[𝘀𝗽𝗿] changes to main this commit is based on

Created using spr 1.3.4

[skip ci]

Author: maksfb

.ci/compute_projects.py

@@ -19,6 +19,7 @@
 PROJECT_DEPENDENCIES = {
     "llvm": set(),
     "clang": {"llvm"},
+    "CIR": {"clang", "mlir"},
     "bolt": {"clang", "lld", "llvm"},
     "clang-tools-extra": {"clang", "llvm"},
     "compiler-rt": {"clang", "lld"},
@@ -55,6 +56,7 @@
     ".ci": {
         "llvm",
         "clang",
+        "CIR",
         "lld",
         "lldb",
         "bolt",
@@ -128,6 +130,7 @@
     "lldb": "check-lldb",
     "llvm": "check-llvm",
     "clang": "check-clang",
+    "CIR": "check-clang-cir",
     "bolt": "check-bolt",
     "lld": "check-lld",
     "flang": "check-flang",
@@ -247,6 +250,14 @@ def _get_modified_projects(modified_files: list[str]) -> Set[str]:
         # capacity.
         if len(path_parts) > 3 and path_parts[:3] == ("llvm", "utils", "gn"):
             continue
+        # If the file is in the clang/lib/CIR directory, add the CIR project.
+        if len(path_parts) > 3 and (
+            path_parts[:3] == ("clang", "lib", "CIR")
+            or path_parts[:3] == ("clang", "test", "CIR")
+            or path_parts[:4] == ("clang", "include", "clang", "CIR")
+        ):
+            modified_projects.add("CIR")
+            # Fall through to add clang.
         modified_projects.add(pathlib.Path(modified_file).parts[0])
     return modified_projects
 
@@ -267,6 +278,13 @@ def get_env_variables(modified_files: list[str], platform: str) -> Set[str]:
     runtimes_check_targets_needs_reconfig = _compute_project_check_targets(
         runtimes_to_test_needs_reconfig
     )
+
+    # CIR is used as a pseudo-project in this script. It is built as part of the
+    # clang build, but it requires an explicit option to enable. We set that
+    # option here, and remove it from the projects_to_build list.
+    enable_cir = "ON" if "CIR" in projects_to_build else "OFF"
+    projects_to_build.discard("CIR")
+
     # We use a semicolon to separate the projects/runtimes as they get passed
     # to the CMake invocation and thus we need to use the CMake list separator
     # (;). We use spaces to separate the check targets as they end up getting
@@ -279,6 +297,7 @@ def get_env_variables(modified_files: list[str], platform: str) -> Set[str]:
         "runtimes_check_targets_needs_reconfig": " ".join(
             sorted(runtimes_check_targets_needs_reconfig)
         ),
+        "enable_cir": enable_cir,
     }
 
 

.ci/compute_projects_test.py

@@ -104,6 +104,10 @@ def test_clang(self):
             env_variables["runtimes_check_targets_needs_reconfig"],
             "check-cxx check-cxxabi check-unwind",
         )
+        self.assertEqual(
+            env_variables["enable_cir"],
+            "OFF",
+        )
 
     def test_clang_windows(self):
         env_variables = compute_projects.get_env_variables(
@@ -126,6 +130,32 @@ def test_clang_windows(self):
             env_variables["runtimes_check_targets_needs_reconfig"],
             "check-cxx check-cxxabi check-unwind",
         )
+        self.assertEqual(env_variables["enable_cir"], "OFF")
+
+    def test_cir(self):
+        env_variables = compute_projects.get_env_variables(
+            ["clang/lib/CIR/CMakeLists.txt"], "Linux"
+        )
+        self.assertEqual(
+            env_variables["projects_to_build"],
+            "clang;clang-tools-extra;lld;llvm;mlir",
+        )
+        self.assertEqual(
+            env_variables["project_check_targets"],
+            "check-clang check-clang-cir check-clang-tools",
+        )
+        self.assertEqual(
+            env_variables["runtimes_to_build"], "compiler-rt;libcxx;libcxxabi;libunwind"
+        )
+        self.assertEqual(
+            env_variables["runtimes_check_targets"],
+            "check-compiler-rt",
+        )
+        self.assertEqual(
+            env_variables["runtimes_check_targets_needs_reconfig"],
+            "check-cxx check-cxxabi check-unwind",
+        )
+        self.assertEqual(env_variables["enable_cir"], "ON")
 
     def test_bolt(self):
         env_variables = compute_projects.get_env_variables(
@@ -158,6 +188,7 @@ def test_mlir(self):
         self.assertEqual(env_variables["runtimes_to_build"], "")
         self.assertEqual(env_variables["runtimes_check_targets"], "")
         self.assertEqual(env_variables["runtimes_check_targets_needs_reconfig"], "")
+        self.assertEqual(env_variables["enable_cir"], "OFF")
 
     def test_flang(self):
         env_variables = compute_projects.get_env_variables(
@@ -168,6 +199,7 @@ def test_flang(self):
         self.assertEqual(env_variables["runtimes_to_build"], "")
         self.assertEqual(env_variables["runtimes_check_targets"], "")
         self.assertEqual(env_variables["runtimes_check_targets_needs_reconfig"], "")
+        self.assertEqual(env_variables["enable_cir"], "OFF")
 
     def test_invalid_subproject(self):
         env_variables = compute_projects.get_env_variables(
@@ -237,7 +269,7 @@ def test_ci(self):
         )
         self.assertEqual(
             env_variables["project_check_targets"],
-            "check-bolt check-clang check-clang-tools check-flang check-lld check-lldb check-llvm check-mlir check-polly",
+            "check-bolt check-clang check-clang-cir check-clang-tools check-flang check-lld check-lldb check-llvm check-mlir check-polly",
         )
         self.assertEqual(
             env_variables["runtimes_to_build"],

.ci/monolithic-linux.sh

@@ -21,12 +21,7 @@ BUILD_DIR="${BUILD_DIR:=${MONOREPO_ROOT}/build}"
 INSTALL_DIR="${BUILD_DIR}/install"
 rm -rf "${BUILD_DIR}"
 
-ccache --zero-stats
-
-if [[ -n "${CLEAR_CACHE:-}" ]]; then
-  echo "clearing cache"
-  ccache --clear
-fi
+sccache --zero-stats
 
 mkdir -p artifacts/reproducers
 
@@ -36,7 +31,7 @@ export CLANG_CRASH_DIAGNOSTICS_DIR=`realpath artifacts/reproducers`
 function at-exit {
   retcode=$?
 
-  ccache --print-stats > artifacts/ccache_stats.txt
+  sccache --show-stats > artifacts/sccache_stats.txt
   cp "${BUILD_DIR}"/.ninja_log artifacts/.ninja_log
   cp "${BUILD_DIR}"/test-results.*.xml artifacts/ || :
 
@@ -53,6 +48,7 @@ targets="${2}"
 runtimes="${3}"
 runtime_targets="${4}"
 runtime_targets_needs_reconfig="${5}"
+enable_cir="${6}"
 
 lit_args="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --use-unique-output-file-name --timeout=1200 --time-tests"
 
@@ -72,13 +68,15 @@ cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -G Ninja \
       -D CMAKE_PREFIX_PATH="${HOME}/.local" \
       -D CMAKE_BUILD_TYPE=Release \
+      -D CLANG_ENABLE_CIR=${enable_cir} \
       -D LLVM_ENABLE_ASSERTIONS=ON \
       -D LLVM_BUILD_EXAMPLES=ON \
       -D COMPILER_RT_BUILD_LIBFUZZER=OFF \
       -D LLVM_LIT_ARGS="${lit_args}" \
       -D LLVM_ENABLE_LLD=ON \
       -D CMAKE_CXX_FLAGS=-gmlt \
-      -D LLVM_CCACHE_BUILD=ON \
+      -D CMAKE_C_COMPILER_LAUNCHER=sccache \
+      -D CMAKE_CXX_COMPILER_LAUNCHER=sccache \
       -D LIBCXX_CXX_ABI=libcxxabi \
       -D MLIR_ENABLE_BINDINGS_PYTHON=ON \
       -D LLDB_ENABLE_PYTHON=ON \

.ci/monolithic-windows.sh

@@ -21,11 +21,6 @@ BUILD_DIR="${BUILD_DIR:=${MONOREPO_ROOT}/build}"
 
 rm -rf "${BUILD_DIR}"
 
-if [[ -n "${CLEAR_CACHE:-}" ]]; then
-  echo "clearing sccache"
-  rm -rf "$SCCACHE_DIR"
-fi
-
 sccache --zero-stats
 function at-exit {
   retcode=$?

.github/CODEOWNERS

@@ -31,9 +31,9 @@
 /clang/www/cxx_dr_status.html @Endilll
 /clang/www/make_cxx_dr_status @Endilll
 
-/clang/include/clang/CIR @lanza @bcardosolopes
-/clang/lib/CIR @lanza @bcardosolopes
-/clang/tools/cir-* @lanza @bcardosolopes
+/clang/include/clang/CIR @lanza @bcardosolopes @xlauko @andykaylor
+/clang/lib/CIR @lanza @bcardosolopes @xlauko @andykaylor
+/clang/tools/cir-* @lanza @bcardosolopes @xlauko @andykaylor
 
 /lldb/ @JDevlieghere
 

.github/new-prs-labeler.yml

@@ -48,6 +48,9 @@ flang:frontend:
   - flang/Evaluate/**/*
   - flang/Semantics/**/*
 
+libclc:
+  - libclc/**
+
 HLSL:
   - clang/*HLSL*/**/*
   - clang/**/*HLSL*
@@ -717,6 +720,8 @@ mlgo:
   - llvm/lib/Analysis/IR2Vec.cpp
   - llvm/lib/Analysis/models/**
   - llvm/test/Analysis/IR2Vec/**
+  - llvm/tools/llvm-ir2vec/**
+  - llvm/docs/CommandGuide/llvm-ir2vec.rst
 
 tools:llvm-exegesis:
   - llvm/tools/llvm-exegesis/**

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

@@ -63,11 +63,21 @@ RUN apt-get update && \
     python3-pip \
     ccache \
     file \
-    tzdata \
-    sccache && \
+    tzdata && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
+# We need sccache for caching. We cannot use the apt repository version because
+# it is too old and has bugs related to features we require (particularly GCS
+# caching), so we manually install it here.
+# TODO(boomanaiden154): We should return to installing this from the apt
+# repository once a version containing the necessary bug fixes is available.
+RUN curl -L 'https://github.com/mozilla/sccache/releases/download/v0.10.0/sccache-v0.10.0-x86_64-unknown-linux-musl.tar.gz' > /tmp/sccache.tar.gz && \
+    echo "1fbb35e135660d04a2d5e42b59c7874d39b3deb17de56330b25b713ec59f849b /tmp/sccache.tar.gz" | sha256sum -c && \
+    tar xzf /tmp/sccache.tar.gz -O --wildcards '*/sccache' > '/usr/local/bin/sccache' && \
+    rm /tmp/sccache.tar.gz && \
+    chmod +x /usr/local/bin/sccache
+
 ENV LLVM_SYSROOT=$LLVM_SYSROOT
 ENV PATH=${LLVM_SYSROOT}/bin:${PATH}
 

.github/workflows/premerge.yaml

@@ -37,6 +37,7 @@ jobs:
       - name: Setup ccache
         uses: hendrikmuhs/ccache-action@a1209f81afb8c005c13b4296c32e363431bffea5 # v1.2.17
         with:
+          variant: "sccache"
           max-size: "2000M"
       - name: Build and Test
         # Mark the job as a success even if the step fails so that people do
@@ -61,7 +62,7 @@ jobs:
           export CC=/opt/llvm/bin/clang
           export CXX=/opt/llvm/bin/clang++
 
-          ./.ci/monolithic-linux.sh "${projects_to_build}" "${project_check_targets}" "${runtimes_to_build}" "${runtimes_check_targets}" "${runtimes_check_targets_needs_reconfig}"
+          ./.ci/monolithic-linux.sh "${projects_to_build}" "${project_check_targets}" "${runtimes_to_build}" "${runtimes_check_targets}" "${runtimes_check_targets_needs_reconfig}" "${enable_cir}"
       - name: Upload Artifacts
         if: '!cancelled()'
         uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0
@@ -76,7 +77,7 @@ jobs:
     if: >-
         github.repository_owner == 'llvm' &&
         (github.event_name != 'pull_request' || github.event.action != 'closed')
-    runs-on: llvm-premerge-windows-runners
+    runs-on: llvm-premerge-windows-2022-runners
     defaults:
       run:
         shell: bash

bolt/include/bolt/Core/BinaryContext.h

@@ -225,6 +225,9 @@ class BinaryContext {
   /// Store all functions in the binary, sorted by original address.
   std::map<uint64_t, BinaryFunction> BinaryFunctions;
 
+  /// Functions to be included in the output in the sorted order.
+  std::vector<BinaryFunction *> OutputFunctions;
+
   /// A mutex that is used to control parallel accesses to BinaryFunctions
   mutable llvm::sys::RWMutex BinaryFunctionsMutex;
 
@@ -559,6 +562,8 @@ class BinaryContext {
     return InjectedBinaryFunctions;
   }
 
+  BinaryFunction *createThunkBinaryFunction(const std::string &Name);
+
   /// Return vector with all functions, i.e. include functions from the input
   /// binary and functions created by BOLT.
   std::vector<BinaryFunction *> getAllBinaryFunctions();
@@ -1356,8 +1361,12 @@ class BinaryContext {
   unsigned addDebugFilenameToUnit(const uint32_t DestCUID,
                                   const uint32_t SrcCUID, unsigned FileIndex);
 
-  /// Return functions in output layout order
-  std::vector<BinaryFunction *> getSortedFunctions();
+  /// Return a vector of functions in the order ready for code emission.
+  /// The vector will include functions added/injected by BOLT.
+  const std::vector<BinaryFunction *> &getOutputFunctions();
+
+  /// Update function list for the output.
+  void updateOutputFunctions(std::vector<BinaryFunction *> &Functions);
 
   /// Do the best effort to calculate the size of the function by emitting
   /// its code, and relaxing branch instructions. By default, branch
@@ -1378,6 +1387,10 @@ class BinaryContext {
   uint64_t
   computeInstructionSize(const MCInst &Inst,
                          const MCCodeEmitter *Emitter = nullptr) const {
+    // FIXME: hack for faster size computation on aarch64.
+    if (isAArch64())
+      return MIB->isPseudo(Inst) ? 0 : 4;
+
     if (std::optional<uint32_t> Size = MIB->getSize(Inst))
       return *Size;
 

bolt/include/bolt/Core/BinaryFunction.h

@@ -368,6 +368,10 @@ class BinaryFunction {
   /// True if the function should not have an associated symbol table entry.
   bool IsAnonymous{false};
 
+  /// True if the function is used for remapping hot text and shall not be
+  /// placed on a huge page.
+  bool IsHotTextMover{false};
+
   /// Name for the section this function code should reside in.
   std::string CodeSectionName;
 
@@ -1415,6 +1419,8 @@ class BinaryFunction {
   /// Return true if the function uses ORC format for stack unwinding.
   bool hasORC() const { return HasORC; }
 
+  bool isHotTextMover() const { return IsHotTextMover; }
+
   const JumpTable *getJumpTable(const MCInst &Inst) const {
     const uint64_t Address = BC.MIB->getJumpTable(Inst);
     return getJumpTableContainingAddress(Address);
@@ -1769,6 +1775,8 @@ class BinaryFunction {
   /// Mark function that should not be emitted.
   void setIgnored();
 
+  void setHotTextMover(bool V) { IsHotTextMover = V; }
+
   void setHasIndirectTargetToSplitFragment(bool V) {
     HasIndirectTargetToSplitFragment = V;
   }