[𝘀𝗽𝗿] changes introduced through rebase

Created using spr 1.3.4

[skip ci]

Author: ilovepi

.ci/generate-buildkite-pipeline-premerge

@@ -272,7 +272,7 @@ if [[ "${linux_projects}" != "" ]]; then
   artifact_paths:
   - 'artifacts/**/*'
   - '*_result.json'
-  - 'build/test-results.xml'
+  - 'build/test-results.*.xml'
   agents: ${LINUX_AGENTS}
   retry:
     automatic:
@@ -295,7 +295,7 @@ if [[ "${windows_projects}" != "" ]]; then
   artifact_paths:
   - 'artifacts/**/*'
   - '*_result.json'
-  - 'build/test-results.xml'
+  - 'build/test-results.*.xml'
   agents: ${WINDOWS_AGENTS}
   retry:
     automatic:

.ci/monolithic-linux.sh

@@ -37,6 +37,8 @@ trap show-stats EXIT
 projects="${1}"
 targets="${2}"
 
+lit_args="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --use-unique-output-file-name --timeout=1200 --time-tests"
+
 echo "--- cmake"
 pip install -q -r "${MONOREPO_ROOT}"/mlir/python/requirements.txt
 pip install -q -r "${MONOREPO_ROOT}"/lldb/test/requirements.txt
@@ -47,7 +49,7 @@ cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_ASSERTIONS=ON \
       -D LLVM_BUILD_EXAMPLES=ON \
       -D COMPILER_RT_BUILD_LIBFUZZER=OFF \
-      -D LLVM_LIT_ARGS="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --timeout=1200 --time-tests" \
+      -D LLVM_LIT_ARGS="${lit_args}" \
       -D LLVM_ENABLE_LLD=ON \
       -D CMAKE_CXX_FLAGS=-gmlt \
       -D LLVM_CCACHE_BUILD=ON \
@@ -87,7 +89,8 @@ if [[ "${runtimes}" != "" ]]; then
       -D CMAKE_BUILD_TYPE=RelWithDebInfo \
       -D CMAKE_INSTALL_PREFIX="${INSTALL_DIR}" \
       -D LIBCXX_TEST_PARAMS="std=c++03" \
-      -D LIBCXXABI_TEST_PARAMS="std=c++03"
+      -D LIBCXXABI_TEST_PARAMS="std=c++03" \
+      -D LLVM_LIT_ARGS="${lit_args}"
 
   echo "--- ninja runtimes C++03"
 
@@ -104,7 +107,8 @@ if [[ "${runtimes}" != "" ]]; then
       -D CMAKE_BUILD_TYPE=RelWithDebInfo \
       -D CMAKE_INSTALL_PREFIX="${INSTALL_DIR}" \
       -D LIBCXX_TEST_PARAMS="std=c++26" \
-      -D LIBCXXABI_TEST_PARAMS="std=c++26"
+      -D LIBCXXABI_TEST_PARAMS="std=c++26" \
+      -D LLVM_LIT_ARGS="${lit_args}"
 
   echo "--- ninja runtimes C++26"
 
@@ -121,7 +125,8 @@ if [[ "${runtimes}" != "" ]]; then
       -D CMAKE_BUILD_TYPE=RelWithDebInfo \
       -D CMAKE_INSTALL_PREFIX="${INSTALL_DIR}" \
       -D LIBCXX_TEST_PARAMS="enable_modules=clang" \
-      -D LIBCXXABI_TEST_PARAMS="enable_modules=clang"
+      -D LIBCXXABI_TEST_PARAMS="enable_modules=clang" \
+      -D LLVM_LIT_ARGS="${lit_args}"
 
   echo "--- ninja runtimes clang modules"
 

.ci/monolithic-windows.sh

@@ -53,7 +53,7 @@ cmake -S "${MONOREPO_ROOT}"/llvm -B "${BUILD_DIR}" \
       -D LLVM_ENABLE_ASSERTIONS=ON \
       -D LLVM_BUILD_EXAMPLES=ON \
       -D COMPILER_RT_BUILD_LIBFUZZER=OFF \
-      -D LLVM_LIT_ARGS="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --timeout=1200 --time-tests" \
+      -D LLVM_LIT_ARGS="-v --xunit-xml-output ${BUILD_DIR}/test-results.xml --use-unique-output-file-name --timeout=1200 --time-tests" \
       -D COMPILER_RT_BUILD_ORC=OFF \
       -D CMAKE_C_COMPILER_LAUNCHER=sccache \
       -D CMAKE_CXX_COMPILER_LAUNCHER=sccache \

.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/new-prs-labeler.yml

@@ -605,6 +605,14 @@ llvm:transforms:
   - llvm/test/Transforms/**
   - llvm/unittests/Transforms/**
 
+llvm:instcombine:
+  - llvm/lib/Analysis/InstructionSimplify.cpp
+  - llvm/lib/Transforms/InstCombine/**
+  - llvm/include/llvm/Transforms/InstCombine/
+  - llvm/include/llvm/Analysis/InstructionSimplify.h
+  - llvm/test/Transforms/InstCombine/**
+  - llvm/test/Transforms/InstSimplify/**
+
 clangd:
   - clang-tools-extra/clangd/**
 

.github/workflows/containers/github-action-ci/stage1.Dockerfile

@@ -2,7 +2,7 @@ FROM docker.io/library/ubuntu:22.04 as base
 ENV LLVM_SYSROOT=/opt/llvm
 
 FROM base as stage1-toolchain
-ENV LLVM_VERSION=18.1.8
+ENV LLVM_VERSION=19.1.2
 
 RUN apt-get update && \
     apt-get install -y \

.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
@@ -79,12 +80,14 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/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:
@@ -123,6 +126,7 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*
@@ -155,25 +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 }}
@@ -188,6 +190,7 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*
@@ -230,6 +233,7 @@ jobs:
           path: |
             **/test-results.xml
             **/*.abilist
+            **/CMakeConfigureLog.yaml
             **/CMakeError.log
             **/CMakeOutput.log
             **/crash_diagnostics/*

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/BinaryContext.h

@@ -723,12 +723,28 @@ class BinaryContext {
     /// Stats for stale profile matching:
     ///   the total number of basic blocks in the profile
     uint32_t NumStaleBlocks{0};
-    ///   the number of matched basic blocks
-    uint32_t NumMatchedBlocks{0};
+    ///   the number of exactly matched basic blocks
+    uint32_t NumExactMatchedBlocks{0};
+    ///   the number of loosely matched basic blocks
+    uint32_t NumLooseMatchedBlocks{0};
+    ///   the number of exactly pseudo probe matched basic blocks
+    uint32_t NumPseudoProbeExactMatchedBlocks{0};
+    ///   the number of loosely pseudo probe matched basic blocks
+    uint32_t NumPseudoProbeLooseMatchedBlocks{0};
+    ///   the number of call matched basic blocks
+    uint32_t NumCallMatchedBlocks{0};
     ///   the total count of samples in the profile
     uint64_t StaleSampleCount{0};
-    ///   the count of matched samples
-    uint64_t MatchedSampleCount{0};
+    ///   the count of exactly matched samples
+    uint64_t ExactMatchedSampleCount{0};
+    ///   the count of loosely matched samples
+    uint64_t LooseMatchedSampleCount{0};
+    ///   the count of exactly pseudo probe matched samples
+    uint64_t PseudoProbeExactMatchedSampleCount{0};
+    ///   the count of loosely pseudo probe matched samples
+    uint64_t PseudoProbeLooseMatchedSampleCount{0};
+    ///   the count of call matched samples
+    uint64_t CallMatchedSampleCount{0};
     ///   the number of stale functions that have matching number of blocks in
     ///   the profile
     uint64_t NumStaleFuncsWithEqualBlockCount{0};

bolt/include/bolt/Core/BinaryFunction.h

@@ -386,6 +386,9 @@ class BinaryFunction {
   /// Raw branch count for this function in the profile.
   uint64_t RawBranchCount{0};
 
+  /// Dynamically executed function bytes, used for density computation.
+  uint64_t SampleCountInBytes{0};
+
   /// Indicates the type of profile the function is using.
   uint16_t ProfileFlags{PF_NONE};
 
@@ -905,6 +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,
@@ -1844,6 +1851,9 @@ class BinaryFunction {
   /// to this function.
   void setRawBranchCount(uint64_t Count) { RawBranchCount = Count; }
 
+  /// Return the number of dynamically executed bytes, from raw perf data.
+  uint64_t getSampleCountInBytes() const { return SampleCountInBytes; }
+
   /// Return the execution count for functions with known profile.
   /// Return 0 if the function has no profile.
   uint64_t getKnownExecutionCount() const {