[clang][aarch64] Fix mangling of bfloat16 neon vectors

The AAPCS64 specifies the internal type is used for c++ mangling. For
bfloat16 it was defined as `BFloat16` when it should be `Bfloat16`, i.e.
lowercase 'f'.

For more information, see:

https://github.com/ARM-software/abi-aa/blob/master/aapcs64/aapcs64.rst#appendix-support-for-advanced-simd-extensions

Reviewed By: stuij

Differential Revision: https://reviews.llvm.org/D87463

(cherry picked from commit cabd60c)

Author: c-rhodes

clang/lib/AST/ItaniumMangle.cpp

@@ -3248,7 +3248,7 @@ static StringRef mangleAArch64VectorBase(const BuiltinType *EltType) {
   case BuiltinType::Double:
     return "Float64";
   case BuiltinType::BFloat16:
-    return "BFloat16";
+    return "Bfloat16";
   default:
     llvm_unreachable("Unexpected vector element base type");
   }

clang/test/CodeGenCXX/mangle-neon-vectors.cpp

@@ -1,6 +1,7 @@
 // RUN: %clang_cc1 -triple armv7-apple-ios -target-feature +neon  %s -emit-llvm -o - | FileCheck %s
 // RUN: %clang_cc1 -triple arm64-apple-ios -target-feature +neon %s -emit-llvm -o - | FileCheck %s
 // RUN: %clang_cc1 -triple arm64-linux-gnu -target-feature +neon %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK-AARCH64
+// RUN: %clang_cc1 -triple arm64-linux-gnu -target-feature +neon -target-feature +bf16 %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK-AARCH64-BF16
 
 typedef float float32_t;
 typedef double float64_t;
@@ -14,6 +15,10 @@ typedef short poly16_t;
 #endif
 typedef unsigned __INT64_TYPE__ uint64_t;
 
+#if defined(__ARM_FEATURE_BF16)
+typedef __bf16 bfloat16_t;
+#endif
+
 typedef __attribute__((neon_vector_type(2))) int int32x2_t;
 typedef __attribute__((neon_vector_type(4))) int int32x4_t;
 typedef __attribute__((neon_vector_type(1))) uint64_t uint64x1_t;
@@ -28,6 +33,10 @@ typedef __attribute__((neon_vector_type(2))) float64_t float64x2_t;
 typedef __attribute__((neon_polyvector_type(16))) poly8_t  poly8x16_t;
 typedef __attribute__((neon_polyvector_type(8)))  poly16_t poly16x8_t;
 
+#if defined(__ARM_FEATURE_BF16)
+typedef __attribute__((neon_vector_type(4))) __bf16 bfloat16x4_t;
+#endif
+
 // CHECK: 16__simd64_int32_t
 // CHECK-AARCH64: 11__Int32x2_t
 void f1(int32x2_t v) { }
@@ -72,3 +81,8 @@ void f10(poly16x8_t v) {}
 // CHECK-AARCH64: 13__Float64x2_t
 void f11(float64x2_t v) { }
 #endif
+
+#if defined(__ARM_FEATURE_BF16)
+// CHECK-AARCH64-BF16: 14__Bfloat16x4_t
+void f12(bfloat16x4_t v) {}
+#endif