Type T(TS, ".");
+      if (T.isDouble())
+        IsA64 = true;
+
+      if (InIfdef && !IsA64) {
+        OS << "#endif\n";
+        InIfdef = false;
+      }
+      if (!InIfdef && IsA64) {
+        OS << "#ifdef __aarch64__\n";
+        InIfdef = true;
+      }
+
+      const char Mods[] = { static_cast<char>('2' + (NumMembers - 2)), 0};
+      Type VT(TS, Mods);
+      OS << "typedef struct " << VT.str() << " {\n";
+      OS << "  " << T.str() << " val";
+      OS << "[" << NumMembers << "]";
+      OS << ";\n} ";
+      OS << VT.str() << ";\n";
+      OS << "\n";
+    }
+  }
+  if (InIfdef)
+    OS << "#endif\n";
+}
+
 /// run - Read the records in arm_neon.td and output arm_neon.h.  arm_neon.h
 /// is comprised of type definitions and function declarations.
 void NeonEmitter::run(raw_ostream &OS) {
@@ -2218,6 +2317,11 @@
 
   OS << "#include <stdint.h>\n\n";
 
+  OS << "#ifdef __ARM_FEATURE_BF16\n";
+  OS << "#include <arm_bf16.h>\n";
+  OS << "typedef __bf16 bfloat16_t;\n";
+  OS << "#endif\n\n";
+
   // Emit NEON-specific scalar typedefs.
   OS << "typedef float float32_t;\n";
   OS << "typedef __fp16 float16_t;\n";
@@ -2238,74 +2342,118 @@
   OS << "typedef int64_t poly64_t;\n";
   OS << "#endif\n";
 
-  // Emit Neon vector typedefs.
-  std::string TypedefTypes(
-      "cQcsQsiQilQlUcQUcUsQUsUiQUiUlQUlhQhfQfdQdPcQPcPsQPsPlQPl");
-  std::vector<TypeSpec> TDTypeVec = TypeSpec::fromTypeSpecs(TypedefTypes);
+  emitNeonTypeDefs("cQcsQsiQilQlUcQUcUsQUsUiQUiUlQUlhQhfQfdQdPcQPcPsQPsPlQPl", OS);
 
-  // Emit vector typedefs.
-  bool InIfdef = false;
-  for (auto &TS : TDTypeVec) {
-    bool IsA64 = false;
-    Type T(TS, ".");
-    if (T.isDouble())
-      IsA64 = true;
+  OS << "#ifdef __ARM_FEATURE_BF16\n";
+  emitNeonTypeDefs("bQb", OS);
+  OS << "#endif\n\n";
 
-    if (InIfdef && !IsA64) {
-      OS << "#endif\n";
-      InIfdef = false;
-    }
-    if (!InIfdef && IsA64) {
-      OS << "#ifdef __aarch64__\n";
-      InIfdef = true;
-    }
+  OS << "#define __ai static __inline__ __attribute__((__always_inline__, "
+        "__nodebug__))\n\n";
 
-    if (T.isPoly())
-      OS << "typedef __attribute__((neon_polyvector_type(";
-    else
-      OS << "typedef __attribute__((neon_vector_type(";
+  SmallVector<Intrinsic *, 128> Defs;
+  std::vector<Record *> RV = Records.getAllDerivedDefinitions("Inst");
+  for (auto *R : RV)
+    createIntrinsic(R, Defs);
 
-    Type T2 = T;
-    T2.makeScalar();
-    OS << T.getNumElements() << "))) ";
-    OS << T2.str();
-    OS << " " << T.str() << ";\n";
-  }
-  if (InIfdef)
-    OS << "#endif\n";
-  OS << "\n";
+  for (auto *I : Defs)
+    I->indexBody();
 
-  // Emit struct typedefs.
-  InIfdef = false;
-  for (unsigned NumMembers = 2; NumMembers <= 4; ++NumMembers) {
-    for (auto &TS : TDTypeVec) {
-      bool IsA64 = false;
-      Type T(TS, ".");
-      if (T.isDouble())
-        IsA64 = true;
+  llvm::stable_sort(Defs, llvm::deref<std::less<>>());
 
-      if (InIfdef && !IsA64) {
-        OS << "#endif\n";
-        InIfdef = false;
+  // Only emit a def when its requirements have been met.
+  // FIXME: This loop could be made faster, but it's fast enough for now.
+  bool MadeProgress = true;
+  std::string InGuard;
+  while (!Defs.empty() && MadeProgress) {
+    MadeProgress = false;
+
+    for (SmallVector<Intrinsic *, 128>::iterator I = Defs.begin();
+         I != Defs.end(); /*No step*/) {
+      bool DependenciesSatisfied = true;
+      for (auto *II : (*I)->getDependencies()) {
+        if (llvm::is_contained(Defs, II))
+          DependenciesSatisfied = false;
       }
-      if (!InIfdef && IsA64) {
-        OS << "#ifdef __aarch64__\n";
-        InIfdef = true;
+      if (!DependenciesSatisfied) {
+        // Try the next one.
+        ++I;
+        continue;
       }
 
-      const char Mods[] = { static_cast<char>('2' + (NumMembers - 2)), 0};
-      Type VT(TS, Mods);
-      OS << "typedef struct " << VT.str() << " {\n";
-      OS << "  " << T.str() << " val";
-      OS << "[" << NumMembers << "]";
-      OS << ";\n} ";
-      OS << VT.str() << ";\n";
-      OS << "\n";
+      // Emit #endif/#if pair if needed.
+      if ((*I)->getGuard() != InGuard) {
+        if (!InGuard.empty())
+          OS << "#endif\n";
+        InGuard = (*I)->getGuard();
+        if (!InGuard.empty())
+          OS << "#if " << InGuard << "\n";
+      }
+
+      // Actually generate the intrinsic code.
+      OS << (*I)->generate();
+
+      MadeProgress = true;
+      I = Defs.erase(I);
     }
   }
-  if (InIfdef)
+  assert(Defs.empty() && "Some requirements were not satisfied!");
+  if (!InGuard.empty())
     OS << "#endif\n";
+
   OS << "\n";
+  OS << "#undef __ai\n\n";
+  OS << "#endif /* __ARM_NEON_H */\n";
+}
+
+/// run - Read the records in arm_fp16.td and output arm_fp16.h.  arm_fp16.h
+/// is comprised of type definitions and function declarations.
+void NeonEmitter::runFP16(raw_ostream &OS) {
+  OS << "/*===---- arm_fp16.h - ARM FP16 intrinsics "
+        "------------------------------"
+        "---===\n"
+        " *\n"
+        " * Permission is hereby granted, free of charge, to any person "
+        "obtaining a copy\n"
+        " * of this software and associated documentation files (the "
+				"\"Software\"), to deal\n"
+        " * in the Software without restriction, including without limitation "
+				"the rights\n"
+        " * to use, copy, modify, merge, publish, distribute, sublicense, "
+				"and/or sell\n"
+        " * copies of the Software, and to permit persons to whom the Software "
+				"is\n"
+        " * furnished to do so, subject to the following conditions:\n"
+        " *\n"
+        " * The above copyright notice and this permission notice shall be "
+        "included in\n"
+        " * all copies or substantial portions of the Software.\n"
+        " *\n"
+        " * THE SOFTWARE IS PROVIDED \"AS IS\", WITHOUT WARRANTY OF ANY KIND, "
+        "EXPRESS OR\n"
+        " * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF "
+        "MERCHANTABILITY,\n"
+        " * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT "
+        "SHALL THE\n"
+        " * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR "
+        "OTHER\n"
+        " * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, "
+        "ARISING FROM,\n"
+        " * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER "
+        "DEALINGS IN\n"
+        " * THE SOFTWARE.\n"
+        " *\n"
+        " *===-----------------------------------------------------------------"
+        "---"
+        "---===\n"
+        " */\n\n";
+
+  OS << "#ifndef __ARM_FP16_H\n";
+  OS << "#define __ARM_FP16_H\n\n";
+
+  OS << "#include <stdint.h>\n\n";
+
+  OS << "typedef __fp16 float16_t;\n";
 
   OS << "#define __ai static __inline__ __attribute__((__always_inline__, "
         "__nodebug__))\n\n";
@@ -2362,13 +2510,11 @@
 
   OS << "\n";
   OS << "#undef __ai\n\n";
-  OS << "#endif /* __ARM_NEON_H */\n";
+  OS << "#endif /* __ARM_FP16_H */\n";
 }
 
-/// run - Read the records in arm_fp16.td and output arm_fp16.h.  arm_fp16.h
-/// is comprised of type definitions and function declarations.
-void NeonEmitter::runFP16(raw_ostream &OS) {
-  OS << "/*===---- arm_fp16.h - ARM FP16 intrinsics "
+void NeonEmitter::runBF16(raw_ostream &OS) {
+  OS << "/*===---- arm_bf16.h - ARM BF16 intrinsics "
         "------------------------------"
         "---===\n"
         " *\n"
@@ -2407,12 +2553,10 @@
         "---===\n"
         " */\n\n";
 
-  OS << "#ifndef __ARM_FP16_H\n";
-  OS << "#define __ARM_FP16_H\n\n";
+  OS << "#ifndef __ARM_BF16_H\n";
+  OS << "#define __ARM_BF16_H\n\n";
 
-  OS << "#include <stdint.h>\n\n";
-
-  OS << "typedef __fp16 float16_t;\n";
+  OS << "typedef __bf16 bfloat16_t;\n";
 
   OS << "#define __ai static __inline__ __attribute__((__always_inline__, "
         "__nodebug__))\n\n";
@@ -2469,7 +2613,8 @@
 
   OS << "\n";
   OS << "#undef __ai\n\n";
-  OS << "#endif /* __ARM_FP16_H */\n";
+
+  OS << "#endif";
 }
 
 void clang::EmitNeon(RecordKeeper &Records, raw_ostream &OS) {
@@ -2480,6 +2625,10 @@
   NeonEmitter(Records).runFP16(OS);
 }
 
+void clang::EmitBF16(RecordKeeper &Records, raw_ostream &OS) {
+  NeonEmitter(Records).runBF16(OS);
+}
+
 void clang::EmitNeonSema(RecordKeeper &Records, raw_ostream &OS) {
   NeonEmitter(Records).runHeader(OS);
 }
diff --git a/clang/utils/TableGen/TableGen.cpp b/clang/utils/TableGen/TableGen.cpp
--- a/clang/utils/TableGen/TableGen.cpp
+++ b/clang/utils/TableGen/TableGen.cpp
@@ -63,6 +63,7 @@
   GenClangOpenCLBuiltins,
   GenArmNeon,
   GenArmFP16,
+  GenArmBF16,
   GenArmNeonSema,
   GenArmNeonTest,
   GenArmMveHeader,
@@ -186,6 +187,7 @@
                    "Generate OpenCL builtin declaration handlers"),
         clEnumValN(GenArmNeon, "gen-arm-neon", "Generate arm_neon.h for clang"),
         clEnumValN(GenArmFP16, "gen-arm-fp16", "Generate arm_fp16.h for clang"),
+        clEnumValN(GenArmBF16, "gen-arm-bf16", "Generate arm_bf16.h for clang"),
         clEnumValN(GenArmNeonSema, "gen-arm-neon-sema",
                    "Generate ARM NEON sema support for clang"),
         clEnumValN(GenArmNeonTest, "gen-arm-neon-test",
@@ -360,6 +362,9 @@
   case GenArmFP16:
     EmitFP16(Records, OS);
     break;
+  case GenArmBF16:
+    EmitBF16(Records, OS);
+    break;
   case GenArmNeonSema:
     EmitNeonSema(Records, OS);
     break;
diff --git a/clang/utils/TableGen/TableGenBackends.h b/clang/utils/TableGen/TableGenBackends.h
--- a/clang/utils/TableGen/TableGenBackends.h
+++ b/clang/utils/TableGen/TableGenBackends.h
@@ -85,6 +85,7 @@
 
 void EmitNeon(llvm::RecordKeeper &Records, llvm::raw_ostream &OS);
 void EmitFP16(llvm::RecordKeeper &Records, llvm::raw_ostream &OS);
+void EmitBF16(llvm::RecordKeeper &Records, llvm::raw_ostream &OS);
 void EmitNeonSema(llvm::RecordKeeper &Records, llvm::raw_ostream &OS);
 void EmitNeonTest(llvm::RecordKeeper &Records, llvm::raw_ostream &OS);
 void EmitNeon2(llvm::RecordKeeper &Records, llvm::raw_ostream &OS);