Merge branch 'main' into lialan/dynamic_masked_load

Author: lialan

.github/CODEOWNERS

@@ -68,7 +68,7 @@
 /mlir/lib/Dialect/Linalg/Transforms/ElementwiseOpFusion.cpp @MaheshRavishankar @nicolasvasilache
 /mlir/lib/Dialect/Linalg/Transforms/DataLayoutPropagation.cpp @hanhanW @nicolasvasilache
 /mlir/lib/Dialect/Linalg/Transforms/Transforms.cpp @dcaballe @hanhanW @nicolasvasilache
-/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp @banach-space @dcaballe @hanhanW @nicolasvasilache
+/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp @banach-space @dcaballe @hanhanW @nicolasvasilache @Groverkss
 
 # MemRef Dialect in MLIR.
 /mlir/lib/Dialect/MemRef/Transforms/EmulateNarrowType.cpp @MaheshRavishankar @nicolasvasilache
@@ -82,9 +82,9 @@
 /mlir/**/*VectorToSCF* @banach-space @dcaballe @matthias-springer @nicolasvasilache
 /mlir/**/*VectorToLLVM* @banach-space @dcaballe @nicolasvasilache
 /mlir/**/*X86Vector* @aartbik @dcaballe @nicolasvasilache
-/mlir/include/mlir/Dialect/Vector @banach-space @dcaballe @nicolasvasilache
+/mlir/include/mlir/Dialect/Vector @banach-space @dcaballe @nicolasvasilache @Groverkss
 /mlir/include/mlir/Dialect/Vector/IR @kuhar
-/mlir/lib/Dialect/Vector @banach-space @dcaballe @nicolasvasilache
+/mlir/lib/Dialect/Vector @banach-space @dcaballe @nicolasvasilache @Groverkss
 /mlir/lib/Dialect/Vector/Transforms/* @banach-space @dcaballe @hanhanW @nicolasvasilache
 /mlir/lib/Dialect/Vector/Transforms/VectorEmulateNarrowType.cpp @banach-space @dcaballe @MaheshRavishankar @nicolasvasilache
 /mlir/**/*EmulateNarrowType* @dcaballe @hanhanW
@@ -141,7 +141,7 @@
 /clang/tools/clang-installapi/ @cyndyishida
 
 # ExtractAPI
-/clang/**/ExtractAPI @daniel-grumberg
+/clang/**/ExtractAPI @daniel-grumberg @QuietMisdreavus
 
 # DWARFLinker, dwarfutil, dsymutil
 /llvm/**/DWARFLinker/ @JDevlieghere

.github/workflows/libcxx-build-and-test.yaml

@@ -49,7 +49,8 @@ env:
 jobs:
   stage1:
     if: github.repository_owner == 'llvm'
-    runs-on: libcxx-runners-8-set
+    runs-on: libcxx-runners-set
+    container: ghcr.io/libcxx/actions-builder:testing-2024-09-21
     continue-on-error: false
     strategy:
       fail-fast: false
@@ -85,7 +86,8 @@ jobs:
             **/crash_diagnostics/*
   stage2:
     if: github.repository_owner == 'llvm'
-    runs-on: libcxx-runners-8-set
+    runs-on: libcxx-runners-set
+    container: ghcr.io/libcxx/actions-builder:testing-2024-09-21
     needs: [ stage1 ]
     continue-on-error: false
     strategy:
@@ -157,25 +159,23 @@ jobs:
           'generic-no-rtti',
           'generic-optimized-speed',
           'generic-static',
-          # TODO Find a better place for the benchmark and bootstrapping builds to live. They're either very expensive
-          # or don't provide much value since the benchmark run results are too noise on the bots.
-          'benchmarks',
           'bootstrapping-build'
         ]
-        machine: [ 'libcxx-runners-8-set' ]
+        machine: [ 'libcxx-runners-set' ]
         include:
         - config: 'generic-cxx26'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         - config: 'generic-asan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         - config: 'generic-tsan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         - config: 'generic-ubsan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
         # Use a larger machine for MSAN to avoid timeout and memory allocation issues.
         - config: 'generic-msan'
-          machine: libcxx-runners-8-set
+          machine: libcxx-runners-set
     runs-on: ${{ matrix.machine }}
+    container: ghcr.io/libcxx/actions-builder:testing-2024-09-21
     steps:
       - uses: actions/checkout@v4
       - name: ${{ matrix.config }}

bolt/include/bolt/Core/BinaryBasicBlock.h

@@ -819,6 +819,9 @@ class BinaryBasicBlock {
     return OutputAddressRange;
   }
 
+  uint64_t getOutputStartAddress() const { return OutputAddressRange.first; }
+  uint64_t getOutputEndAddress() const { return OutputAddressRange.second; }
+
   bool hasLocSyms() const { return LocSyms != nullptr; }
 
   /// Return mapping of input offsets to symbols in the output.

bolt/include/bolt/Core/BinaryFunction.h

@@ -908,6 +908,10 @@ class BinaryFunction {
     return BB && BB->getOffset() == Offset ? BB : nullptr;
   }
 
+  const BinaryBasicBlock *getBasicBlockAtOffset(uint64_t Offset) const {
+    return const_cast<BinaryFunction *>(this)->getBasicBlockAtOffset(Offset);
+  }
+
   /// Retrieve the landing pad BB associated with invoke instruction \p Invoke
   /// that is in \p BB. Return nullptr if none exists
   BinaryBasicBlock *getLandingPadBBFor(const BinaryBasicBlock &BB,

bolt/include/bolt/Core/FunctionLayout.h

@@ -123,7 +123,8 @@ class FunctionFragment {
   const_iterator begin() const;
   iterator end();
   const_iterator end() const;
-  const BinaryBasicBlock *front() const;
+  BinaryBasicBlock *front() const;
+  BinaryBasicBlock *back() const;
 
   friend class FunctionLayout;
 };

bolt/include/bolt/Passes/LongJmp.h

@@ -63,6 +63,19 @@ class LongJmpPass : public BinaryFunctionPass {
   uint32_t NumColdStubs{0};
   uint32_t NumSharedStubs{0};
 
+  /// The shortest distance for any branch instruction on AArch64.
+  static constexpr size_t ShortestJumpBits = 16;
+  static constexpr size_t ShortestJumpSpan = 1ULL << (ShortestJumpBits - 1);
+
+  /// The longest single-instruction branch.
+  static constexpr size_t LongestJumpBits = 28;
+  static constexpr size_t LongestJumpSpan = 1ULL << (LongestJumpBits - 1);
+
+  /// Relax all internal function branches including those between fragments.
+  /// Assume that fragments are placed in different sections but are within
+  /// 128MB of each other.
+  void relaxLocalBranches(BinaryFunction &BF);
+
   ///                 -- Layout estimation methods --
   /// Try to do layout before running the emitter, by looking at BinaryFunctions
   /// and MCInsts -- this is an estimation. To be correct for longjmp inserter

bolt/include/bolt/Profile/DataAggregator.h

@@ -266,7 +266,8 @@ class DataAggregator : public DataReader {
                      uint64_t Mispreds);
 
   /// Register a \p Branch.
-  bool doBranch(uint64_t From, uint64_t To, uint64_t Count, uint64_t Mispreds);
+  bool doBranch(uint64_t From, uint64_t To, uint64_t Count, uint64_t Mispreds,
+                bool IsPreagg);
 
   /// Register a trace between two LBR entries supplied in execution order.
   bool doTrace(const LBREntry &First, const LBREntry &Second,

bolt/include/bolt/Profile/YAMLProfileReader.h

@@ -105,7 +105,7 @@ class YAMLProfileReader : public ProfileReaderBase {
   yaml::bolt::BinaryProfile YamlBP;
 
   /// Map a function ID from a YAML profile to a BinaryFunction object.
-  std::vector<BinaryFunction *> YamlProfileToFunction;
+  DenseMap<uint32_t, BinaryFunction *> YamlProfileToFunction;
 
   using FunctionSet = std::unordered_set<const BinaryFunction *>;
   /// To keep track of functions that have a matched profile before the profile
@@ -162,8 +162,6 @@ class YAMLProfileReader : public ProfileReaderBase {
   /// Update matched YAML -> BinaryFunction pair.
   void matchProfileToFunction(yaml::bolt::BinaryFunctionProfile &YamlBF,
                               BinaryFunction &BF) {
-    if (YamlBF.Id >= YamlProfileToFunction.size())
-      YamlProfileToFunction.resize(YamlBF.Id + 1);
     YamlProfileToFunction[YamlBF.Id] = &BF;
     YamlBF.Used = true;
 

bolt/lib/Core/FunctionLayout.cpp

@@ -33,7 +33,9 @@ FunctionFragment::const_iterator FunctionFragment::end() const {
   return const_iterator(Layout->block_begin() + StartIndex + Size);
 }
 
-const BinaryBasicBlock *FunctionFragment::front() const { return *begin(); }
+BinaryBasicBlock *FunctionFragment::front() const { return *begin(); }
+
+BinaryBasicBlock *FunctionFragment::back() const { return *std::prev(end()); }
 
 FunctionLayout::FunctionLayout() { addFragment(); }