Merge branch 'main' into himadhith/xxleqv_vec

Author: Himadhith

.ci/metrics/metrics.py

@@ -40,6 +40,7 @@
 GITHUB_JOB_TO_TRACK = {
     "github_llvm_premerge_checks": {
         "Build and Test Linux": "premerge_linux",
+        "Build and Test Linux AArch64": "premerge_linux_aarch64",
         "Build and Test Windows": "premerge_windows",
     },
     "github_libcxx_premerge_checks": {

.github/workflows/containers/github-action-ci/Dockerfile

@@ -2,7 +2,7 @@ FROM docker.io/library/ubuntu:24.04 AS base
 ENV LLVM_SYSROOT=/opt/llvm
 
 FROM base AS stage1-toolchain
-ENV LLVM_VERSION=21.1.1
+ENV LLVM_VERSION=21.1.3
 
 RUN apt-get update && \
     apt-get install -y \

bolt/docs/BinaryAnalysis.md

@@ -1,7 +1,7 @@
 # BOLT-based binary analysis
 
 As part of post-link-time optimizing, BOLT needs to perform a range of analyses
-on binaries such as recontructing control flow graphs, and more.
+on binaries such as reconstructing control flow graphs, and more.
 
 The `llvm-bolt-binary-analysis` tool enables running requested binary analyses
 on binaries, and generating reports. It does this by building on top of the

bolt/docs/CommandLineArgumentReference.md

@@ -375,7 +375,7 @@
 
 - `--use-old-text`
 
-  Re-use space in old .text if possible (relocation mode)
+  Reuse space in old .text if possible (relocation mode)
 
 - `-v <uint>`
 

bolt/docs/RuntimeLibrary.md

@@ -15,7 +15,7 @@ However, this approach quickly becomes awkward if we want to insert a lot of cod
 Currently, our runtime library is written in C++ and contains code that helps us instrument a binary.
 
 ### Limitations
-Our library is not written with regular C++ code as it is not linked against any other libraries (this means we cannnot rely on anything defined on libstdc++, glibc, libgcc etc), but is self sufficient. In runtime/CMakeLists.txt, we can see it is built with -ffreestanding, which requires the compiler to avoid using a runtime library by itself.
+Our library is not written with regular C++ code as it is not linked against any other libraries (this means we cannot rely on anything defined on libstdc++, glibc, libgcc etc), but is self sufficient. In runtime/CMakeLists.txt, we can see it is built with -ffreestanding, which requires the compiler to avoid using a runtime library by itself.
 
 While this requires us to make our own syscalls, it does simplify our linker a lot, which is very limited and can only do basic function name resolving. However, this is a big improvement in comparison with programmatically generating the code in assembly language using MCInsts.
 

bolt/docs/doxygen.cfg.in

@@ -1070,7 +1070,7 @@ HTML_STYLESHEET        =
 # defined cascading style sheet that is included after the standard style sheets
 # created by doxygen. Using this option one can overrule certain style aspects.
 # This is preferred over using HTML_STYLESHEET since it does not replace the
-# standard style sheet and is therefor more robust against future updates.
+# standard style sheet and is therefore more robust against future updates.
 # Doxygen will copy the style sheet file to the output directory. For an example
 # see the documentation.
 # This tag requires that the tag GENERATE_HTML is set to YES.

bolt/include/bolt/Core/BinaryFunction.h

@@ -1336,7 +1336,7 @@ class BinaryFunction {
     ColdCodeSectionName = Name.str();
   }
 
-  /// Return true iif the function will halt execution on entry.
+  /// Return true if the function will halt execution on entry.
   bool trapsOnEntry() const { return TrapsOnEntry; }
 
   /// Make the function always trap on entry. Other than the trap instruction,

bolt/include/bolt/Core/DIEBuilder.h

@@ -60,7 +60,7 @@ class DIEBuilder {
     uint32_t UnitLength = 0;
     bool IsConstructed = false;
     // A map of DIE offsets in original DWARF section to DIE ID.
-    // Whih is used to access DieInfoVector.
+    // Which is used to access DieInfoVector.
     std::unordered_map<uint64_t, uint32_t> DIEIDMap;
 
     // Some STL implementations don't have a noexcept move constructor for

bolt/include/bolt/Core/DebugData.h

@@ -326,8 +326,8 @@ class DebugAddrWriter {
   /// Write out entries in to .debug_addr section for CUs.
   virtual std::optional<uint64_t> finalize(const size_t BufferSize);
 
-  /// Return buffer with all the entries in .debug_addr already writen out using
-  /// update(...).
+  /// Return buffer with all the entries in .debug_addr already written out
+  /// using update(...).
   virtual std::unique_ptr<AddressSectionBuffer> releaseBuffer() {
     return std::move(Buffer);
   }
@@ -409,7 +409,7 @@ class DebugAddrWriter {
   std::mutex WriterMutex;
   std::unique_ptr<AddressSectionBuffer> Buffer;
   std::unique_ptr<raw_svector_ostream> AddressStream;
-  /// Used to track sections that were not modified so that they can be re-used.
+  /// Used to track sections that were not modified so that they can be reused.
   static DenseMap<uint64_t, uint64_t> UnmodifiedAddressOffsets;
 };
 

bolt/include/bolt/Core/DebugNames.h

@@ -65,7 +65,7 @@ class DWARF5AcceleratorTable {
   void setCurrentUnit(DWARFUnit &Unit, const uint64_t UnitStartOffset);
   /// Emit Accelerator table.
   void emitAccelTable();
-  /// Returns true if the table was crated.
+  /// Returns true if the table was created.
   bool isCreated() const { return NeedToCreate; }
   /// Returns buffer containing the accelerator table.
   std::unique_ptr<DebugBufferVector> releaseBuffer() {
@@ -91,7 +91,7 @@ class DWARF5AcceleratorTable {
   uint64_t CurrentUnitOffset = 0;
   const DWARFUnit *CurrentUnit = nullptr;
   std::unordered_map<uint32_t, uint32_t> AbbrevTagToIndexMap;
-  /// Contains a map of TU hashes to a Foreign TU indecies.
+  /// Contains a map of TU hashes to a Foreign TU indices.
   /// This is used to reduce the size of Foreign TU list since there could be
   /// multiple TUs with the same hash.
   DenseMap<uint64_t, uint32_t> TUHashToIndexMap;