Merge remote-tracking branch 'origin/main' into vplan-split-prepareforvectorization

Author: fhahn

.github/CODEOWNERS

@@ -129,7 +129,7 @@
 /mlir/**/Transforms/SROA.* @moxinilian
 
 # BOLT
-/bolt/ @aaupov @maksfb @rafaelauler @ayermolo @yota9 @paschalis-mpeis
+/bolt/ @aaupov @maksfb @rafaelauler @ayermolo @yota9 @paschalis-mpeis @yozhu
 
 # Bazel build system.
 /utils/bazel/ @rupprecht @keith @aaronmondal

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

@@ -90,7 +90,7 @@ RUN powershell -Command \
 RUN git config --system core.longpaths true & \
     git config --global core.autocrlf false
 
-ARG RUNNER_VERSION=2.327.0
+ARG RUNNER_VERSION=2.327.1
 ENV RUNNER_VERSION=$RUNNER_VERSION
 
 RUN powershell -Command \

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

@@ -94,7 +94,7 @@ WORKDIR /home/gha
 
 FROM ci-container as ci-container-agent
 
-ENV GITHUB_RUNNER_VERSION=2.327.0
+ENV GITHUB_RUNNER_VERSION=2.327.1
 
 RUN mkdir actions-runner && \
     cd actions-runner && \

.github/workflows/libc-fullbuild-tests.yml

@@ -21,37 +21,37 @@ jobs:
           - os: ubuntu-24.04
             build_type: Debug
             ccache-variant: sccache
-            c_compiler: clang-21
-            cpp_compiler: clang++-21
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
             target: x86_64-unknown-linux-llvm
             include_scudo: ON
           - os: ubuntu-24.04
             build_type: Release
             ccache-variant: sccache
-            c_compiler: clang-21
-            cpp_compiler: clang++-21
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
             target: x86_64-unknown-linux-llvm
             include_scudo: ON
           - os: ubuntu-24.04
             build_type: MinSizeRel
             ccache-variant: sccache
-            c_compiler: clang-21
-            cpp_compiler: clang++-21
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
             target: x86_64-unknown-linux-llvm
             include_scudo: ON
           # TODO: remove ccache logic when https://github.com/hendrikmuhs/ccache-action/issues/279 is resolved.
           - os: ubuntu-24.04-arm
             build_type: Debug
             ccache-variant: ccache
-            c_compiler: clang-21
-            cpp_compiler: clang++-21
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
             target: aarch64-unknown-linux-llvm
             include_scudo: ON
           - os: ubuntu-24.04
             build_type: Debug
             ccache-variant: ccache
-            c_compiler: clang-21
-            cpp_compiler: clang++-21
+            c_compiler: clang-20
+            cpp_compiler: clang++-20
             target: x86_64-unknown-uefi-llvm
             include_scudo: OFF
           # TODO: add back gcc build when it is fixed
@@ -81,7 +81,7 @@ jobs:
       run: |
         wget https://apt.llvm.org/llvm.sh
         chmod +x llvm.sh
-        sudo ./llvm.sh 21
+        sudo ./llvm.sh 20
         sudo apt-get update
         sudo apt-get install -y libmpfr-dev libgmp-dev libmpc-dev ninja-build linux-libc-dev
         sudo ln -sf /usr/include/$(uname -p)-linux-gnu/asm /usr/include/asm

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

@@ -128,6 +128,7 @@ jobs:
           'generic-abi-unstable',
           'generic-hardening-mode-debug',
           'generic-hardening-mode-extensive',
+          'generic-hardening-mode-extensive-observe-semantic',
           'generic-hardening-mode-fast',
           'generic-hardening-mode-fast-with-abi-breaks',
           'generic-merged',

.github/workflows/libcxx-build-containers.yml

@@ -34,7 +34,9 @@ jobs:
 
     - name: Build the Linux builder image
       working-directory: libcxx/utils/ci
-      run: docker compose build actions-builder
+      run: |
+        docker compose build builder-base
+        docker compose build actions-builder
       env:
         TAG: ${{ github.sha }}
 
@@ -55,6 +57,7 @@ jobs:
       if: github.event_name == 'push'
       working-directory: libcxx/utils/ci
       run: |
+        docker compose push builder-base
         docker compose push actions-builder
       env:
         TAG: ${{ github.sha }}

.github/workflows/release-tasks.yml

@@ -111,3 +111,31 @@ jobs:
     # Called workflows don't have access to secrets by default, so we need to explicitly pass secrets that we use.
     secrets:
       RELEASE_TASKS_USER_TOKEN: ${{ secrets.RELEASE_TASKS_USER_TOKEN }}
+
+  uncomment-download-links:
+    name: Uncomment download links
+    runs-on: ubuntu-24.04
+    permissions:
+      contents: write # For updating the release message.
+    needs:
+      - validate-tag
+      - release-create
+      - release-binaries
+
+    steps:
+      - name: Install Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install python3-github
+
+      - name: Checkout LLVM
+        uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+        with:
+          sparse-checkout: llvm/utils/release/github-upload-release.py
+          sparse-checkout-cone-mode: false
+
+      - name: Uncomment Download Links
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: |
+          ./llvm/utils/release/./github-upload-release.py --token "$GITHUB_TOKEN" --release ${{ needs.validate-tag.outputs.release-version }} uncomment_download_links

bolt/include/bolt/Profile/DataAggregator.h

@@ -502,6 +502,9 @@ class DataAggregator : public DataReader {
   /// entries).
   void imputeFallThroughs();
 
+  /// Register profiled functions for lite mode.
+  void registerProfiledFunctions();
+
   /// Debugging dump methods
   void dump() const;
   void dump(const PerfBranchSample &Sample) const;

bolt/lib/Core/Relocation.cpp

@@ -1018,15 +1018,15 @@ void Relocation::print(raw_ostream &OS) const {
     OS << "RType:" << Twine::utohexstr(Type);
     break;
 
-  case Triple::aarch64:
+  case Triple::aarch64: {
     static const char *const AArch64RelocNames[] = {
 #define ELF_RELOC(name, value) #name,
 #include "llvm/BinaryFormat/ELFRelocs/AArch64.def"
 #undef ELF_RELOC
     };
     assert(Type < ArrayRef(AArch64RelocNames).size());
     OS << AArch64RelocNames[Type];
-    break;
+  } break;
 
   case Triple::riscv64:
     // RISC-V relocations are not sequentially numbered so we cannot use an
@@ -1043,15 +1043,15 @@ void Relocation::print(raw_ostream &OS) const {
     }
     break;
 
-  case Triple::x86_64:
+  case Triple::x86_64: {
     static const char *const X86RelocNames[] = {
 #define ELF_RELOC(name, value) #name,
 #include "llvm/BinaryFormat/ELFRelocs/x86_64.def"
 #undef ELF_RELOC
     };
     assert(Type < ArrayRef(X86RelocNames).size());
     OS << X86RelocNames[Type];
-    break;
+  } break;
   }
   OS << ", 0x" << Twine::utohexstr(Offset);
   if (Symbol) {

bolt/lib/Profile/DataAggregator.cpp

@@ -581,6 +581,26 @@ void DataAggregator::imputeFallThroughs() {
     outs() << "BOLT-INFO: imputed " << InferredTraces << " traces\n";
 }
 
+void DataAggregator::registerProfiledFunctions() {
+  DenseSet<uint64_t> Addrs;
+  for (const auto &Trace : llvm::make_first_range(Traces)) {
+    if (Trace.Branch != Trace::FT_ONLY &&
+        Trace.Branch != Trace::FT_EXTERNAL_ORIGIN)
+      Addrs.insert(Trace.Branch);
+    Addrs.insert(Trace.From);
+  }
+
+  for (const auto [PC, _] : BasicSamples)
+    Addrs.insert(PC);
+
+  for (const PerfMemSample &MemSample : MemSamples)
+    Addrs.insert(MemSample.PC);
+
+  for (const uint64_t Addr : Addrs)
+    if (BinaryFunction *Func = getBinaryFunctionContainingAddress(Addr))
+      Func->setHasProfileAvailable();
+}
+
 Error DataAggregator::preprocessProfile(BinaryContext &BC) {
   this->BC = &BC;
 
@@ -603,6 +623,7 @@ Error DataAggregator::preprocessProfile(BinaryContext &BC) {
       exit(0);
   }
 
+  registerProfiledFunctions();
   return Error::success();
 }
 
@@ -1347,10 +1368,6 @@ std::error_code DataAggregator::parseAggregatedLBREntry() {
   }
 
   const uint64_t FromOffset = Addr[0]->Offset;
-  BinaryFunction *FromFunc = getBinaryFunctionContainingAddress(FromOffset);
-  if (FromFunc)
-    FromFunc->setHasProfileAvailable();
-
   int64_t Count = Counters[0];
   int64_t Mispreds = Counters[1];
 
@@ -1361,11 +1378,6 @@ std::error_code DataAggregator::parseAggregatedLBREntry() {
     return std::error_code();
   }
 
-  const uint64_t ToOffset = Addr[1]->Offset;
-  BinaryFunction *ToFunc = getBinaryFunctionContainingAddress(ToOffset);
-  if (ToFunc)
-    ToFunc->setHasProfileAvailable();
-
   /// For fall-through types, adjust locations to match Trace container.
   if (Type == FT || Type == FT_EXTERNAL_ORIGIN || Type == FT_EXTERNAL_RETURN) {
     Addr[2] = Location(Addr[1]->Offset); // Trace To
@@ -1613,9 +1625,6 @@ std::error_code DataAggregator::parseBranchEvents() {
   Traces.reserve(TraceMap.size());
   for (const auto &[Trace, Info] : TraceMap) {
     Traces.emplace_back(Trace, Info);
-    for (const uint64_t Addr : {Trace.Branch, Trace.From})
-      if (BinaryFunction *BF = getBinaryFunctionContainingAddress(Addr))
-        BF->setHasProfileAvailable();
   }
   clear(TraceMap);
 
@@ -1676,9 +1685,6 @@ std::error_code DataAggregator::parseBasicEvents() {
       continue;
     ++NumTotalSamples;
 
-    if (BinaryFunction *BF = getBinaryFunctionContainingAddress(Sample->PC))
-      BF->setHasProfileAvailable();
-
     ++BasicSamples[Sample->PC];
     EventNames.insert(Sample->EventName);
   }
@@ -1716,9 +1722,6 @@ std::error_code DataAggregator::parseMemEvents() {
     if (std::error_code EC = Sample.getError())
       return EC;
 
-    if (BinaryFunction *BF = getBinaryFunctionContainingAddress(Sample->PC))
-      BF->setHasProfileAvailable();
-
     MemSamples.emplace_back(std::move(Sample.get()));
   }