Merge branch 'users/meinersbur/flang_runtime_shared' into users/meinersbur/flang_runtime_remove-FLANG_INCLUDE_RUNTIME

Author: Meinersbur

clang/docs/SourceBasedCodeCoverage.rst

@@ -94,6 +94,11 @@ directory structure will be created.  Additionally, the following special
   not specified (i.e the pattern is "%m"), it's assumed that ``N = 1``. The
   merge pool specifier can only occur once per filename pattern.
 
+* "%b" expands out to the binary ID (build ID). It can be used with "%Nm" to
+  avoid binary signature collisions. To use it, the program should be compiled
+  with the build ID linker option (``--build-id`` for GNU ld or LLD,
+  ``/build-id`` for lld-link on Windows). Linux, Windows and AIX are supported.
+
 * "%c" expands out to nothing, but enables a mode in which profile counter
   updates are continuously synced to a file. This means that if the
   instrumented program crashes, or is killed by a signal, perfect coverage

clang/docs/UsersManual.rst

@@ -2965,7 +2965,8 @@ instrumentation:
    environment variable to specify an alternate file. If non-default file name
    is specified by both the environment variable and the command line option,
    the environment variable takes precedence. The file name pattern specified
-   can include different modifiers: ``%p``, ``%h``, ``%m``, ``%t``, and ``%c``.
+   can include different modifiers: ``%p``, ``%h``, ``%m``, ``%b``, ``%t``, and
+   ``%c``.
 
    Any instance of ``%p`` in that file name will be replaced by the process
    ID, so that you can easily distinguish the profile output from multiple
@@ -2987,11 +2988,11 @@ instrumentation:
    ``%p`` is that the storage requirement for raw profile data files is greatly
    increased.  To avoid issues like this, the ``%m`` specifier can used in the profile
    name.  When this specifier is used, the profiler runtime will substitute ``%m``
-   with a unique integer identifier associated with the instrumented binary. Additionally,
+   with an integer identifier associated with the instrumented binary. Additionally,
    multiple raw profiles dumped from different processes that share a file system (can be
    on different hosts) will be automatically merged by the profiler runtime during the
    dumping. If the program links in multiple instrumented shared libraries, each library
-   will dump the profile data into its own profile data file (with its unique integer
+   will dump the profile data into its own profile data file (with its integer
    id embedded in the profile name). Note that the merging enabled by ``%m`` is for raw
    profile data generated by profiler runtime. The resulting merged "raw" profile data
    file still needs to be converted to a different format expected by the compiler (
@@ -3001,6 +3002,12 @@ instrumentation:
 
      $ LLVM_PROFILE_FILE="code-%m.profraw" ./code
 
+   Although rare, binary signatures used by the ``%m`` specifier can have
+   collisions. In this case, the ``%b`` specifier, which expands to the binary
+   ID (build ID in ELF and COFF), can be added. To use it, the program should be
+   compiled with the build ID linker option (``--build-id`` for GNU ld or LLD,
+   ``/build-id`` for lld-link on Windows). Linux, Windows and AIX are supported.
+
    See `this <SourceBasedCodeCoverage.html#running-the-instrumented-program>`_ section
    about the ``%t``, and ``%c`` modifiers.
 

clang/include/clang/AST/OperationKinds.def

@@ -367,6 +367,9 @@ CAST_OPERATION(HLSLVectorTruncation)
 // Non-decaying array RValue cast (HLSL only).
 CAST_OPERATION(HLSLArrayRValue)
 
+// Aggregate by Value cast (HLSL only).
+CAST_OPERATION(HLSLElementwiseCast)
+
 //===- Binary Operations  -------------------------------------------------===//
 // Operators listed in order of precedence.
 // Note that additions to this should also update the StmtVisitor class,

clang/include/clang/Basic/BuiltinsSME.def

@@ -797,22 +797,14 @@ class Driver {
   const ToolChain &getToolChain(const llvm::opt::ArgList &Args,
                                 const llvm::Triple &Target) const;
 
-  /// @}
-
-  /// Retrieves a ToolChain for a particular device \p Target triple
-  ///
-  /// \param[in] HostTC is the host ToolChain paired with the device
-  ///
-  /// \param[in] TargetDeviceOffloadKind (e.g. OFK_Cuda/OFK_OpenMP/OFK_SYCL) is
-  /// an Offloading action that is optionally passed to a ToolChain (used by
-  /// CUDA, to specify if it's used in conjunction with OpenMP)
+  /// Retrieves a ToolChain for a particular \p Target triple for offloading.
   ///
   /// Will cache ToolChains for the life of the driver object, and create them
   /// on-demand.
-  const ToolChain &getOffloadingDeviceToolChain(
-      const llvm::opt::ArgList &Args, const llvm::Triple &Target,
-      const ToolChain &HostTC,
-      const Action::OffloadKind &TargetDeviceOffloadKind) const;
+  const ToolChain &getOffloadToolChain(const llvm::opt::ArgList &Args,
+                                       const Action::OffloadKind Kind,
+                                       const llvm::Triple &Target,
+                                       const llvm::Triple &AuxTarget) const;
 
   /// Get bitmasks for which option flags to include and exclude based on
   /// the driver mode.

clang/include/clang/Basic/BuiltinsSVE.def

@@ -141,6 +141,9 @@ class SemaHLSL : public SemaBase {
   // Diagnose whether the input ID is uint/unit2/uint3 type.
   bool diagnoseInputIDType(QualType T, const ParsedAttr &AL);
 
+  bool CanPerformScalarCast(QualType SrcTy, QualType DestTy);
+  bool ContainsBitField(QualType BaseTy);
+  bool CanPerformElementwiseCast(Expr *Src, QualType DestType);
   ExprResult ActOnOutParamExpr(ParmVarDecl *Param, Expr *Arg);
 
   QualType getInoutParameterType(QualType Ty);

clang/include/clang/Driver/Driver.h

@@ -49,11 +49,7 @@ module Clang_Basic {
   textual header "clang/Basic/BuiltinsLoongArchLASX.def"
   textual header "clang/Basic/BuiltinsLoongArchLSX.def"
   textual header "clang/Basic/BuiltinsMips.def"
-  textual header "clang/Basic/BuiltinsNEON.def"
   textual header "clang/Basic/BuiltinsPPC.def"
-  textual header "clang/Basic/BuiltinsRISCVVector.def"
-  textual header "clang/Basic/BuiltinsSME.def"
-  textual header "clang/Basic/BuiltinsSVE.def"
   textual header "clang/Basic/BuiltinsSystemZ.def"
   textual header "clang/Basic/BuiltinsVE.def"
   textual header "clang/Basic/BuiltinsVEVL.gen.def"

clang/include/clang/Sema/SemaHLSL.h

@@ -1956,6 +1956,7 @@ bool CastExpr::CastConsistency() const {
   case CK_FixedPointToBoolean:
   case CK_HLSLArrayRValue:
   case CK_HLSLVectorTruncation:
+  case CK_HLSLElementwiseCast:
   CheckNoBasePath:
     assert(path_empty() && "Cast kind should not have a base path!");
     break;

clang/include/module.modulemap

@@ -15047,6 +15047,7 @@ bool IntExprEvaluator::VisitCastExpr(const CastExpr *E) {
   case CK_NoOp:
   case CK_LValueToRValueBitCast:
   case CK_HLSLArrayRValue:
+  case CK_HLSLElementwiseCast:
     return ExprEvaluatorBaseTy::VisitCastExpr(E);
 
   case CK_MemberPointerToBoolean:
@@ -15905,6 +15906,7 @@ bool ComplexExprEvaluator::VisitCastExpr(const CastExpr *E) {
   case CK_IntegralToFixedPoint:
   case CK_MatrixCast:
   case CK_HLSLVectorTruncation:
+  case CK_HLSLElementwiseCast:
     llvm_unreachable("invalid cast kind for complex value");
 
   case CK_LValueToRValue: