Gpu known subgroup size

.github/new-prs-labeler.yml

@@ -69,7 +69,7 @@ PGO:
   - llvm/**/llvm-profdata/**/*
   - llvm/**/llvm-profgen/**/*
 
-vectorization:
+vectorizers:
   - llvm/lib/Transforms/Vectorize/**/*
   - llvm/include/llvm/Transforms/Vectorize/**/*
 

.github/workflows/release-binaries.yml

@@ -328,7 +328,7 @@ jobs:
       run: |
         # Build some of the mlir tools that take a long time to link
         if [ "${{ needs.prepare.outputs.build-flang }}" = "true" ]; then
-          ninja -C ${{ steps.setup-stage.outputs.build-prefix }}/build/tools/clang/stage2-bins/ -j2 flang-new bbc
+          ninja -C ${{ steps.setup-stage.outputs.build-prefix }}/build/tools/clang/stage2-bins/ -j2 flang bbc
         fi
         ninja -C ${{ steps.setup-stage.outputs.build-prefix }}/build/tools/clang/stage2-bins/ \
             mlir-bytecode-parser-fuzzer \

bolt/lib/Profile/YAMLProfileReader.cpp

@@ -643,11 +643,7 @@ size_t YAMLProfileReader::matchWithNameSimilarity(BinaryContext &BC) {
     // equal number of blocks.
     if (NamespaceToProfiledBFSizesIt->second.count(BF->size()) == 0)
       continue;
-    auto NamespaceToBFsIt = NamespaceToBFs.find(Namespace);
-    if (NamespaceToBFsIt == NamespaceToBFs.end())
-      NamespaceToBFs[Namespace] = {BF};
-    else
-      NamespaceToBFsIt->second.push_back(BF);
+    NamespaceToBFs[Namespace].push_back(BF);
   }
 
   // Iterates through all profiled functions and binary functions belonging to

clang-tools-extra/clang-tidy/cppcoreguidelines/ProTypeMemberInitCheck.cpp

@@ -474,10 +474,8 @@ void ProTypeMemberInitCheck::checkMissingMemberInitializer(
   // It only includes fields that have not been fixed
   SmallPtrSet<const FieldDecl *, 16> AllFieldsToInit;
   forEachField(ClassDecl, FieldsToInit, [&](const FieldDecl *F) {
-    if (!HasRecordClassMemberSet.contains(F)) {
+    if (HasRecordClassMemberSet.insert(F).second)
       AllFieldsToInit.insert(F);
-      HasRecordClassMemberSet.insert(F);
-    }
   });
   if (FieldsToInit.empty())
     return;

clang-tools-extra/clang-tidy/performance/MoveConstArgCheck.cpp

@@ -209,8 +209,9 @@ void MoveConstArgCheck::check(const MatchFinder::MatchResult &Result) {
     }
 
     if (const CXXRecordDecl *RecordDecl = ArgType->getAsCXXRecordDecl();
-        RecordDecl && !(RecordDecl->hasMoveConstructor() &&
-                        RecordDecl->hasMoveAssignment())) {
+        RecordDecl && RecordDecl->hasDefinition() &&
+        !(RecordDecl->hasMoveConstructor() &&
+          RecordDecl->hasMoveAssignment())) {
       const bool MissingMoveAssignment = !RecordDecl->hasMoveAssignment();
       const bool MissingMoveConstructor = !RecordDecl->hasMoveConstructor();
       const bool MissingBoth = MissingMoveAssignment && MissingMoveConstructor;

clang-tools-extra/clang-tidy/rename_check.py

@@ -8,16 +8,16 @@
 #
 # ===-----------------------------------------------------------------------===#
 
-from __future__ import unicode_literals
-
 import argparse
 import glob
 import io
 import os
 import re
+import sys
+from typing import List
 
 
-def replaceInFileRegex(fileName, sFrom, sTo):
+def replaceInFileRegex(fileName: str, sFrom: str, sTo: str) -> None:
     if sFrom == sTo:
         return
 
@@ -35,7 +35,7 @@ def replaceInFileRegex(fileName, sFrom, sTo):
         f.write(txt)
 
 
-def replaceInFile(fileName, sFrom, sTo):
+def replaceInFile(fileName: str, sFrom: str, sTo: str) -> None:
     if sFrom == sTo:
         return
     txt = None
@@ -51,7 +51,7 @@ def replaceInFile(fileName, sFrom, sTo):
         f.write(txt)
 
 
-def generateCommentLineHeader(filename):
+def generateCommentLineHeader(filename: str) -> str:
     return "".join(
         [
             "//===--- ",
@@ -63,7 +63,7 @@ def generateCommentLineHeader(filename):
     )
 
 
-def generateCommentLineSource(filename):
+def generateCommentLineSource(filename: str) -> str:
     return "".join(
         [
             "//===--- ",
@@ -75,7 +75,7 @@ def generateCommentLineSource(filename):
     )
 
 
-def fileRename(fileName, sFrom, sTo):
+def fileRename(fileName: str, sFrom: str, sTo: str) -> str:
     if sFrom not in fileName or sFrom == sTo:
         return fileName
     newFileName = fileName.replace(sFrom, sTo)
@@ -84,7 +84,7 @@ def fileRename(fileName, sFrom, sTo):
     return newFileName
 
 
-def deleteMatchingLines(fileName, pattern):
+def deleteMatchingLines(fileName: str, pattern: str) -> bool:
     lines = None
     with io.open(fileName, "r", encoding="utf8") as f:
         lines = f.readlines()
@@ -101,7 +101,7 @@ def deleteMatchingLines(fileName, pattern):
     return True
 
 
-def getListOfFiles(clang_tidy_path):
+def getListOfFiles(clang_tidy_path: str) -> List[str]:
     files = glob.glob(os.path.join(clang_tidy_path, "**"), recursive=True)
     files += [
         os.path.normpath(os.path.join(clang_tidy_path, "../docs/ReleaseNotes.rst"))
@@ -124,7 +124,7 @@ def getListOfFiles(clang_tidy_path):
 
 # Adapts the module's CMakelist file. Returns 'True' if it could add a new
 # entry and 'False' if the entry already existed.
-def adapt_cmake(module_path, check_name_camel):
+def adapt_cmake(module_path: str, check_name_camel: str) -> bool:
     filename = os.path.join(module_path, "CMakeLists.txt")
     with io.open(filename, "r", encoding="utf8") as f:
         lines = f.readlines()
@@ -153,7 +153,9 @@ def adapt_cmake(module_path, check_name_camel):
 
 
 # Modifies the module to include the new check.
-def adapt_module(module_path, module, check_name, check_name_camel):
+def adapt_module(
+    module_path: str, module: str, check_name: str, check_name_camel: str
+) -> None:
     modulecpp = next(
         iter(
             filter(
@@ -204,7 +206,9 @@ def adapt_module(module_path, module, check_name, check_name_camel):
 
 
 # Adds a release notes entry.
-def add_release_notes(clang_tidy_path, old_check_name, new_check_name):
+def add_release_notes(
+    clang_tidy_path: str, old_check_name: str, new_check_name: str
+) -> None:
     filename = os.path.normpath(
         os.path.join(clang_tidy_path, "../docs/ReleaseNotes.rst")
     )
@@ -262,7 +266,7 @@ def add_release_notes(clang_tidy_path, old_check_name, new_check_name):
             f.write(line)
 
 
-def main():
+def main() -> None:
     parser = argparse.ArgumentParser(description="Rename clang-tidy check.")
     parser.add_argument("old_check_name", type=str, help="Old check name.")
     parser.add_argument("new_check_name", type=str, help="New check name.")
@@ -311,7 +315,7 @@ def main():
                 "Check name '%s' not found in %s. Exiting."
                 % (check_name_camel, cmake_lists)
             )
-            return 1
+            sys.exit(1)
 
         modulecpp = next(
             iter(

clang-tools-extra/docs/ReleaseNotes.rst

@@ -210,6 +210,10 @@ Changes in existing checks
   <clang-tidy/checks/performance/avoid-endl>` check to use ``std::endl`` as
   placeholder when lexer cannot get source text.
 
+- Improved :doc:`performance-move-const-arg
+  <clang-tidy/checks/performance/move-const-arg>` check to fix a crash when
+  an argument type is declared but not defined.
+
 - Improved :doc:`readability-container-contains
   <clang-tidy/checks/readability/container-contains>` check to let it work on
   any class that has a ``contains`` method.

clang-tools-extra/test/clang-tidy/checkers/performance/move-const-arg.cpp

@@ -546,3 +546,17 @@ void testAlsoNonMoveable() {
 }
 
 } // namespace issue_62550
+
+namespace GH111450 {
+struct Status;
+
+struct Error {
+    Error(const Status& S);
+};
+
+struct Result {
+  Error E;
+  Result(Status&& S) : E(std::move(S)) {}
+  // CHECK-MESSAGES: :[[@LINE-1]]:{{[0-9]+}}: warning: passing result of std::move() as a const reference argument; no move will actually happen [performance-move-const-arg]
+};
+} // namespace GH111450

clang/docs/ReleaseNotes.rst

@@ -174,6 +174,10 @@ C++23 Feature Support
 C++20 Feature Support
 ^^^^^^^^^^^^^^^^^^^^^
 
+C++17 Feature Support
+^^^^^^^^^^^^^^^^^^^^^
+- The implementation of the relaxed template template argument matching rules is
+  more complete and reliable, and should provide more accurate diagnostics.
 
 Resolutions to C++ Defect Reports
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -200,7 +204,8 @@ Resolutions to C++ Defect Reports
   (`CWG2351: void{} <https://cplusplus.github.io/CWG/issues/2351.html>`_).
 
 - Clang now has improved resolution to CWG2398, allowing class templates to have
-  default arguments deduced when partial ordering.
+  default arguments deduced when partial ordering, and better backwards compatibility
+  in overload resolution.
 
 - Clang now allows comparing unequal object pointers that have been cast to ``void *``
   in constant expressions. These comparisons always worked in non-constant expressions.
@@ -331,6 +336,10 @@ Improvements to Clang's diagnostics
 
 - Clang now diagnoses when the result of a [[nodiscard]] function is discarded after being cast in C. Fixes #GH104391.
 
+- Clang now properly explains the reason a template template argument failed to
+  match a template template parameter, in terms of the C++17 relaxed matching rules
+  instead of the old ones.
+
 - Don't emit duplicated dangling diagnostics. (#GH93386).
 
 - Improved diagnostic when trying to befriend a concept. (#GH45182).
@@ -440,6 +449,8 @@ Bug Fixes to C++ Support
 - Correctly check constraints of explicit instantiations of member functions. (#GH46029)
 - When performing partial ordering of function templates, clang now checks that
   the deduction was consistent. Fixes (#GH18291).
+- Fixes to several issues in partial ordering of template template parameters, which
+  were documented in the test suite.
 - Fixed an assertion failure about a constraint of a friend function template references to a value with greater
   template depth than the friend function template. (#GH98258)
 - Clang now rebuilds the template parameters of out-of-line declarations and specializations in the context
@@ -468,7 +479,6 @@ Bug Fixes to C++ Support
 - Fixed an assertion failure in debug mode, and potential crashes in release mode, when
   diagnosing a failed cast caused indirectly by a failed implicit conversion to the type of the constructor parameter.
 - Fixed an assertion failure by adjusting integral to boolean vector conversions (#GH108326)
-- Clang is now better at keeping track of friend function template instance contexts. (#GH55509)
 - Fixed an issue deducing non-type template arguments of reference type. (#GH73460)
 - Fixed an issue in constraint evaluation, where type constraints on the lambda expression
   containing outer unexpanded parameters were not correctly expanded. (#GH101754)
@@ -478,9 +488,9 @@ Bug Fixes to C++ Support
   in certain friend declarations. (#GH93099)
 - Clang now instantiates the correct lambda call operator when a lambda's class type is
   merged across modules. (#GH110401)
-- Clang now uses the correct set of template argument lists when comparing the constraints of
-  out-of-line definitions and member templates explicitly specialized for a given implicit instantiation of
-  a class template. (#GH102320)
+- Fix a crash when parsing a pseudo destructor involving an invalid type. (#GH111460)
+- Fixed an assertion failure when invoking recovery call expressions with explicit attributes
+  and undeclared templates. (#GH107047, #GH49093)
 
 Bug Fixes to AST Handling
 ^^^^^^^^^^^^^^^^^^^^^^^^^

clang/include/clang/AST/Decl.h

@@ -2299,13 +2299,6 @@ class FunctionDecl : public DeclaratorDecl,
     FunctionDeclBits.IsLateTemplateParsed = ILT;
   }
 
-  bool isInstantiatedFromMemberTemplate() const {
-    return FunctionDeclBits.IsInstantiatedFromMemberTemplate;
-  }
-  void setInstantiatedFromMemberTemplate(bool Val = true) {
-    FunctionDeclBits.IsInstantiatedFromMemberTemplate = Val;
-  }
-
   /// Whether this function is "trivial" in some specialized C++ senses.
   /// Can only be true for default constructors, copy constructors,
   /// copy assignment operators, and destructors.  Not meaningful until

clang/include/clang/AST/DeclBase.h

@@ -687,6 +687,9 @@ class alignas(8) Decl {
   /// Whether this declaration comes from a named module.
   bool isInNamedModule() const;
 
+  /// Whether this declaration comes from a header unit.
+  bool isFromHeaderUnit() const;
+
   /// Return true if this declaration has an attribute which acts as
   /// definition of the entity, such as 'alias' or 'ifunc'.
   bool hasDefiningAttr() const;
@@ -1763,8 +1766,6 @@ class DeclContext {
     uint64_t HasImplicitReturnZero : 1;
     LLVM_PREFERRED_TYPE(bool)
     uint64_t IsLateTemplateParsed : 1;
-    LLVM_PREFERRED_TYPE(bool)
-    uint64_t IsInstantiatedFromMemberTemplate : 1;
 
     /// Kind of contexpr specifier as defined by ConstexprSpecKind.
     LLVM_PREFERRED_TYPE(ConstexprSpecKind)
@@ -1815,7 +1816,7 @@ class DeclContext {
   };
 
   /// Number of inherited and non-inherited bits in FunctionDeclBitfields.
-  enum { NumFunctionDeclBits = NumDeclContextBits + 32 };
+  enum { NumFunctionDeclBits = NumDeclContextBits + 31 };
 
   /// Stores the bits used by CXXConstructorDecl. If modified
   /// NumCXXConstructorDeclBits and the accessor
@@ -1826,12 +1827,12 @@ class DeclContext {
     LLVM_PREFERRED_TYPE(FunctionDeclBitfields)
     uint64_t : NumFunctionDeclBits;
 
-    /// 19 bits to fit in the remaining available space.
+    /// 20 bits to fit in the remaining available space.
     /// Note that this makes CXXConstructorDeclBitfields take
     /// exactly 64 bits and thus the width of NumCtorInitializers
     /// will need to be shrunk if some bit is added to NumDeclContextBitfields,
     /// NumFunctionDeclBitfields or CXXConstructorDeclBitfields.
-    uint64_t NumCtorInitializers : 16;
+    uint64_t NumCtorInitializers : 17;
     LLVM_PREFERRED_TYPE(bool)
     uint64_t IsInheritingConstructor : 1;
 
@@ -1845,7 +1846,7 @@ class DeclContext {
   };
 
   /// Number of inherited and non-inherited bits in CXXConstructorDeclBitfields.
-  enum { NumCXXConstructorDeclBits = NumFunctionDeclBits + 19 };
+  enum { NumCXXConstructorDeclBits = NumFunctionDeclBits + 20 };
 
   /// Stores the bits used by ObjCMethodDecl.
   /// If modified NumObjCMethodDeclBits and the accessor