LLVM and SPIRV-LLVM-Translator pulldown (WW46)

LLVM: llvm/llvm-project@56daf02
SPIRV-LLVM-Translator: KhronosGroup/SPIRV-LLVM-Translator@1010efc

Author: bb-sycl

.github/new-prs-labeler.yml

@@ -1,5 +1,9 @@
 clang:dataflow:
-  - clang/**/Analysis/**/*
+  - clang/include/clang/Analysis/FlowSensitive/**/*
+  - clang/lib/Analysis/FlowSensitive/**/*
+  - clang/unittests/Analysis/FlowSensitive/**/*
+  - clang/docs/DataFlowAnalysisIntro.md
+  - clang/docs/DataFlowAnalysisIntroImages/**/*
 
 clang:frontend:
   - clang/lib/AST/**/*

.github/workflows/issue-subscriber.yml

@@ -15,8 +15,8 @@ jobs:
     steps:
       - name: Setup Automation Script
         run: |
-          curl -O -L https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/"$GITHUB_SHA"/llvm/utils/git/github-automation.py
-          curl -O -L https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/"$GITHUB_SHA"/llvm/utils/git/requirements.txt
+          curl -O -L --fail https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/"$GITHUB_SHA"/llvm/utils/git/github-automation.py
+          curl -O -L --fail https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/"$GITHUB_SHA"/llvm/utils/git/requirements.txt
           chmod a+x github-automation.py
           pip install -r requirements.txt
 

.github/workflows/pr-code-format.yml

@@ -11,14 +11,33 @@ jobs:
       - name: Fetch LLVM sources
         uses: actions/checkout@v4
         with:
-          fetch-depth: 2 # Fetches only the last 2 commits
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Checkout through merge base
+        uses: rmacklin/fetch-through-merge-base@v0
+        with:
+          base_ref: ${{ github.event.pull_request.base.ref }}
+          head_ref: ${{ github.event.pull_request.head.sha }}
+          deepen_length: 500
 
       - name: Get changed files
         id: changed-files
         uses: tj-actions/changed-files@v39
         with:
           separator: ","
-          fetch_depth: 2000 # Fetches only the last 2000 commits
+          skip_initial_fetch: true
+
+      # We need to make sure that we aren't executing/using any code from the
+      # PR for security reasons as we're using pull_request_target. Checkout
+      # the target branch with the necessary files.
+      - name: Fetch code formatting utils
+        uses: actions/checkout@v4
+        with:
+          sparse-checkout: |
+            llvm/utils/git/requirements_formatting.txt
+            llvm/utils/git/code-format-helper.py
+          sparse-checkout-cone-mode: false
+          path: code-format-tools
 
       - name: "Listed files"
         run: |
@@ -35,10 +54,10 @@ jobs:
         with:
           python-version: '3.11'
           cache: 'pip'
-          cache-dependency-path: 'llvm/utils/git/requirements_formatting.txt'
+          cache-dependency-path: 'code-format-tools/llvm/utils/git/requirements_formatting.txt'
 
       - name: Install python dependencies
-        run: pip install -r llvm/utils/git/requirements_formatting.txt
+        run: pip install -r code-format-tools/llvm/utils/git/requirements_formatting.txt
 
       - name: Run code formatter
         env:
@@ -47,7 +66,7 @@ jobs:
           END_REV: ${{ github.event.pull_request.head.sha }}
           CHANGED_FILES: ${{ steps.changed-files.outputs.all_changed_files }}
         run: |
-          python llvm/utils/git/code-format-helper.py \
+          python ./code-format-tools/llvm/utils/git/code-format-helper.py \
             --token ${{ secrets.GITHUB_TOKEN }} \
             --issue-number $GITHUB_PR_NUMBER \
             --start-rev $START_REV \

.github/workflows/pr-subscriber.yml

@@ -15,9 +15,8 @@ jobs:
     steps:
       - name: Setup Automation Script
         run: |
-          curl -O -L https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/main/llvm/utils/git/github-automation.py
-          curl -O -L https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/main/llvm/utils/git/requirements.txt
-          curl -O -L https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/main/.github/workflows/pr-subscriber-wait.py
+          curl -O -L --fail https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/main/llvm/utils/git/github-automation.py
+          curl -O -L --fail https://raw.githubusercontent.com/"$GITHUB_REPOSITORY"/main/llvm/utils/git/requirements.txt
           chmod a+x github-automation.py
           pip install -r requirements.txt
 

bolt/docs/doxygen.cfg.in

@@ -1954,7 +1954,7 @@ PREDEFINED             =
 EXPAND_AS_DEFINED      =
 
 # If the SKIP_FUNCTION_MACROS tag is set to YES then doxygen's preprocessor will
-# remove all refrences to function-like macros that are alone on a line, have an
+# remove all references to function-like macros that are alone on a line, have an
 # all uppercase name, and do not end with a semicolon. Such function macros are
 # typically used for boiler-plate code, and will confuse the parser if not
 # removed.

bolt/include/bolt/Core/BinaryContext.h

@@ -950,7 +950,7 @@ class BinaryContext {
   bool registerFragment(BinaryFunction &TargetFunction,
                         BinaryFunction &Function) const;
 
-  /// Add unterprocedural reference for \p Function to \p Address
+  /// Add interprocedural reference for \p Function to \p Address
   void addInterproceduralReference(BinaryFunction *Function, uint64_t Address) {
     InterproceduralReferences.push_back({Function, Address});
   }
@@ -1239,8 +1239,8 @@ class BinaryContext {
   uint64_t
   computeInstructionSize(const MCInst &Inst,
                          const MCCodeEmitter *Emitter = nullptr) const {
-    if (auto Size = MIB->getAnnotationWithDefault<uint32_t>(Inst, "Size"))
-      return Size;
+    if (std::optional<uint32_t> Size = MIB->getSize(Inst))
+      return *Size;
 
     if (!Emitter)
       Emitter = this->MCE.get();

bolt/include/bolt/Core/BinaryFunction.h

@@ -319,10 +319,6 @@ class BinaryFunction {
   /// Execution halts whenever this function is entered.
   bool TrapsOnEntry{false};
 
-  /// True if the function had an indirect branch with a fixed internal
-  /// destination.
-  bool HasFixedIndirectBranch{false};
-
   /// True if the function is a fragment of another function. This means that
   /// this function could only be entered via its parent or one of its sibling
   /// fragments. It could be entered at any basic block. It can also return
@@ -1445,7 +1441,8 @@ class BinaryFunction {
 
   /// Rebuilds BBs layout, ignoring dead BBs. Returns the number of removed
   /// BBs and the removed number of bytes of code.
-  std::pair<unsigned, uint64_t> eraseInvalidBBs();
+  std::pair<unsigned, uint64_t>
+  eraseInvalidBBs(const MCCodeEmitter *Emitter = nullptr);
 
   /// Get the relative order between two basic blocks in the original
   /// layout.  The result is > 0 if B occurs before A and < 0 if B
@@ -2172,7 +2169,7 @@ class BinaryFunction {
   /// is corrupted. If it is unable to fix it, it returns false.
   bool finalizeCFIState();
 
-  /// Return true if this function needs an address-transaltion table after
+  /// Return true if this function needs an address-translation table after
   /// its code emission.
   bool requiresAddressTranslation() const;
 

bolt/include/bolt/Core/BinarySection.h

@@ -127,7 +127,7 @@ class BinarySection {
     return *ContentsOrErr;
   }
 
-  /// Get the set of relocations refering to data in this section that
+  /// Get the set of relocations referring to data in this section that
   /// has been reordered.  The relocation offsets will be modified to
   /// reflect the new data locations.
   RelocationSetType reorderRelocations(bool Inplace) const;

bolt/include/bolt/Core/DebugData.h

@@ -64,7 +64,7 @@ std::optional<AttrInfo> findAttributeInfo(const DWARFDie DIE,
                                           dwarf::Attribute Attr);
 
 // DWARF5 Header in order of encoding.
-// Types represent encodnig sizes.
+// Types represent encoding sizes.
 using UnitLengthType = uint32_t;
 using VersionType = uint16_t;
 using AddressSizeType = uint8_t;
@@ -372,13 +372,13 @@ class DebugAddrWriter {
     }
 
     /// Updates AddressToIndex Map.
-    /// Follows the same symantics as unordered map [].
+    /// Follows the same semantics as unordered map [].
     void updateAddressToIndex(uint64_t Address, uint32_t Index) {
       AddressToIndex[Address] = Index;
     }
 
     /// Updates IndexToAddress Map.
-    /// Follows the same symantics as unordered map [].
+    /// Follows the same semantics as unordered map [].
     void updateIndexToAddrss(uint64_t Address, uint32_t Index) {
       IndexToAddress[Index] = Address;
     }
@@ -474,7 +474,7 @@ class DebugStrWriter {
   }
 
   /// Adds string to .debug_str.
-  /// On first invokation it initializes internal data stractures.
+  /// On first invocation it initializes internal data structures.
   uint32_t addString(StringRef Str);
 
   /// Returns False if no strings were added to .debug_str.
@@ -485,7 +485,7 @@ class DebugStrWriter {
   std::mutex WriterMutex;
   /// Initializes Buffer and Stream.
   void initialize();
-  /// Creats internal data stractures.
+  /// Creates internal data structures.
   void create();
   std::unique_ptr<DebugStrBufferVector> StrBuffer;
   std::unique_ptr<raw_svector_ostream> StrStream;
@@ -585,7 +585,7 @@ class DebugLoclistWriter : public DebugLocWriter {
   void finalize(DIEBuilder &DIEBldr, DIE &Die) override;
 
   /// Returns CU ID.
-  /// For Skelton CU it is a CU Offset.
+  /// For Skeleton CU it is a CU Offset.
   /// For DWO CU it is a DWO ID.
   uint64_t getCUID() const {
     return CU.isDWOUnit() ? *CU.getDWOId() : CU.getOffset();

bolt/include/bolt/Core/DynoStats.h

@@ -121,7 +121,7 @@ class DynoStats {
   /// Maps instruction opcodes to:
   /// 1. Accumulated executed instruction counts.
   /// 2. a multimap that records highest execution counts, function names,
-  /// and BB offsets where intructions of these opcodes occur.
+  /// and BB offsets where instructions of these opcodes occur.
   using MaxOpcodeHistogramTy =
       std::multimap<uint64_t, std::pair<StringRef, uint32_t>>;
   using OpcodeHistogramTy =