diff --git a/clang/lib/AST/StmtOpenACC.cpp b/clang/lib/AST/StmtOpenACC.cpp
@@ -28,44 +28,15 @@ OpenACCComputeConstruct::CreateEmpty(const ASTContext &C, unsigned NumClauses) {
 OpenACCComputeConstruct *OpenACCComputeConstruct::Create(
     const ASTContext &C, OpenACCDirectiveKind K, SourceLocation BeginLoc,
     SourceLocation DirLoc, SourceLocation EndLoc,
-    ArrayRef<const OpenACCClause *> Clauses, Stmt *StructuredBlock,
-    ArrayRef<OpenACCLoopConstruct *> AssociatedLoopConstructs) {
+    ArrayRef<const OpenACCClause *> Clauses, Stmt *StructuredBlock) {
   void *Mem = C.Allocate(
       OpenACCComputeConstruct::totalSizeToAlloc<const OpenACCClause *>(
           Clauses.size()));
   auto *Inst = new (Mem) OpenACCComputeConstruct(K, BeginLoc, DirLoc, EndLoc,
                                                  Clauses, StructuredBlock);
-
-  llvm::for_each(AssociatedLoopConstructs, [&](OpenACCLoopConstruct *C) {
-    C->setParentComputeConstruct(Inst);
-  });
-
   return Inst;
 }
 
-void OpenACCComputeConstruct::findAndSetChildLoops() {
-  struct LoopConstructFinder : RecursiveASTVisitor<LoopConstructFinder> {
-    OpenACCComputeConstruct *Construct = nullptr;
-
-    LoopConstructFinder(OpenACCComputeConstruct *Construct)
-        : Construct(Construct) {}
-
-    bool TraverseOpenACCComputeConstruct(OpenACCComputeConstruct *C) {
-      // Stop searching if we find a compute construct.
-      return true;
-    }
-    bool TraverseOpenACCLoopConstruct(OpenACCLoopConstruct *C) {
-      // Stop searching if we find a loop construct, after taking ownership of
-      // it.
-      C->setParentComputeConstruct(Construct);
-      return true;
-    }
-  };
-
-  LoopConstructFinder f(this);
-  f.TraverseStmt(getAssociatedStmt());
-}
-
 OpenACCLoopConstruct::OpenACCLoopConstruct(unsigned NumClauses)
     : OpenACCAssociatedStmtConstruct(
           OpenACCLoopConstructClass, OpenACCDirectiveKind::Loop,
@@ -79,11 +50,13 @@ OpenACCLoopConstruct::OpenACCLoopConstruct(unsigned NumClauses)
 }
 
 OpenACCLoopConstruct::OpenACCLoopConstruct(
-    SourceLocation Start, SourceLocation DirLoc, SourceLocation End,
+    OpenACCDirectiveKind ParentKind, SourceLocation Start,
+    SourceLocation DirLoc, SourceLocation End,
     ArrayRef<const OpenACCClause *> Clauses, Stmt *Loop)
     : OpenACCAssociatedStmtConstruct(OpenACCLoopConstructClass,
                                      OpenACCDirectiveKind::Loop, Start, DirLoc,
-                                     End, Loop) {
+                                     End, Loop),
+      ParentComputeConstructKind(ParentKind) {
   // accept 'nullptr' for the loop. This is diagnosed somewhere, but this gives
   // us some level of AST fidelity in the error case.
   assert((Loop == nullptr || isa<ForStmt, CXXForRangeStmt>(Loop)) &&
@@ -96,12 +69,6 @@ OpenACCLoopConstruct::OpenACCLoopConstruct(
                                 Clauses.size()));
 }
 
-void OpenACCLoopConstruct::setLoop(Stmt *Loop) {
-  assert((isa<ForStmt, CXXForRangeStmt>(Loop)) &&
-         "Associated Loop not a for loop?");
-  setAssociatedStmt(Loop);
-}
-
 OpenACCLoopConstruct *OpenACCLoopConstruct::CreateEmpty(const ASTContext &C,
                                                         unsigned NumClauses) {
   void *Mem =
@@ -111,15 +78,14 @@ OpenACCLoopConstruct *OpenACCLoopConstruct::CreateEmpty(const ASTContext &C,
   return Inst;
 }
 
-OpenACCLoopConstruct *
-OpenACCLoopConstruct::Create(const ASTContext &C, SourceLocation BeginLoc,
-                             SourceLocation DirLoc, SourceLocation EndLoc,
-                             ArrayRef<const OpenACCClause *> Clauses,
-                             Stmt *Loop) {
+OpenACCLoopConstruct *OpenACCLoopConstruct::Create(
+    const ASTContext &C, OpenACCDirectiveKind ParentKind,
+    SourceLocation BeginLoc, SourceLocation DirLoc, SourceLocation EndLoc,
+    ArrayRef<const OpenACCClause *> Clauses, Stmt *Loop) {
   void *Mem =
       C.Allocate(OpenACCLoopConstruct::totalSizeToAlloc<const OpenACCClause *>(
           Clauses.size()));
-  auto *Inst =
-      new (Mem) OpenACCLoopConstruct(BeginLoc, DirLoc, EndLoc, Clauses, Loop);
+  auto *Inst = new (Mem)
+      OpenACCLoopConstruct(ParentKind, BeginLoc, DirLoc, EndLoc, Clauses, Loop);
   return Inst;
 }
diff --git a/clang/lib/AST/TextNodeDumper.cpp b/clang/lib/AST/TextNodeDumper.cpp
@@ -2928,7 +2928,7 @@ void TextNodeDumper::VisitOpenACCLoopConstruct(const OpenACCLoopConstruct *S) {
   if (S->isOrphanedLoopConstruct())
     OS << " <orphan>";
   else
-    OS << " parent: " << S->getParentComputeConstruct();
+    OS << " parent: " << S->getParentComputeConstructKind();
 }
 
 void TextNodeDumper::VisitEmbedExpr(const EmbedExpr *S) {

diff --git a/clang/lib/Basic/Attributes.cpp b/clang/lib/Basic/Attributes.cpp
@@ -18,6 +18,7 @@
 #include "clang/Basic/TargetInfo.h"
 
 #include "llvm/ADT/StringMap.h"
+#include "llvm/ADT/StringSwitch.h"
 
 using namespace clang;
 
@@ -155,26 +156,17 @@ std::string AttributeCommonInfo::getNormalizedFullName() const {
       normalizeName(getAttrName(), getScopeName(), getSyntax()));
 }
 
-// Sorted list of attribute scope names
-static constexpr std::pair<StringRef, AttributeCommonInfo::Scope> ScopeList[] =
-    {{"", AttributeCommonInfo::Scope::NONE},
-     {"clang", AttributeCommonInfo::Scope::CLANG},
-     {"gnu", AttributeCommonInfo::Scope::GNU},
-     {"gsl", AttributeCommonInfo::Scope::GSL},
-     {"hlsl", AttributeCommonInfo::Scope::HLSL},
-     {"msvc", AttributeCommonInfo::Scope::MSVC},
-     {"omp", AttributeCommonInfo::Scope::OMP},
-     {"riscv", AttributeCommonInfo::Scope::RISCV}};
-
 AttributeCommonInfo::Scope
 getScopeFromNormalizedScopeName(StringRef ScopeName) {
-  auto It = std::lower_bound(
-      std::begin(ScopeList), std::end(ScopeList), ScopeName,
-      [](const std::pair<StringRef, AttributeCommonInfo::Scope> &Element,
-         StringRef Value) { return Element.first < Value; });
-  assert(It != std::end(ScopeList) && It->first == ScopeName);
-
-  return It->second;
+  return llvm::StringSwitch<AttributeCommonInfo::Scope>(ScopeName)
+      .Case("", AttributeCommonInfo::Scope::NONE)
+      .Case("clang", AttributeCommonInfo::Scope::CLANG)
+      .Case("gnu", AttributeCommonInfo::Scope::GNU)
+      .Case("gsl", AttributeCommonInfo::Scope::GSL)
+      .Case("hlsl", AttributeCommonInfo::Scope::HLSL)
+      .Case("msvc", AttributeCommonInfo::Scope::MSVC)
+      .Case("omp", AttributeCommonInfo::Scope::OMP)
+      .Case("riscv", AttributeCommonInfo::Scope::RISCV);
 }
 
 unsigned AttributeCommonInfo::calculateAttributeSpellingListIndex() const {

diff --git a/clang/lib/Basic/Targets/AArch64.cpp b/clang/lib/Basic/Targets/AArch64.cpp
@@ -473,7 +473,7 @@ void AArch64TargetInfo::getTargetDefines(const LangOptions &Opts,
   if (HasSVE2p1)
     Builder.defineMacro("__ARM_FEATURE_SVE2p1", "1");
 
-  if (HasSVE2 && HasSVEAES)
+  if (HasSVE2 && HasSVE2AES)
     Builder.defineMacro("__ARM_FEATURE_SVE2_AES", "1");
 
   if (HasSVE2 && HasSVE2BitPerm)
@@ -769,7 +769,7 @@ bool AArch64TargetInfo::hasFeature(StringRef Feature) const {
       .Case("f32mm", FPU & SveMode && HasMatmulFP32)
       .Case("f64mm", FPU & SveMode && HasMatmulFP64)
       .Case("sve2", FPU & SveMode && HasSVE2)
-      .Case("sve2-pmull128", FPU & SveMode && HasSVEAES && HasSVE2)
+      .Case("sve2-pmull128", FPU & SveMode && HasSVE2AES)
       .Case("sve2-bitperm", FPU & SveMode && HasSVE2BitPerm)
       .Case("sve2-sha3", FPU & SveMode && HasSVE2SHA3)
       .Case("sve2-sm4", FPU & SveMode && HasSVE2SM4)
@@ -861,10 +861,12 @@ bool AArch64TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
       HasSVE2 = true;
       HasSVE2p1 = true;
     }
-    if (Feature == "+sve-aes") {
+    if (Feature == "+sve2-aes") {
       FPU |= NeonMode;
-      HasAES = true;
-      HasSVEAES = true;
+      FPU |= SveMode;
+      HasFullFP16 = true;
+      HasSVE2 = true;
+      HasSVE2AES = true;
     }
     if (Feature == "+sve2-sha3") {
       FPU |= NeonMode;

diff --git a/clang/lib/Basic/Targets/AArch64.h b/clang/lib/Basic/Targets/AArch64.h
@@ -78,7 +78,7 @@ class LLVM_LIBRARY_VISIBILITY AArch64TargetInfo : public TargetInfo {
   bool HasBFloat16 = false;
   bool HasSVE2 = false;
   bool HasSVE2p1 = false;
-  bool HasSVEAES = false;
+  bool HasSVE2AES = false;
   bool HasSVE2SHA3 = false;
   bool HasSVE2SM4 = false;
   bool HasSVEB16B16 = false;

diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -337,12 +337,9 @@ void AMDGPUTargetInfo::getTargetDefines(const LangOptions &Opts,
   if (hasFastFMA())
     Builder.defineMacro("FP_FAST_FMA");
 
-  Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE__", Twine(WavefrontSize),
-                      "compile-time-constant access to the wavefront size will "
-                      "be removed in a future release");
-  Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE", Twine(WavefrontSize),
-                      "compile-time-constant access to the wavefront size will "
-                      "be removed in a future release");
+  Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE__", Twine(WavefrontSize));
+  // ToDo: deprecate this macro for naming consistency.
+  Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE", Twine(WavefrontSize));
   Builder.defineMacro("__AMDGCN_CUMODE__", Twine(CUMode));
 }
 

diff --git a/clang/lib/CIR/CodeGen/CIRGenModule.cpp b/clang/lib/CIR/CodeGen/CIRGenModule.cpp
@@ -22,7 +22,9 @@
 #include "mlir/IR/Location.h"
 #include "mlir/IR/MLIRContext.h"
 
-using namespace cir;
+using namespace clang;
+using namespace clang::CIRGen;
+
 CIRGenModule::CIRGenModule(mlir::MLIRContext &context,
                            clang::ASTContext &astctx,
                            const clang::CodeGenOptions &cgo,
@@ -75,7 +77,7 @@ void CIRGenModule::buildGlobal(clang::GlobalDecl gd) {
 void CIRGenModule::buildGlobalFunctionDefinition(clang::GlobalDecl gd,
                                                  mlir::Operation *op) {
   auto const *funcDecl = cast<FunctionDecl>(gd.getDecl());
-  auto funcOp = builder.create<mlir::cir::FuncOp>(
+  auto funcOp = builder.create<cir::FuncOp>(
       getLoc(funcDecl->getSourceRange()), funcDecl->getIdentifier()->getName());
   theModule.push_back(funcOp);
 }

diff --git a/clang/lib/CIR/CodeGen/CIRGenModule.h b/clang/lib/CIR/CodeGen/CIRGenModule.h
@@ -31,10 +31,8 @@ class LangOptions;
 class SourceLocation;
 class SourceRange;
 class TargetInfo;
-} // namespace clang
 
-using namespace clang;
-namespace cir {
+namespace CIRGen {
 
 /// This class organizes the cross-function state that is used while generating
 /// CIR code.
@@ -91,6 +89,8 @@ class CIRGenModule : public CIRGenTypeCache {
   DiagnosticBuilder errorNYI(SourceRange, llvm::StringRef);
   DiagnosticBuilder errorNYI(SourceRange, llvm::StringRef, llvm::StringRef);
 };
-} // namespace cir
+} // namespace CIRGen
+
+} // namespace clang
 
 #endif // LLVM_CLANG_LIB_CIR_CODEGEN_CIRGENMODULE_H
diff --git a/clang/lib/CIR/CodeGen/CIRGenTypeCache.h b/clang/lib/CIR/CodeGen/CIRGenTypeCache.h
@@ -13,7 +13,7 @@
 #ifndef LLVM_CLANG_LIB_CIR_CIRGENTYPECACHE_H
 #define LLVM_CLANG_LIB_CIR_CIRGENTYPECACHE_H
 
-namespace cir {
+namespace clang::CIRGen {
 
 /// This structure provides a set of types that are commonly used
 /// during IR emission. It's initialized once in CodeGenModule's
@@ -22,6 +22,6 @@ struct CIRGenTypeCache {
   CIRGenTypeCache() = default;
 };
 
-} // namespace cir
+} // namespace clang::CIRGen
 
 #endif // LLVM_CLANG_LIB_CIR_CODEGEN_CIRGENTYPECACHE_H
diff --git a/clang/lib/CIR/CodeGen/CIRGenerator.cpp b/clang/lib/CIR/CodeGen/CIRGenerator.cpp
@@ -35,9 +35,9 @@ void CIRGenerator::Initialize(ASTContext &astCtx) {
   this->astCtx = &astCtx;
 
   mlirCtx = std::make_unique<mlir::MLIRContext>();
-  mlirCtx->loadDialect<mlir::cir::CIRDialect>();
-  cgm = std::make_unique<CIRGenModule>(*mlirCtx.get(), astCtx, codeGenOpts,
-                                       diags);
+  mlirCtx->loadDialect<cir::CIRDialect>();
+  cgm = std::make_unique<clang::CIRGen::CIRGenModule>(*mlirCtx.get(), astCtx,
+                                                      codeGenOpts, diags);
 }
 
 mlir::ModuleOp CIRGenerator::getModule() const { return cgm->getModule(); }

diff --git a/clang/lib/CIR/Dialect/IR/CIRAttrs.cpp b/clang/lib/CIR/Dialect/IR/CIRAttrs.cpp
@@ -13,7 +13,7 @@
 #include "clang/CIR/Dialect/IR/CIRDialect.h"
 
 using namespace mlir;
-using namespace mlir::cir;
+using namespace cir;
 
 //===----------------------------------------------------------------------===//
 // General CIR parsing / printing

diff --git a/clang/lib/CIR/Dialect/IR/CIRDialect.cpp b/clang/lib/CIR/Dialect/IR/CIRDialect.cpp
@@ -17,13 +17,13 @@
 #include "clang/CIR/Dialect/IR/CIROpsDialect.cpp.inc"
 
 using namespace mlir;
-using namespace mlir::cir;
+using namespace cir;
 
 //===----------------------------------------------------------------------===//
 // CIR Dialect
 //===----------------------------------------------------------------------===//
 
-void mlir::cir::CIRDialect::initialize() {
+void cir::CIRDialect::initialize() {
   registerTypes();
   registerAttributes();
   addOperations<
@@ -36,8 +36,8 @@ void mlir::cir::CIRDialect::initialize() {
 // FuncOp
 //===----------------------------------------------------------------------===//
 
-void mlir::cir::FuncOp::build(OpBuilder &builder, OperationState &result,
-                              StringRef name) {
+void cir::FuncOp::build(OpBuilder &builder, OperationState &result,
+                        StringRef name) {
   result.addAttribute(SymbolTable::getSymbolAttrName(),
                       builder.getStringAttr(name));
 }
@@ -56,7 +56,7 @@ void cir::FuncOp::print(OpAsmPrinter &p) {
   p.printSymbolName(getSymName());
 }
 
-mlir::LogicalResult mlir::cir::FuncOp::verify() { return success(); }
+mlir::LogicalResult cir::FuncOp::verify() { return success(); }
 
 //===----------------------------------------------------------------------===//
 // TableGen'd op method definitions

diff --git a/clang/lib/CIR/Dialect/IR/CIRTypes.cpp b/clang/lib/CIR/Dialect/IR/CIRTypes.cpp
@@ -13,7 +13,7 @@
 #include "clang/CIR/Dialect/IR/CIRDialect.h"
 
 using namespace mlir;
-using namespace mlir::cir;
+using namespace cir;
 
 //===----------------------------------------------------------------------===//
 // General CIR parsing / printing

diff --git a/clang/lib/FrontendTool/ExecuteCompilerInvocation.cpp b/clang/lib/FrontendTool/ExecuteCompilerInvocation.cpp
@@ -67,7 +67,7 @@ CreateFrontendBaseAction(CompilerInstance &CI) {
   case EmitBC:                 return std::make_unique<EmitBCAction>();
   case EmitCIR:
 #if CLANG_ENABLE_CIR
-    return std::make_unique<::cir::EmitCIRAction>();
+    return std::make_unique<cir::EmitCIRAction>();
 #else
     llvm_unreachable("CIR suppport not built into clang");
 #endif

diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
@@ -4626,7 +4626,8 @@ _mm_movepi64_pi64(__m128i __a) {
 ///    A 64-bit value.
 /// \returns A 128-bit integer vector. The lower 64 bits contain the value from
 ///    the operand. The upper 64 bits are assigned zeros.
-static __inline__ __m128i __DEFAULT_FN_ATTRS _mm_movpi64_epi64(__m64 __a) {
+static __inline__ __m128i __DEFAULT_FN_ATTRS_CONSTEXPR
+_mm_movpi64_epi64(__m64 __a) {
   return __builtin_shufflevector((__v1di)__a, _mm_setzero_si64(), 0, 1);
 }
 

diff --git a/clang/lib/Headers/mmintrin.h b/clang/lib/Headers/mmintrin.h
@@ -49,6 +49,12 @@ typedef char __v16qi __attribute__((__vector_size__(16)));
                  __min_vector_width__(128)))
 #endif
 
+#if defined(__cplusplus) && (__cplusplus >= 201103L)
+#define __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR __DEFAULT_FN_ATTRS_SSE2 constexpr
+#else
+#define __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR __DEFAULT_FN_ATTRS_SSE2
+#endif
+
 #define __trunc64(x)                                                           \
   (__m64) __builtin_shufflevector((__v2di)(x), __extension__(__v2di){}, 0)
 #define __anyext128(x)                                                         \
@@ -1332,10 +1338,9 @@ _mm_cmpgt_pi32(__m64 __m1, __m64 __m2)
 /// This intrinsic corresponds to the <c> PXOR </c> instruction.
 ///
 /// \returns An initialized 64-bit integer vector with all elements set to zero.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_setzero_si64(void)
-{
-    return __extension__ (__m64){ 0LL };
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_setzero_si64(void) {
+  return __extension__(__m64){0LL};
 }
 
 /// Constructs a 64-bit integer vector initialized with the specified
@@ -1353,10 +1358,9 @@ _mm_setzero_si64(void)
 ///    A 32-bit integer value used to initialize the lower 32 bits of the
 ///    result.
 /// \returns An initialized 64-bit integer vector.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_set_pi32(int __i1, int __i0)
-{
-    return __extension__ (__m64)(__v2si){__i0, __i1};
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_set_pi32(int __i1, int __i0) {
+  return __extension__(__m64)(__v2si){__i0, __i1};
 }
 
 /// Constructs a 64-bit integer vector initialized with the specified
@@ -1376,10 +1380,9 @@ _mm_set_pi32(int __i1, int __i0)
 /// \param __s0
 ///    A 16-bit integer value used to initialize bits [15:0] of the result.
 /// \returns An initialized 64-bit integer vector.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_set_pi16(short __s3, short __s2, short __s1, short __s0)
-{
-    return __extension__ (__m64)(__v4hi){__s0, __s1, __s2, __s3};
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_set_pi16(short __s3, short __s2, short __s1, short __s0) {
+  return __extension__(__m64)(__v4hi){__s0, __s1, __s2, __s3};
 }
 
 /// Constructs a 64-bit integer vector initialized with the specified
@@ -1407,12 +1410,11 @@ _mm_set_pi16(short __s3, short __s2, short __s1, short __s0)
 /// \param __b0
 ///    An 8-bit integer value used to initialize bits [7:0] of the result.
 /// \returns An initialized 64-bit integer vector.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_set_pi8(char __b7, char __b6, char __b5, char __b4, char __b3, char __b2,
-            char __b1, char __b0)
-{
-    return __extension__ (__m64)(__v8qi){__b0, __b1, __b2, __b3,
-                                         __b4, __b5, __b6, __b7};
+            char __b1, char __b0) {
+  return __extension__(__m64)(__v8qi){__b0, __b1, __b2, __b3,
+                                      __b4, __b5, __b6, __b7};
 }
 
 /// Constructs a 64-bit integer vector of [2 x i32], with each of the
@@ -1428,10 +1430,9 @@ _mm_set_pi8(char __b7, char __b6, char __b5, char __b4, char __b3, char __b2,
 ///    A 32-bit integer value used to initialize each vector element of the
 ///    result.
 /// \returns An initialized 64-bit integer vector of [2 x i32].
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_set1_pi32(int __i)
-{
-    return _mm_set_pi32(__i, __i);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_set1_pi32(int __i) {
+  return _mm_set_pi32(__i, __i);
 }
 
 /// Constructs a 64-bit integer vector of [4 x i16], with each of the
@@ -1447,10 +1448,9 @@ _mm_set1_pi32(int __i)
 ///    A 16-bit integer value used to initialize each vector element of the
 ///    result.
 /// \returns An initialized 64-bit integer vector of [4 x i16].
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_set1_pi16(short __w)
-{
-    return _mm_set_pi16(__w, __w, __w, __w);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_set1_pi16(short __w) {
+  return _mm_set_pi16(__w, __w, __w, __w);
 }
 
 /// Constructs a 64-bit integer vector of [8 x i8], with each of the
@@ -1465,10 +1465,9 @@ _mm_set1_pi16(short __w)
 ///    An 8-bit integer value used to initialize each vector element of the
 ///    result.
 /// \returns An initialized 64-bit integer vector of [8 x i8].
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_set1_pi8(char __b)
-{
-    return _mm_set_pi8(__b, __b, __b, __b, __b, __b, __b, __b);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_set1_pi8(char __b) {
+  return _mm_set_pi8(__b, __b, __b, __b, __b, __b, __b, __b);
 }
 
 /// Constructs a 64-bit integer vector, initialized in reverse order with
@@ -1486,10 +1485,9 @@ _mm_set1_pi8(char __b)
 ///    A 32-bit integer value used to initialize the upper 32 bits of the
 ///    result.
 /// \returns An initialized 64-bit integer vector.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_setr_pi32(int __i0, int __i1)
-{
-    return _mm_set_pi32(__i1, __i0);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_setr_pi32(int __i0, int __i1) {
+  return _mm_set_pi32(__i1, __i0);
 }
 
 /// Constructs a 64-bit integer vector, initialized in reverse order with
@@ -1509,10 +1507,9 @@ _mm_setr_pi32(int __i0, int __i1)
 /// \param __w3
 ///    A 16-bit integer value used to initialize bits [63:48] of the result.
 /// \returns An initialized 64-bit integer vector.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
-_mm_setr_pi16(short __w0, short __w1, short __w2, short __w3)
-{
-    return _mm_set_pi16(__w3, __w2, __w1, __w0);
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
+_mm_setr_pi16(short __w0, short __w1, short __w2, short __w3) {
+  return _mm_set_pi16(__w3, __w2, __w1, __w0);
 }
 
 /// Constructs a 64-bit integer vector, initialized in reverse order with
@@ -1540,11 +1537,10 @@ _mm_setr_pi16(short __w0, short __w1, short __w2, short __w3)
 /// \param __b7
 ///    An 8-bit integer value used to initialize bits [63:56] of the result.
 /// \returns An initialized 64-bit integer vector.
-static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2
+static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2_CONSTEXPR
 _mm_setr_pi8(char __b0, char __b1, char __b2, char __b3, char __b4, char __b5,
-             char __b6, char __b7)
-{
-    return _mm_set_pi8(__b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0);
+             char __b6, char __b7) {
+  return _mm_set_pi8(__b7, __b6, __b5, __b4, __b3, __b2, __b1, __b0);
 }
 
 #undef __anyext128

diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
@@ -19365,11 +19365,12 @@ void Sema::ActOnFields(Scope *S, SourceLocation RecLoc, Decl *EnclosingDecl,
       }
 
       // Structs without named members are extension in C (C99 6.7.2.1p7),
-      // but are accepted by GCC.
-      if (NonBitFields == 0 && !getLangOpts().CPlusPlus) {
-        Diag(RecLoc, IsEmpty ? diag::ext_empty_struct_union :
-                               diag::ext_no_named_members_in_struct_union)
-          << Record->isUnion();
+      // but are accepted by GCC. In C2y, this became implementation-defined
+      // (C2y 6.7.3.2p10).
+      if (NonBitFields == 0 && !getLangOpts().CPlusPlus && !getLangOpts().C2y) {
+        Diag(RecLoc, IsEmpty ? diag::ext_empty_struct_union
+                             : diag::ext_no_named_members_in_struct_union)
+            << Record->isUnion();
       }
     }
   } else {

diff --git a/clang/lib/Sema/SemaOpenACC.cpp b/clang/lib/Sema/SemaOpenACC.cpp
@@ -1538,7 +1538,6 @@ SemaOpenACC::AssociatedStmtRAII::AssociatedStmtRAII(
     CollectActiveReductionClauses(S.ActiveReductionClauses, Clauses);
     SemaRef.ActiveComputeConstructInfo.Kind = DirKind;
     SemaRef.ActiveComputeConstructInfo.Clauses = Clauses;
-    SemaRef.ParentlessLoopConstructs.swap(ParentlessLoopConstructs);
 
     // OpenACC 3.3 2.9.2: When the parent compute construct is a kernels
     // construct, the gang clause behaves as follows. ... The region of a loop
@@ -1668,9 +1667,8 @@ SemaOpenACC::AssociatedStmtRAII::~AssociatedStmtRAII() {
   if (DirKind == OpenACCDirectiveKind::Parallel ||
       DirKind == OpenACCDirectiveKind::Serial ||
       DirKind == OpenACCDirectiveKind::Kernels) {
-    assert(SemaRef.ParentlessLoopConstructs.empty() &&
-           "Didn't consume loop construct list?");
-    SemaRef.ParentlessLoopConstructs.swap(ParentlessLoopConstructs);
+    // Nothing really to do here, the restorations above should be enough for
+    // now.
   } else if (DirKind == OpenACCDirectiveKind::Loop) {
     // Nothing really to do here, the LoopInConstruct should handle restorations
     // correctly.
@@ -3171,27 +3169,14 @@ StmtResult SemaOpenACC::ActOnEndStmtDirective(OpenACCDirectiveKind K,
   case OpenACCDirectiveKind::Parallel:
   case OpenACCDirectiveKind::Serial:
   case OpenACCDirectiveKind::Kernels: {
-    auto *ComputeConstruct = OpenACCComputeConstruct::Create(
+    return OpenACCComputeConstruct::Create(
         getASTContext(), K, StartLoc, DirLoc, EndLoc, Clauses,
-        AssocStmt.isUsable() ? AssocStmt.get() : nullptr,
-        ParentlessLoopConstructs);
-
-    ParentlessLoopConstructs.clear();
-
-    return ComputeConstruct;
+        AssocStmt.isUsable() ? AssocStmt.get() : nullptr);
   }
   case OpenACCDirectiveKind::Loop: {
-    auto *LoopConstruct = OpenACCLoopConstruct::Create(
-        getASTContext(), StartLoc, DirLoc, EndLoc, Clauses,
-        AssocStmt.isUsable() ? AssocStmt.get() : nullptr);
-
-    // If we are in the scope of a compute construct, add this to the list of
-    // loop constructs that need assigning to the next closing compute
-    // construct.
-    if (isInComputeConstruct())
-      ParentlessLoopConstructs.push_back(LoopConstruct);
-
-    return LoopConstruct;
+    return OpenACCLoopConstruct::Create(
+        getASTContext(), ActiveComputeConstructInfo.Kind, StartLoc, DirLoc,
+        EndLoc, Clauses, AssocStmt.isUsable() ? AssocStmt.get() : nullptr);
   }
   }
   llvm_unreachable("Unhandled case in directive handling?");

diff --git a/clang/lib/Sema/SemaType.cpp b/clang/lib/Sema/SemaType.cpp
@@ -1500,16 +1500,19 @@ static QualType ConvertDeclSpecToType(TypeProcessingState &state) {
     // C99 6.7.3p8:
     //   If the specification of a function type includes any type qualifiers,
     //   the behavior is undefined.
+    // C2y changed this behavior to be implementation-defined. Clang defines
+    // the behavior in all cases to ignore the qualifier, as in C++.
     // C++11 [dcl.fct]p7:
     //   The effect of a cv-qualifier-seq in a function declarator is not the
     //   same as adding cv-qualification on top of the function type. In the
     //   latter case, the cv-qualifiers are ignored.
     if (Result->isFunctionType()) {
+      unsigned DiagId = diag::warn_typecheck_function_qualifiers_ignored;
+      if (!S.getLangOpts().CPlusPlus && !S.getLangOpts().C2y)
+        DiagId = diag::ext_typecheck_function_qualifiers_unspecified;
       diagnoseAndRemoveTypeQualifiers(
           S, DS, TypeQuals, Result, DeclSpec::TQ_const | DeclSpec::TQ_volatile,
-          S.getLangOpts().CPlusPlus
-              ? diag::warn_typecheck_function_qualifiers_ignored
-              : diag::warn_typecheck_function_qualifiers_unspecified);
+          DiagId);
       // No diagnostic for 'restrict' or '_Atomic' applied to a
       // function type; we'll diagnose those later, in BuildQualifiedType.
     }

diff --git a/clang/lib/Serialization/ASTReaderStmt.cpp b/clang/lib/Serialization/ASTReaderStmt.cpp
@@ -2836,12 +2836,12 @@ void ASTStmtReader::VisitOpenACCAssociatedStmtConstruct(
 void ASTStmtReader::VisitOpenACCComputeConstruct(OpenACCComputeConstruct *S) {
   VisitStmt(S);
   VisitOpenACCAssociatedStmtConstruct(S);
-  S->findAndSetChildLoops();
 }
 
 void ASTStmtReader::VisitOpenACCLoopConstruct(OpenACCLoopConstruct *S) {
   VisitStmt(S);
   VisitOpenACCAssociatedStmtConstruct(S);
+  S->ParentComputeConstructKind = Record.readEnum<OpenACCDirectiveKind>();
 }
 
 //===----------------------------------------------------------------------===//

diff --git a/clang/lib/Serialization/ASTWriterStmt.cpp b/clang/lib/Serialization/ASTWriterStmt.cpp
@@ -2915,6 +2915,7 @@ void ASTStmtWriter::VisitOpenACCComputeConstruct(OpenACCComputeConstruct *S) {
 void ASTStmtWriter::VisitOpenACCLoopConstruct(OpenACCLoopConstruct *S) {
   VisitStmt(S);
   VisitOpenACCAssociatedStmtConstruct(S);
+  Record.writeEnum(S->getParentComputeConstructKind());
   Code = serialization::STMT_OPENACC_LOOP_CONSTRUCT;
 }
 

diff --git a/clang/test/C/C2y/n3341.c b/clang/test/C/C2y/n3341.c
@@ -0,0 +1,18 @@
+// RUN: %clang_cc1 -verify -std=c2y -Wall -pedantic %s
+// RUN: %clang_cc1 -verify=gnu -Wall -pedantic %s
+
+/* WG14 N3341: Yes
+ * Slay Some Earthly Demons III
+ *
+ * Empty structure and union objects are now implementation-defined.
+ */
+
+// expected-no-diagnostics
+
+struct R {};               // gnu-warning {{empty struct is a GNU extension}}
+#if __STDC_VERSION__ >= 201112L
+struct S { struct { }; };  // gnu-warning {{empty struct is a GNU extension}}
+#endif
+struct T { int : 0; };     // gnu-warning {{struct without named members is a GNU extension}}
+union U {};                // gnu-warning {{empty union is a GNU extension}}
+
diff --git a/clang/test/C/C2y/n3342.c b/clang/test/C/C2y/n3342.c
@@ -0,0 +1,31 @@
+// RUN: %clang_cc1 -verify=expected,both -std=c2y -Wall -pedantic %s
+// RUN: %clang_cc1 -verify=clang,both -Wall -pedantic %s
+
+/* WG14 N3342: Yes
+ * Slay Some Earthly Demons IV
+ *
+ * Qualified function types are now implementation-defined instead of
+ * undefined. Clang strips the qualifiers.
+ */
+
+typedef int f(void);
+
+const f one;      /* expected-warning {{'const' qualifier on function type 'f' (aka 'int (void)') has no effect}}
+                     clang-warning {{'const' qualifier on function type 'f' (aka 'int (void)') has no effect and is a Clang extension}}
+                   */
+volatile f two;   /* expected-warning {{'volatile' qualifier on function type 'f' (aka 'int (void)') has no effect}}
+                     clang-warning {{'volatile' qualifier on function type 'f' (aka 'int (void)') has no effect and is a Clang extension}}
+                   */
+
+const volatile f three; /* expected-warning {{'const' qualifier on function type 'f' (aka 'int (void)') has no effect}}
+                           clang-warning {{'const' qualifier on function type 'f' (aka 'int (void)') has no effect and is a Clang extension}}
+                           expected-warning {{'volatile' qualifier on function type 'f' (aka 'int (void)') has no effect}}
+                           clang-warning {{'volatile' qualifier on function type 'f' (aka 'int (void)') has no effect and is a Clang extension}}
+                         */
+
+#if __STDC_VERSION__ >= 201112L
+// Atomic types have an explicit constraint making it ill-formed.
+_Atomic f four;   // both-error {{_Atomic cannot be applied to function type 'f' (aka 'int (void)')}}
+#endif
+
+// There's no point to testing 'restrict' because that requires a pointer type.
diff --git a/clang/test/C/C2y/n3346.c b/clang/test/C/C2y/n3346.c
@@ -0,0 +1,74 @@
+// RUN: %clang_cc1 -verify -std=c2y -Wall -pedantic -ffreestanding %s
+// RUN: %clang_cc1 -std=c99 -verify=expected,ped -Wall -pedantic -ffreestanding %s
+
+/* WG14 N3346: Yes
+ * Slay Some Earthly Demons VIII
+ *
+ * Updates some undefined behavior during initialization to instead be a
+ * constraint violation.
+ */
+
+// The initializer for a scalar shall be a single expression, optionally
+// enclosed in braces, or it shall be an empty initializer.
+int i = 12, j = {12}, k = {}; // ped-warning {{use of an empty initializer is a C23 extension}}
+
+struct S {
+  int i;
+  float f;
+  int : 0;
+  char c;
+};
+
+void test1(void) {
+  // The initializer for an object that has structure or union type shall be
+  // either a single expression that has compatible type or a brace-enclosed
+  // list of initializers for the elements or named members.
+  struct S s1 = { 1, 1.2f, 'a' };
+  struct S s2 = s1;
+
+  // Despite being structurally identical to S, T is not compatible with S.
+  struct T { int i; float f; int : 0; char c; } t;
+  struct S s3 = t; // expected-error {{initializing 'struct S' with an expression of incompatible type 'struct T'}}
+}
+
+void test2(void) {
+  typedef __WCHAR_TYPE__ wchar_t;
+
+  // The initializer for an array shall be either a string literal, optionally
+  // enclosed in braces, or a brace-enclosed list of initializers for the
+  // elements. An array initialized by character string literal or UTF-8 string
+  // literal shall have a character type as element type. An array initialized
+  // with a wide string literal shall have element type compatible with a
+  // qualified or unqualified wchar_t, char16_t, or char32_t, and the string
+  // literal shall have the corresponding encoding prefix (L, u, or U,
+  // respectively).
+  char str1[] = "string literal";
+  char str2[] = { "string literal" };
+
+  float str5[] = "this doesn't work";          // expected-error {{array initializer must be an initializer list}}
+  float str6[] = { "this also doesn't work" }; // expected-error {{initializing 'float' with an expression of incompatible type 'char[23]'}}
+
+  wchar_t str7[] = L"string literal";
+  wchar_t str8[] = { L"string literal" };
+
+#if __STDC_VERSION__ >= 201112L
+  typedef __CHAR16_TYPE__ char16_t;
+  typedef __CHAR32_TYPE__ char32_t;
+
+  char str3[] = u8"string literal";
+  char str4[] = { u8"string literal" };
+
+  char16_t str9[] = u"string literal";
+  char16_t str10[] = { u"string literal" };
+  char32_t str11[] = U"string literal";
+  char32_t str12[] = { U"string literal" };
+
+  char16_t str15[] = "nope";     // expected-error {{initializing wide char array with non-wide string literal}}
+  char16_t str16[] = { "nope" }; // expected-error-re {{incompatible pointer to integer conversion initializing 'char16_t' (aka '{{.*}}') with an expression of type 'char[5]'}}
+  char32_t str17[] = "nope";     // expected-error {{initializing wide char array with non-wide string literal}}
+  char32_t str18[] = { "nope" }; // expected-error-re {{incompatible pointer to integer conversion initializing 'char32_t' (aka '{{.*}}') with an expression of type 'char[5]'}}
+#endif
+
+  wchar_t str13[] = "nope";      // expected-error {{initializing wide char array with non-wide string literal}}
+  wchar_t str14[] = { "nope" };  // expected-error-re {{incompatible pointer to integer conversion initializing 'wchar_t' (aka '{{.*}}') with an expression of type 'char[5]'}}
+}
diff --git a/clang/test/CodeGen/X86/builtin_test_helpers.h b/clang/test/CodeGen/X86/builtin_test_helpers.h
@@ -9,6 +9,25 @@ constexpr bool match_m64(__m64 _v, unsigned long long a) {
   return v[0] == a;
 }
 
+constexpr bool match_v1di(__m64 v, long long a) {
+  return v[0] == a;
+}
+
+constexpr bool match_v2si(__m64 _v, int a, int b) {
+  __v2si v = (__v2si)_v;
+  return v[0] == a && v[1] == b;
+}
+
+constexpr bool match_v4hi(__m64 _v, short a, short b, short c, short d) {
+  __v4hi v = (__v4hi)_v;
+  return v[0] == a && v[1] == b && v[2] == c && v[3] == d;
+}
+
+constexpr bool match_v8qi(__m64 _v, char a, char b, char c, char d, char e, char f, char g, char h) {
+  __v8qi v = (__v8qi)_v;
+  return v[0] == a && v[1] == b && v[2] == c && v[3] == d && v[4] == e && v[5] == f && v[6] == g && v[7] == h;
+}
+
 constexpr bool match_m128(__m128 v, float a, float b, float c, float d) {
   return v[0] == a && v[1] == b && v[2] == c && v[3] == d;
 }

diff --git a/clang/test/CodeGen/X86/mmx-builtins.c b/clang/test/CodeGen/X86/mmx-builtins.c
@@ -9,6 +9,7 @@
 
 
 #include <immintrin.h>
+#include "builtin_test_helpers.h"
 
 __m64 test_mm_abs_pi8(__m64 a) {
   // CHECK-LABEL: test_mm_abs_pi8
@@ -409,6 +410,7 @@ __m64 test_mm_set_pi8(char a, char b, char c, char d, char e, char f, char g, ch
   // CHECK: insertelement <8 x i8>
   return _mm_set_pi8(a, b, c, d, e, f, g, h);
 }
+TEST_CONSTEXPR(match_v8qi(_mm_set_pi8(0, -1, 2, -3, 4, -5, 6, -7), -7, 6, -5, 4, -3, 2, -1, 0));
 
 __m64 test_mm_set_pi16(short a, short b, short c, short d) {
   // CHECK-LABEL: test_mm_set_pi16
@@ -418,13 +420,15 @@ __m64 test_mm_set_pi16(short a, short b, short c, short d) {
   // CHECK: insertelement <4 x i16>
   return _mm_set_pi16(a, b, c, d);
 }
+TEST_CONSTEXPR(match_v4hi(_mm_set_pi16(101, 102, -103, -104), -104, -103, 102, 101));
 
 __m64 test_mm_set_pi32(int a, int b) {
   // CHECK-LABEL: test_mm_set_pi32
   // CHECK: insertelement <2 x i32>
   // CHECK: insertelement <2 x i32>
   return _mm_set_pi32(a, b);
 }
+TEST_CONSTEXPR(match_v2si(_mm_set_pi32(5000, -1500), -1500, 5000));
 
 __m64 test_mm_setr_pi8(char a, char b, char c, char d, char e, char f, char g, char h) {
   // CHECK-LABEL: test_mm_setr_pi8
@@ -438,6 +442,7 @@ __m64 test_mm_setr_pi8(char a, char b, char c, char d, char e, char f, char g, c
   // CHECK: insertelement <8 x i8>
   return _mm_setr_pi8(a, b, c, d, e, f, g, h);
 }
+TEST_CONSTEXPR(match_v8qi(_mm_setr_pi8(0, -1, 2, -3, 4, -5, 6, -7), 0, -1, 2, -3, 4, -5, 6, -7));
 
 __m64 test_mm_setr_pi16(short a, short b, short c, short d) {
   // CHECK-LABEL: test_mm_setr_pi16
@@ -447,13 +452,22 @@ __m64 test_mm_setr_pi16(short a, short b, short c, short d) {
   // CHECK: insertelement <4 x i16>
   return _mm_setr_pi16(a, b, c, d);
 }
+TEST_CONSTEXPR(match_v4hi(_mm_setr_pi16(101, 102, -103, -104), 101, 102, -103, -104));
 
 __m64 test_mm_setr_pi32(int a, int b) {
   // CHECK-LABEL: test_mm_setr_pi32
   // CHECK: insertelement <2 x i32>
   // CHECK: insertelement <2 x i32>
   return _mm_setr_pi32(a, b);
 }
+TEST_CONSTEXPR(match_v2si(_mm_setr_pi32(5000, -1500), 5000, -1500));
+
+__m64 test_mm_setzero_si64() {
+  // CHECK-LABEL: test_mm_setzero_si64
+  // CHECK: zeroinitializer
+  return _mm_setzero_si64();
+}
+TEST_CONSTEXPR(match_m64(_mm_setzero_si64(), 0ULL));
 
 __m64 test_mm_set1_pi8(char a) {
   // CHECK-LABEL: test_mm_set1_pi8
@@ -467,6 +481,7 @@ __m64 test_mm_set1_pi8(char a) {
   // CHECK: insertelement <8 x i8>
   return _mm_set1_pi8(a);
 }
+TEST_CONSTEXPR(match_v8qi(_mm_set1_pi8(99), 99, 99, 99, 99, 99, 99, 99, 99));
 
 __m64 test_mm_set1_pi16(short a) {
   // CHECK-LABEL: test_mm_set1_pi16
@@ -476,13 +491,15 @@ __m64 test_mm_set1_pi16(short a) {
   // CHECK: insertelement <4 x i16>
   return _mm_set1_pi16(a);
 }
+TEST_CONSTEXPR(match_v4hi(_mm_set1_pi16(-128), -128, -128, -128, -128));
 
 __m64 test_mm_set1_pi32(int a) {
   // CHECK-LABEL: test_mm_set1_pi32
   // CHECK: insertelement <2 x i32>
   // CHECK: insertelement <2 x i32>
   return _mm_set1_pi32(a);
 }
+TEST_CONSTEXPR(match_v2si(_mm_set1_pi32(55), 55, 55));
 
 __m64 test_mm_shuffle_pi8(__m64 a, __m64 b) {
   // CHECK-LABEL: test_mm_shuffle_pi8

diff --git a/clang/test/CodeGen/X86/sse2-builtins.c b/clang/test/CodeGen/X86/sse2-builtins.c
@@ -867,20 +867,19 @@ __m128d test_mm_min_sd(__m128d A, __m128d B) {
   return _mm_min_sd(A, B);
 }
 
-__m64 test_mm_movepi64_pi64(__m128i A)
-{
+__m64 test_mm_movepi64_pi64(__m128i A) {
   // CHECK-LABEL: test_mm_movepi64_pi64
   // CHECK: [[EXT:%.*]] = extractelement <2 x i64> %1, i32 0
   return _mm_movepi64_pi64(A);
 }
 TEST_CONSTEXPR(match_m64(_mm_movepi64_pi64((__m128i){8, -8}), 8ULL));
 
-__m128i test_mm_movpi64_epi64(__m64 A)
-{
+__m128i test_mm_movpi64_epi64(__m64 A) {
   // CHECK-LABEL: test_mm_movpi64_epi64
   // CHECK: shufflevector <1 x i64> %{{.*}}, <1 x i64> %{{.*}}, <2 x i32> <i32 0, i32 1>
   return _mm_movpi64_epi64(A);
 }
+TEST_CONSTEXPR(match_m128i(_mm_movpi64_epi64((__m64){5LL}), 5ULL, 0ULL));
 
 __m128i test_mm_move_epi64(__m128i A) {
   // CHECK-LABEL: test_mm_move_epi64

diff --git a/clang/test/CodeGen/aarch64-fmv-dependencies.c b/clang/test/CodeGen/aarch64-fmv-dependencies.c
@@ -189,7 +189,7 @@ int caller() {
 // CHECK: attributes #[[ssbs]] = { {{.*}} "target-features"="+fp-armv8,+neon,+outline-atomics,+ssbs,+v8a"
 // CHECK: attributes #[[sve]] = { {{.*}} "target-features"="+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+v8a"
 // CHECK: attributes #[[sve2]] = { {{.*}} "target-features"="+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve2,+v8a"
-// CHECK: attributes #[[sve2_aes]] = { {{.*}} "target-features"="+aes,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve-aes,+sve2,+v8a"
+// CHECK: attributes #[[sve2_aes]] = { {{.*}} "target-features"="+aes,+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve2,+sve2-aes,+v8a"
 // CHECK: attributes #[[sve2_bitperm]] = { {{.*}} "target-features"="+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve2,+sve2-bitperm,+v8a"
 // CHECK: attributes #[[sve2_sha3]] = { {{.*}} "target-features"="+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve2,+sve2-sha3,+v8a"
 // CHECK: attributes #[[sve2_sm4]] = { {{.*}} "target-features"="+fp-armv8,+fullfp16,+neon,+outline-atomics,+sve,+sve2,+sve2-sm4,+v8a"

diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aesd.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aesd.c
@@ -1,8 +1,8 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
 
 // REQUIRES: aarch64-registered-target
 

diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aese.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aese.c
@@ -1,8 +1,8 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
 
 // REQUIRES: aarch64-registered-target
 

diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aesimc.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aesimc.c
@@ -1,8 +1,8 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
-// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
 
 // REQUIRES: aarch64-registered-target
 

diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aesmc.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_aesmc.c
@@ -1,8 +1,8 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
-// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
 
 // REQUIRES: aarch64-registered-target
 

diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb_128.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullb_128.c
@@ -1,10 +1,10 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // REQUIRES: aarch64-registered-target
 
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
 
 #include <arm_sve.h>
 

diff --git a/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt_128.c b/clang/test/CodeGen/aarch64-sve2-intrinsics/acle_sve2_pmullt_128.c
@@ -1,10 +1,10 @@
 // NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
 // REQUIRES: aarch64-registered-target
 
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
-// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -fclang-abi-compat=latest -DSVE_OVERLOADED_FORMS -triple aarch64 -target-feature +sve -target-feature +sve2 -target-feature +sve2-aes -O1 -Werror -Wall -emit-llvm -o - -x c++ %s | FileCheck %s -check-prefix=CPP-CHECK
 
 #include <arm_sve.h>
 

diff --git a/clang/test/Driver/aarch64-implied-sve-features.c b/clang/test/Driver/aarch64-implied-sve-features.c
@@ -36,7 +36,7 @@
 // SVE2-BITPERM-REVERT: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "-sve2-bitperm"
 
 // RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve2-aes+nosve2-aes %s -### 2>&1 | FileCheck %s --check-prefix=SVE2-AES-REVERT
-// SVE2-AES-REVERT: "-target-feature" "+sve" "-target-feature" "+sve-aes" "-target-feature" "+sve2" "-target-feature" "-sve2-aes"
+// SVE2-AES-REVERT: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "-sve2-aes"
 
 // RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve2-sha3+nosve2-sha3 %s -### 2>&1 | FileCheck %s --check-prefix=SVE2-SHA3-REVERT
 // SVE2-SHA3-REVERT: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "-sve2-sha3"
@@ -47,11 +47,8 @@
 // RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve2-sha3 %s -### 2>&1 | FileCheck %s --check-prefix=SVE2-SHA3
 // SVE2-SHA3: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "+sve2-sha3"
 
-// RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve-aes %s -### 2>&1 | FileCheck %s --check-prefix=SVE-AES
-// SVE-AES: "-target-feature" "+aes"{{.*}} "-target-feature" "+sve-aes"
-
 // RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve2-aes %s -### 2>&1 | FileCheck %s --check-prefix=SVE2-AES
-// SVE2-AES: "-target-feature" "+sve" "-target-feature" "+sve-aes" "-target-feature" "+sve2" "-target-feature" "+sve2-aes"
+// SVE2-AES: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "+sve2-aes"
 
 // RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+sve2-sm4 %s -### 2>&1 | FileCheck %s --check-prefix=SVE2-SM4
 // SVE2-SM4: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "+sve2-sm4"
@@ -69,7 +66,7 @@
 // SVE-SUBFEATURE-CONFLICT-NOT: "-target-feature" "+sve"
 
 // RUN: %clang --target=aarch64-linux-gnu -march=armv8-a+nosve+sve2-aes %s -### 2>&1 | FileCheck %s --check-prefix=SVE-SUBFEATURE-CONFLICT-REV
-// SVE-SUBFEATURE-CONFLICT-REV: "-target-feature" "+sve" "-target-feature" "+sve-aes" "-target-feature" "+sve2" "-target-feature" "+sve2-aes"
+// SVE-SUBFEATURE-CONFLICT-REV: "-target-feature" "+sve" "-target-feature" "+sve2" "-target-feature" "+sve2-aes"
 
 // RUN: %clang --target=aarch64-linux-gnu -mcpu=neoverse-n2+nosve2 %s -### 2>&1 | FileCheck %s --check-prefix=SVE-MCPU-FEATURES
 // SVE-MCPU-FEATURES-NOT: "-target-feature" "+sve2-bitperm"

diff --git a/clang/test/Driver/hip-wavefront-size-deprecation-diagnostics.hip b/clang/test/Driver/hip-wavefront-size-deprecation-diagnostics.hip
diff --git a/clang/test/Driver/print-supported-extensions-aarch64.c b/clang/test/Driver/print-supported-extensions-aarch64.c
@@ -77,18 +77,17 @@
 // CHECK-NEXT:     profile             FEAT_SPE                                               Enable Statistical Profiling extension
 // CHECK-NEXT:     predres2            FEAT_SPECRES2                                          Enable Speculation Restriction Instruction
 // CHECK-NEXT:     ssbs                FEAT_SSBS, FEAT_SSBS2                                  Enable Speculative Store Bypass Safe bit
-// CHECK-NEXT:     ssve-aes            FEAT_SSVE_AES                                          Enable Armv9.6-A SVE AES support in streaming SVE mode
+// CHECK-NEXT:     ssve-aes            FEAT_SSVE_AES                                          Enable Armv9.6-A SVE2 AES support in streaming SVE mode
 // CHECK-NEXT:     ssve-fp8dot2        FEAT_SSVE_FP8DOT2                                      Enable SVE2 FP8 2-way dot product instructions
 // CHECK-NEXT:     ssve-fp8dot4        FEAT_SSVE_FP8DOT4                                      Enable SVE2 FP8 4-way dot product instructions
 // CHECK-NEXT:     ssve-fp8fma         FEAT_SSVE_FP8FMA                                       Enable SVE2 FP8 multiply-add instructions
 // CHECK-NEXT:     sve                 FEAT_SVE                                               Enable Scalable Vector Extension (SVE) instructions
-// CHECK-NEXT:     sve-aes             FEAT_SVE_AES, FEAT_SVE_PMULL128                        Enable SVE AES and quadword SVE polynomial multiply instructions
-// CHECK-NEXT:     sve-aes2            FEAT_SVE_AES2                                          Enable Armv9.6-A SVE multi-vector AES and multi-vector quadword polynomial multiply instructions
+// CHECK-NEXT:     sve-aes2            FEAT_SVE_AES2                                          Enable Armv9.6-A SVE multi-vector AES and 128-bit PMULL instructions
 // CHECK-NEXT:     sve-b16b16          FEAT_SVE_B16B16                                        Enable SVE2 non-widening and SME2 Z-targeting non-widening BFloat16 instructions
 // CHECK-NEXT:     sve-bfscale         FEAT_SVE_BFSCALE                                       Enable Armv9.6-A SVE BFloat16 scaling instructions
 // CHECK-NEXT:     sve-f16f32mm        FEAT_SVE_F16F32MM                                      Enable Armv9.6-A FP16 to FP32 Matrix Multiply
 // CHECK-NEXT:     sve2                FEAT_SVE2                                              Enable Scalable Vector Extension 2 (SVE2) instructions
-// CHECK-NEXT:     sve2-aes                                                                   An alias of +sve2+sve-aes
+// CHECK-NEXT:     sve2-aes            FEAT_SVE_AES, FEAT_SVE_PMULL128                        Enable AES SVE2 instructions
 // CHECK-NEXT:     sve2-bitperm        FEAT_SVE_BitPerm                                       Enable bit permutation SVE2 instructions
 // CHECK-NEXT:     sve2-sha3           FEAT_SVE_SHA3                                          Enable SHA3 SVE2 instructions
 // CHECK-NEXT:     sve2-sm4            FEAT_SVE_SM4                                           Enable SM4 SVE2 instructions

diff --git a/clang/test/Misc/warning-flags.c b/clang/test/Misc/warning-flags.c
@@ -18,7 +18,7 @@ This test serves two purposes:
 
 The list of warnings below should NEVER grow.  It should gradually shrink to 0.
 
-CHECK: Warnings without flags (62):
+CHECK: Warnings without flags (61):
 
 CHECK-NEXT:   ext_expected_semi_decl_list
 CHECK-NEXT:   ext_missing_whitespace_after_macro_name
@@ -76,7 +76,6 @@ CHECK-NEXT:   warn_register_objc_catch_parm
 CHECK-NEXT:   warn_related_result_type_compatibility_class
 CHECK-NEXT:   warn_related_result_type_compatibility_protocol
 CHECK-NEXT:   warn_template_export_unsupported
-CHECK-NEXT:   warn_typecheck_function_qualifiers
 CHECK-NEXT:   warn_undef_interface
 CHECK-NEXT:   warn_undef_interface_suggest
 CHECK-NEXT:   warn_undef_protocolref

diff --git a/clang/test/Preprocessor/aarch64-target-features.c b/clang/test/Preprocessor/aarch64-target-features.c
@@ -227,20 +227,8 @@
 // CHECK-NONEON-NOT: __ARM_FEATURE_SVE 1
 // CHECK-NONEON-NOT: __ARM_NEON 1
 
-// RUN: %clang -target aarch64-none-linux-gnu -march=armv9-a+sve-aes -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SVEAES %s
-// CHECK-SVEAES: __ARM_FEATURE_AES 1
-
 // RUN: %clang -target aarch64-none-linux-gnu -march=armv9-a+sve2-aes -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SVE2AES %s
-// CHECK-SVE2AES: __ARM_FEATURE_AES 1
-// CHECK-SVE2AES: __ARM_FEATURE_SVE2 1
 // CHECK-SVE2AES: __ARM_FEATURE_SVE2_AES 1
-
-// RUN: %clang -target aarch64-none-linux-gnu -march=armv9-a+sve-aes+sve2 -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SVEAES-SVE2 %s
-// CHECK-SVEAES-SVE2: __ARM_FEATURE_AES 1
-// CHECK-SVEAES-SVE2: __ARM_FEATURE_SVE2 1
-// CHECK-SVEAES-SVE2: __ARM_FEATURE_SVE2_AES 1
-
-
 // RUN: %clang -target aarch64-none-linux-gnu -march=armv9-a+sve2-sha3 -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SVE2SHA3 %s
 // CHECK-SVE2SHA3: __ARM_FEATURE_SVE2_SHA3 1
 // RUN: %clang -target aarch64-none-linux-gnu -march=armv9-a+sve2-sm4 -x c -E -dM %s -o - | FileCheck --check-prefix=CHECK-SVE2SM4 %s

diff --git a/clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_aes_bitperm_sha3_sm4.cpp b/clang/test/Sema/aarch64-sve2-intrinsics/acle_sve2_aes_bitperm_sha3_sm4.cpp
@@ -14,17 +14,17 @@
 
 void test(uint8_t u8, uint16_t u16, uint32_t u32, uint64_t u64)
 {
-  // expected-error@+2 {{'svaesd_u8' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svaesd' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svaesd_u8' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svaesd' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svaesd,_u8,,)(svundef_u8(), svundef_u8());
-  // expected-error@+2 {{'svaese_u8' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svaese' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svaese_u8' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svaese' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svaese,_u8,,)(svundef_u8(), svundef_u8());
-  // expected-error@+2 {{'svaesimc_u8' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svaesimc' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svaesimc_u8' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svaesimc' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svaesimc,_u8,,)(svundef_u8());
-  // expected-error@+2 {{'svaesmc_u8' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svaesmc' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svaesmc_u8' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svaesmc' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svaesmc,_u8,,)(svundef_u8());
   // expected-error@+2 {{'svbdep_u8' needs target feature sve,sve2-bitperm}}
   // overload-error@+1 {{'svbdep' needs target feature sve,sve2-bitperm}}
@@ -107,17 +107,17 @@ void test(uint8_t u8, uint16_t u16, uint32_t u32, uint64_t u64)
   // expected-error@+2 {{'svbgrp_n_u64' needs target feature sve,sve2-bitperm}}
   // overload-error@+1 {{'svbgrp' needs target feature sve,sve2-bitperm}}
   SVE_ACLE_FUNC(svbgrp,_n_u64,,)(svundef_u64(), u64);
-  // expected-error@+2 {{'svpmullb_pair_u64' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svpmullb_pair' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svpmullb_pair_u64' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svpmullb_pair' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svpmullb_pair,_u64,,)(svundef_u64(), svundef_u64());
-  // expected-error@+2 {{'svpmullb_pair_n_u64' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svpmullb_pair' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svpmullb_pair_n_u64' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svpmullb_pair' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svpmullb_pair,_n_u64,,)(svundef_u64(), u64);
-  // expected-error@+2 {{'svpmullt_pair_u64' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svpmullt_pair' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svpmullt_pair_u64' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svpmullt_pair' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svpmullt_pair,_u64,,)(svundef_u64(), svundef_u64());
-  // expected-error@+2 {{'svpmullt_pair_n_u64' needs target feature sve,sve2,sve-aes}}
-  // overload-error@+1 {{'svpmullt_pair' needs target feature sve,sve2,sve-aes}}
+  // expected-error@+2 {{'svpmullt_pair_n_u64' needs target feature sve,sve2-aes}}
+  // overload-error@+1 {{'svpmullt_pair' needs target feature sve,sve2-aes}}
   SVE_ACLE_FUNC(svpmullt_pair,_n_u64,,)(svundef_u64(), u64);
   // expected-error@+2 {{'svrax1_u64' needs target feature sve,sve2-sha3}}
   // overload-error@+1 {{'svrax1' needs target feature sve,sve2-sha3}}

diff --git a/clang/test/Sema/declspec.c b/clang/test/Sema/declspec.c
@@ -16,9 +16,9 @@ int gv2;
 static void buggy(int *x) { }
 
 // Type qualifiers.
-typedef int f(void); 
+typedef int f(void);
 typedef f* fptr;
-const f* v1;         // expected-warning {{qualifier on function type 'f' (aka 'int (void)') has unspecified behavior}}
+const f* v1;         // expected-warning {{'const' qualifier on function type 'f' (aka 'int (void)') has no effect and is a Clang extension}}
 __restrict__ f* v2;  // expected-error {{restrict requires a pointer or reference ('f' (aka 'int (void)') is invalid)}}
 __restrict__ fptr v3; // expected-error {{pointer to function type 'f' (aka 'int (void)') may not be 'restrict' qualified}}
 f *__restrict__ v4;   // expected-error {{pointer to function type 'f' (aka 'int (void)') may not be 'restrict' qualified}}

diff --git a/clang/test/SemaOpenACC/compute-construct-default-clause.c b/clang/test/SemaOpenACC/compute-construct-default-clause.c
@@ -23,18 +23,18 @@ void SingleOnly() {
   // expected-warning@+2{{OpenACC clause 'default' not yet implemented}}
   // expected-warning@+1{{OpenACC clause 'copy' not yet implemented}}
   #pragma acc parallel loop self default(present) private(i) default(none) copy(i)
-  while(0);
+  for(int i = 0; i < 5; ++i);
 
   // expected-warning@+3{{OpenACC clause 'self' not yet implemented, clause ignored}}
   // expected-warning@+2{{OpenACC construct 'serial loop' not yet implemented}}
   // expected-error@+1{{expected '('}}
   #pragma acc serial loop self default private(i) default(none) if(i)
-  while(0);
+  for(int i = 0; i < 5; ++i);
 
   // expected-warning@+2{{OpenACC construct 'kernels loop' not yet implemented}}
   // expected-warning@+1{{OpenACC clause 'default' not yet implemented}}
   #pragma acc kernels loop default(none)
-  while(0);
+  for(int i = 0; i < 5; ++i);
 
   // expected-warning@+2{{OpenACC construct 'data' not yet implemented}}
   // expected-warning@+1{{OpenACC clause 'default' not yet implemented}}

diff --git a/clang/test/SemaOpenACC/compute-construct-if-clause.c b/clang/test/SemaOpenACC/compute-construct-if-clause.c
@@ -50,15 +50,15 @@ void BoolExpr(int *I, float *F) {
   // expected-warning@+2{{OpenACC construct 'parallel loop' not yet implemented}}
   // expected-warning@+1{{OpenACC clause 'if' not yet implemented}}
 #pragma acc parallel loop if (*I < *F)
-  while(0);
+  for(int i = 0; i < 5; ++i);
   // expected-warning@+2{{OpenACC construct 'serial loop' not yet implemented}}
   // expected-warning@+1{{OpenACC clause 'if' not yet implemented}}
 #pragma acc serial loop if (*I < *F)
-  while(0);
+  for(int i = 0; i < 5; ++i);
   // expected-warning@+2{{OpenACC construct 'kernels loop' not yet implemented}}
   // expected-warning@+1{{OpenACC clause 'if' not yet implemented}}
 #pragma acc kernels loop if (*I < *F)
-  while(0);
+  for(int i = 0; i < 5; ++i);
 
   // expected-error@+1{{OpenACC 'if' clause is not valid on 'loop' directive}}
 #pragma acc loop if(I)

diff --git a/clang/test/SemaOpenACC/loop-ast.cpp b/clang/test/SemaOpenACC/loop-ast.cpp
@@ -42,12 +42,12 @@ void NormalFunc() {
   // CHECK-NEXT: CompoundStmt
   {
 #pragma acc parallel
-    // CHECK-NEXT: OpenACCComputeConstruct [[PAR_ADDR:[0-9a-fx]+]] {{.*}}parallel
+    // CHECK-NEXT: OpenACCComputeConstruct {{.*}}parallel
     // CHECK-NEXT: CompoundStmt
     {
 #pragma acc loop
       for(int i = 0; i < 5;++i);
-    // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: [[PAR_ADDR]]
+    // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
     // CHECK-NEXT: ForStmt
     // CHECK-NEXT: DeclStmt
     // CHECK-NEXT: VarDecl {{.*}} used i 'int'
@@ -91,16 +91,16 @@ void TemplFunc() {
 
   }
 
-#pragma acc parallel
+#pragma acc serial
   {
-    // CHECK-NEXT: OpenACCComputeConstruct {{.*}}parallel
+    // CHECK-NEXT: OpenACCComputeConstruct {{.*}}serial
     // CHECK-NEXT: CompoundStmt
 #pragma acc parallel
     {
-    // CHECK-NEXT: OpenACCComputeConstruct [[PAR_ADDR_UNINST:[0-9a-fx]+]] {{.*}}parallel
+    // CHECK-NEXT: OpenACCComputeConstruct {{.*}}parallel
     // CHECK-NEXT: CompoundStmt
 #pragma acc loop
-    // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: [[PAR_ADDR_UNINST]]
+    // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
     // CHECK-NEXT: ForStmt
     // CHECK-NEXT: DeclStmt
     // CHECK-NEXT: VarDecl {{.*}} i 'int'
@@ -116,7 +116,7 @@ void TemplFunc() {
       for(int i = 0; i < 5;++i);
 
 #pragma acc loop
-    // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: [[PAR_ADDR_UNINST]]
+    // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
     // CHECK-NEXT: ForStmt
     // CHECK-NEXT: DeclStmt
     // CHECK-NEXT: VarDecl {{.*}} i 'int'
@@ -166,13 +166,13 @@ void TemplFunc() {
   // CHECK-NEXT: DeclStmt
   // CHECK-NEXT: VarDecl{{.*}} I 'typename S::type':'int'
 
-  // CHECK-NEXT: OpenACCComputeConstruct {{.*}}parallel
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}}serial
   // CHECK-NEXT: CompoundStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct [[PAR_ADDR_INST:[0-9a-fx]+]] {{.*}}parallel
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}}parallel
   // CHECK-NEXT: CompoundStmt
 
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: [[PAR_ADDR_INST]]
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
   // CHECK-NEXT: VarDecl {{.*}} i 'int'
@@ -186,7 +186,7 @@ void TemplFunc() {
   // CHECK-NEXT: DeclRefExpr{{.*}} 'i' 'int'
   // CHECK-NEXT: NullStmt
 
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: [[PAR_ADDR_INST]]
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
   // CHECK-NEXT: VarDecl {{.*}} i 'int'

diff --git a/clang/test/SemaOpenACC/loop-construct-gang-ast.cpp b/clang/test/SemaOpenACC/loop-construct-gang-ast.cpp
@@ -53,8 +53,8 @@ void NormalUses() {
 #pragma acc loop gang(static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: gang clause num
   // CHECK-NEXT: IntegerLiteral{{.*}}'int' 1
   // CHECK-NEXT: gang clause static
@@ -76,8 +76,8 @@ void NormalUses() {
 #pragma acc loop gang(num:1) gang(static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: gang clause dim static
   // CHECK-NEXT: ConstantExpr{{.*}} 'int'
   // CHECK-NEXT: value: Int 1
@@ -100,8 +100,8 @@ void NormalUses() {
 #pragma acc loop gang(dim:1, static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause static
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}} 'Val' 'int'
@@ -121,8 +121,8 @@ void NormalUses() {
 #pragma acc loop gang(static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}}serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause static
   // CHECK-NEXT: OpenACCAsteriskSizeExpr
   // CHECK-NEXT: ForStmt
@@ -141,8 +141,8 @@ void NormalUses() {
 #pragma acc loop gang(static:*)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -224,8 +224,8 @@ void TemplateUses(T Val) {
 #pragma acc loop gang(static:*)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: gang clause dim
   // CHECK-NEXT: DeclRefExpr{{.*}}'unsigned int' NonTypeTemplateParm{{.*}} 'One' 'unsigned int'
   // CHECK-NEXT: gang clause static
@@ -246,8 +246,8 @@ void TemplateUses(T Val) {
 #pragma acc loop gang(dim:One) gang(static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: gang clause dim static
   // CHECK-NEXT: DeclRefExpr{{.*}}'unsigned int' NonTypeTemplateParm{{.*}} 'One' 'unsigned int'
   // CHECK-NEXT: DeclRefExpr{{.*}}'T' lvalue ParmVar{{.*}} 'Val' 'T'
@@ -267,8 +267,8 @@ void TemplateUses(T Val) {
 #pragma acc loop gang(dim:One, static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause static
   // CHECK-NEXT: DeclRefExpr{{.*}}'T' lvalue ParmVar{{.*}} 'Val' 'T'
   // CHECK-NEXT: ForStmt
@@ -287,8 +287,8 @@ void TemplateUses(T Val) {
 #pragma acc loop gang(static:Val)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -367,8 +367,8 @@ void TemplateUses(T Val) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: gang clause dim
   // CHECK-NEXT: ConstantExpr{{.*}} 'unsigned int'
   // CHECK-NEXT: value: Int 1
@@ -391,8 +391,8 @@ void TemplateUses(T Val) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: gang clause dim static
   // CHECK-NEXT: ConstantExpr{{.*}} 'unsigned int'
   // CHECK-NEXT: value: Int 1
@@ -414,8 +414,8 @@ void TemplateUses(T Val) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause static
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}}'int' lvalue ParmVar{{.*}} 'Val' 'int'
@@ -432,8 +432,8 @@ void TemplateUses(T Val) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: gang clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt

diff --git a/clang/test/SemaOpenACC/loop-construct-vector-ast.cpp b/clang/test/SemaOpenACC/loop-construct-vector-ast.cpp
@@ -70,8 +70,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop vector(length:CTI)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: DeclRefExpr{{.*}}'Int' lvalue ParmVar{{.*}}'IsI' 'Int'
   // CHECK-NEXT: ForStmt
@@ -90,8 +90,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop vector(length:IsI)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -109,8 +109,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop vector
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: DeclRefExpr{{.*}}'Int' lvalue ParmVar{{.*}}'IsI' 'Int'
   // CHECK-NEXT: ForStmt
@@ -194,8 +194,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}}'int' lvalue ParmVar{{.*}}'IsI' 'int'
@@ -212,8 +212,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -228,8 +228,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}}'int' lvalue ParmVar{{.*}}'IsI' 'int'
@@ -330,8 +330,8 @@ void uses() {
 #pragma acc loop vector(length:C)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -349,8 +349,8 @@ void uses() {
 #pragma acc loop vector
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <UserDefinedConversion>
   // CHECK-NEXT: CXXMemberCallExpr{{.*}}'int'
@@ -372,8 +372,8 @@ void uses() {
 #pragma acc loop vector(C)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}}'int' lvalue Var
@@ -393,8 +393,8 @@ void uses() {
 #pragma acc loop vector(length:i)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -412,8 +412,8 @@ void uses() {
 #pragma acc loop vector
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <UserDefinedConversion>
   // CHECK-NEXT: CXXMemberCallExpr{{.*}}'int'
@@ -435,8 +435,8 @@ void uses() {
 #pragma acc loop vector(C)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}}'int' lvalue Var
@@ -456,8 +456,8 @@ void uses() {
 #pragma acc loop vector(length:i)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: vector clause
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt

diff --git a/clang/test/SemaOpenACC/loop-construct-worker-ast.cpp b/clang/test/SemaOpenACC/loop-construct-worker-ast.cpp
@@ -34,8 +34,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop worker
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -53,8 +53,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop worker
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -72,8 +72,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop worker
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: DeclRefExpr{{.*}} 'ConvertsToInt' lvalue ParmVar
   // CHECK-NEXT: ForStmt
@@ -92,8 +92,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop worker(CTI)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: DeclRefExpr{{.*}} 'Int' lvalue ParmVar
   // CHECK-NEXT: ForStmt
@@ -112,8 +112,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
 #pragma acc loop worker(num:IsI)
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: DeclRefExpr{{.*}} 'unsigned int' NonTypeTemplateParm{{.*}}'I' 'unsigned int'
   // CHECK-NEXT: ForStmt
@@ -159,8 +159,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -175,8 +175,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -191,8 +191,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ImplicitCastExpr{{.*}} 'int' <UserDefinedConversion>
   // CHECK-NEXT: CXXMemberCallExpr{{.*}} 'int'
@@ -211,8 +211,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ImplicitCastExpr{{.*}} 'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}} 'int' lvalue ParmVar{{.*}} 'IsI' 'int'
@@ -229,8 +229,8 @@ void TemplUses(ConvertsToInt CTI, Int IsI) {
   // CHECK-NEXT: DeclRefExpr{{.*}}'i' 'int'
   // CHECK-NEXT: NullStmt
   //
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: SubstNonTypeTemplateParmExpr{{.*}}'unsigned int'
   // CHECK-NEXT: NonTypeTemplateParmDecl{{.*}}'unsigned int' depth 0 index 0 I
@@ -277,8 +277,8 @@ void uses() {
 #pragma acc loop worker
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} parallel
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} parallel
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: parallel
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -296,8 +296,8 @@ void uses() {
 #pragma acc loop worker
   for(int i = 0; i < 5; ++i);
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} serial
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} serial
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: serial
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ForStmt
   // CHECK-NEXT: DeclStmt
@@ -320,8 +320,8 @@ void uses() {
   // CHECK-NEXT: VarDecl
   // CHECK-NEXT: CXXConstructExpr
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <UserDefinedConversion>
   // CHECK-NEXT: CXXMemberCallExpr{{.*}} 'int'
@@ -347,8 +347,8 @@ void uses() {
   // CHECK-NEXT: DeclStmt
   // CHECK-NEXT: VarDecl
 
-  // CHECK-NEXT: OpenACCComputeConstruct 0x[[COMPUTE_ADDR:[0-9a-f]+]]{{.*}} kernels
-  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: 0x[[COMPUTE_ADDR]]
+  // CHECK-NEXT: OpenACCComputeConstruct {{.*}} kernels
+  // CHECK-NEXT: OpenACCLoopConstruct{{.*}} parent: kernels
   // CHECK-NEXT: worker clause{{.*}}
   // CHECK-NEXT: ImplicitCastExpr{{.*}}'int' <LValueToRValue>
   // CHECK-NEXT: DeclRefExpr{{.*}}'int' lvalue Var

diff --git a/clang/utils/perf-training/bolt.lit.cfg b/clang/utils/perf-training/bolt.lit.cfg
@@ -49,3 +49,6 @@ config.substitutions.append(("%clang_cpp", f" {config.clang} --driver-mode=g++ "
 config.substitutions.append(("%clang_skip_driver", config.clang))
 config.substitutions.append(("%clang", config.clang))
 config.substitutions.append(("%test_root", config.test_exec_root))
+config.substitutions.append(('%cmake_generator', config.cmake_generator))
+config.substitutions.append(('%cmake', config.cmake_exe))
+config.substitutions.append(('%llvm_src_dir', config.llvm_src_dir))
diff --git a/clang/utils/perf-training/bolt.lit.site.cfg.in b/clang/utils/perf-training/bolt.lit.site.cfg.in
@@ -11,6 +11,9 @@ config.python_exe = "@Python3_EXECUTABLE@"
 config.clang_obj_root = path(r"@CLANG_BINARY_DIR@")
 config.clang_bolt_mode = "@CLANG_BOLT@"
 config.clang_bolt_name = "@CLANG_BOLT_INSTRUMENTED@"
+config.cmake_exe = "@CMAKE_COMMAND@"
+config.llvm_src_dir ="@CMAKE_SOURCE_DIR@"
+config.cmake_generator ="@CMAKE_GENERATOR@"
 
 # Let the main config do the real work.
 lit_config.load_config(config, "@CLANG_SOURCE_DIR@/utils/perf-training/bolt.lit.cfg")
diff --git a/clang/utils/perf-training/lit.cfg b/clang/utils/perf-training/lit.cfg
@@ -34,8 +34,11 @@ config.test_format = lit.formats.ShTest(use_lit_shell == "0")
 config.substitutions.append( ('%clang_cpp_skip_driver', ' %s %s %s ' % (cc1_wrapper, config.clang, sysroot_flags)))
 config.substitutions.append( ('%clang_cpp', ' %s --driver-mode=g++ %s ' % (config.clang, sysroot_flags)))
 config.substitutions.append( ('%clang_skip_driver', ' %s %s %s ' % (cc1_wrapper, config.clang, sysroot_flags)))
-config.substitutions.append( ('%clang', ' %s %s ' % (config.clang, sysroot_flags) ) )
+config.substitutions.append( ('%clang', '%s %s ' % (config.clang, sysroot_flags) ) )
 config.substitutions.append( ('%test_root', config.test_exec_root ) )
+config.substitutions.append( ('%cmake_generator', config.cmake_generator ) )
+config.substitutions.append( ('%cmake', config.cmake_exe ) )
+config.substitutions.append( ('%llvm_src_dir', config.llvm_src_dir ) )
 
 config.environment['LLVM_PROFILE_FILE'] = 'perf-training-%4m.profraw'
 
diff --git a/clang/utils/perf-training/lit.site.cfg.in b/clang/utils/perf-training/lit.site.cfg.in
@@ -8,6 +8,9 @@ config.test_exec_root = "@CMAKE_CURRENT_BINARY_DIR@"
 config.test_source_root = "@CLANG_PGO_TRAINING_DATA@"
 config.target_triple = "@LLVM_TARGET_TRIPLE@"
 config.python_exe = "@Python3_EXECUTABLE@"
+config.cmake_exe = "@CMAKE_COMMAND@"
+config.llvm_src_dir ="@CMAKE_SOURCE_DIR@"
+config.cmake_generator ="@CMAKE_GENERATOR@"
 
 # Let the main config do the real work.
 lit_config.load_config(config, "@CLANG_SOURCE_DIR@/utils/perf-training/lit.cfg")
diff --git a/clang/utils/perf-training/llvm-support/build.test b/clang/utils/perf-training/llvm-support/build.test
@@ -0,0 +1,2 @@
+RUN: %cmake -G %cmake_generator -B %t -S %llvm_src_dir -DCMAKE_C_COMPILER=%clang -DCMAKE_CXX_COMPILER=%clang -DCMAKE_CXX_FLAGS="--driver-mode=g++" -DCMAKE_BUILD_TYPE=Release
+RUN: %cmake --build %t -v --target LLVMSupport
diff --git a/clang/www/c_status.html b/clang/www/c_status.html
@@ -191,12 +191,12 @@ <h2 id="c2y">C2y implementation status</h2>
     <tr>
       <td>Slay Some Earthly Demons III</td>
       <td><a href="https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3341.pdf">N3341</a></td>
-      <td class="unknown" align="center">Unknown</td>
+      <td class="full" align="center">Yes</td>
     </tr>
     <tr>
       <td>Slay Some Earthly Demons IV</td>
       <td><a href="https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3342.pdf">N3342</a></td>
-      <td class="unknown" align="center">Unknown</td>
+      <td class="full" align="center">Yes</td>
     </tr>
     <tr>
       <td>Slay Some Earthly Demons VI</td>
@@ -211,7 +211,7 @@ <h2 id="c2y">C2y implementation status</h2>
     <tr>
       <td>Slay Some Earthly Demons VIII</td>
       <td><a href="https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3346.pdf">N3346</a></td>
-      <td class="unknown" align="center">Unknown</td>
+      <td class="full" align="center">Yes</td>
     </tr>
     <tr>
       <td>Introduce complex literals v. 2</td>

diff --git a/compiler-rt/cmake/Modules/AddCompilerRT.cmake b/compiler-rt/cmake/Modules/AddCompilerRT.cmake
@@ -713,6 +713,9 @@ macro(add_custom_libcxx name prefix)
     USES_TERMINAL_INSTALL 1
     LIST_SEPARATOR |
     EXCLUDE_FROM_ALL TRUE
+    # Ensure that DESTDIR=... set in the out environment does not affect this
+    # target (we always need to install to the build directory).
+    INSTALL_COMMAND env DESTDIR= ${CMAKE_COMMAND} --build ${prefix}/build --target install
     INSTALL_BYPRODUCTS "${prefix}/lib/libc++.a" "${prefix}/lib/libc++abi.a"
     )
 

diff --git a/flang/include/flang/Parser/dump-parse-tree.h b/flang/include/flang/Parser/dump-parse-tree.h
@@ -177,6 +177,7 @@ class ParseTreeDumper {
   NODE(parser, Call)
   NODE(parser, CallStmt)
   NODE(CallStmt, Chevrons)
+  NODE(CallStmt, StarOrExpr)
   NODE(parser, CaseConstruct)
   NODE(CaseConstruct, Case)
   NODE(parser, CaseSelector)

diff --git a/flang/include/flang/Parser/parse-tree.h b/flang/include/flang/Parser/parse-tree.h
@@ -3247,13 +3247,14 @@ struct FunctionReference {
 
 // R1521 call-stmt -> CALL procedure-designator [ chevrons ]
 //         [( [actual-arg-spec-list] )]
-// (CUDA) chevrons -> <<< scalar-expr, scalar-expr [,
+// (CUDA) chevrons -> <<< * | scalar-expr, scalar-expr [,
 //          scalar-int-expr [, scalar-int-expr ] ] >>>
 struct CallStmt {
   BOILERPLATE(CallStmt);
+  WRAPPER_CLASS(StarOrExpr, std::optional<ScalarExpr>);
   struct Chevrons {
     TUPLE_CLASS_BOILERPLATE(Chevrons);
-    std::tuple<ScalarExpr, ScalarExpr, std::optional<ScalarIntExpr>,
+    std::tuple<StarOrExpr, ScalarExpr, std::optional<ScalarIntExpr>,
         std::optional<ScalarIntExpr>>
         t;
   };
@@ -3694,9 +3695,8 @@ struct OmpMapClause {
 
 // 2.9.5 order-clause -> ORDER ([order-modifier :]concurrent)
 struct OmpOrderModifier {
-  UNION_CLASS_BOILERPLATE(OmpOrderModifier);
   ENUM_CLASS(Kind, Reproducible, Unconstrained)
-  std::variant<Kind> u;
+  WRAPPER_CLASS_BOILERPLATE(OmpOrderModifier, Kind);
 };
 
 struct OmpOrderClause {

diff --git a/flang/lib/Lower/OpenMP/Clauses.cpp b/flang/lib/Lower/OpenMP/Clauses.cpp
@@ -1092,8 +1092,7 @@ Order make(const parser::OmpClause::Order &inp,
   auto &t1 = std::get<wrapped::Type>(inp.v.t);
 
   auto convert3 = [&](const parser::OmpOrderModifier &s) {
-    return Fortran::common::visit(
-        [&](parser::OmpOrderModifier::Kind k) { return convert1(k); }, s.u);
+    return convert1(s.v);
   };
   return Order{
       {/*OrderModifier=*/maybeApply(convert3, t0), /*Ordering=*/convert2(t1)}};

diff --git a/flang/lib/Optimizer/Transforms/CUFOpConversion.cpp b/flang/lib/Optimizer/Transforms/CUFOpConversion.cpp
@@ -337,6 +337,13 @@ struct CUFAllocOpConversion : public mlir::OpRewritePattern<cuf::AllocOp> {
                                                  seqTy.getConstantArraySize());
         }
         bytes = rewriter.create<mlir::arith::MulIOp>(loc, nbElem, width);
+      } else if (fir::isa_derived(op.getInType())) {
+        mlir::Type structTy = typeConverter->convertType(op.getInType());
+        std::size_t structSize = dl->getTypeSizeInBits(structTy) / 8;
+        bytes = builder.createIntegerConstant(loc, builder.getIndexType(),
+                                              structSize);
+      } else {
+        mlir::emitError(loc, "unsupported type in cuf.alloc\n");
       }
       mlir::func::FuncOp func =
           fir::runtime::getRuntimeFunc<mkRTKey(CUFMemAlloc)>(loc, builder);

diff --git a/flang/lib/Parser/program-parsers.cpp b/flang/lib/Parser/program-parsers.cpp
@@ -474,10 +474,13 @@ TYPE_CONTEXT_PARSER("function reference"_en_US,
 
 // R1521 call-stmt -> CALL procedure-designator [chevrons]
 ///                          [( [actual-arg-spec-list] )]
-// (CUDA) chevrons -> <<< scalar-expr, scalar-expr [, scalar-int-expr
+// (CUDA) chevrons -> <<< * | scalar-expr, scalar-expr [, scalar-int-expr
 //                      [, scalar-int-expr ] ] >>>
+constexpr auto starOrExpr{
+    construct<CallStmt::StarOrExpr>("*" >> pure<std::optional<ScalarExpr>>() ||
+        applyFunction(presentOptional<ScalarExpr>, scalarExpr))};
 TYPE_PARSER(extension<LanguageFeature::CUDA>(
-    "<<<" >> construct<CallStmt::Chevrons>(scalarExpr, "," >> scalarExpr,
+    "<<<" >> construct<CallStmt::Chevrons>(starOrExpr, ", " >> scalarExpr,
                  maybe("," >> scalarIntExpr), maybe("," >> scalarIntExpr)) /
         ">>>"))
 constexpr auto actualArgSpecList{optionalList(actualArgSpec)};

diff --git a/flang/lib/Parser/unparse.cpp b/flang/lib/Parser/unparse.cpp
@@ -1703,6 +1703,13 @@ class UnparseVisitor {
   void Unparse(const IntrinsicStmt &x) { // R1519
     Word("INTRINSIC :: "), Walk(x.v, ", ");
   }
+  void Unparse(const CallStmt::StarOrExpr &x) {
+    if (x.v) {
+      Walk(*x.v);
+    } else {
+      Word("*");
+    }
+  }
   void Unparse(const CallStmt::Chevrons &x) { // CUDA
     Walk(std::get<0>(x.t)); // grid
     Word(","), Walk(std::get<1>(x.t)); // block

diff --git a/flang/lib/Semantics/expression.cpp b/flang/lib/Semantics/expression.cpp
@@ -3066,11 +3066,17 @@ std::optional<Chevrons> ExpressionAnalyzer::AnalyzeChevrons(
     return false;
   }};
   if (const auto &chevrons{call.chevrons}) {
-    if (auto expr{Analyze(std::get<0>(chevrons->t))};
-        expr && checkLaunchArg(*expr, "grid")) {
-      result.emplace_back(*expr);
+    auto &starOrExpr{std::get<0>(chevrons->t)};
+    if (starOrExpr.v) {
+      if (auto expr{Analyze(*starOrExpr.v)};
+          expr && checkLaunchArg(*expr, "grid")) {
+        result.emplace_back(*expr);
+      } else {
+        return std::nullopt;
+      }
     } else {
-      return std::nullopt;
+      result.emplace_back(
+          AsGenericExpr(evaluate::Constant<evaluate::CInteger>{-1}));
     }
     if (auto expr{Analyze(std::get<1>(chevrons->t))};
         expr && checkLaunchArg(*expr, "block")) {
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		RUN: %cmake -G %cmake_generator -B %t -S %llvm_src_dir -DCMAKE_C_COMPILER=%clang -DCMAKE_CXX_COMPILER=%clang -DCMAKE_CXX_FLAGS="--driver-mode=g++" -DCMAKE_BUILD_TYPE=Release
		RUN: %cmake --build %t -v --target LLVMSupport