Merge branch 'main' into inbelic/nfc-dxil

Author: inbelic

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

@@ -98,3 +98,45 @@ RUN powershell -Command \
     Add-Type -AssemblyName System.IO.Compression.FileSystem ; \
     [System.IO.Compression.ZipFile]::ExtractToDirectory('actions-runner-win.zip', $PWD) ;\
     rm actions-runner-win.zip
+
+# Set the LLVM_VERSION environment variable
+ENV LLVM_VERSION=21.1.2
+
+# Download and extract Clang compiler.
+# Create directories, download, extract, and clean up all in one layer
+RUN powershell -Command \
+    # --- Setup directories --- \
+    Write-Host "Creating directories..."; \
+    New-Item -Path "C:\temp-download" -ItemType "Directory" -Force ; \
+    New-Item -Path "C:\xz-utils" -ItemType "Directory" -Force ; \
+    New-Item -Path "C:\clang" -ItemType "Directory" -Force ; \
+    # --- 1. Download and extract xz --- \
+    Set-Location C:\temp-download ; \
+    Invoke-WebRequest -Uri "http://github.com/tukaani-project/xz/releases/download/v5.8.1/xz-5.8.1-windows.zip" -OutFile "xz.zip"; \
+    (Get-FileHash -Path "C:\temp-download\xz.zip" -Algorithm MD5).Hash -eq 'c3c69fdce3e825cc0b76123b36b0bcc2' ; \
+    Add-Type -AssemblyName "System.IO.Compression.FileSystem"; \
+    [System.IO.Compression.ZipFile]::ExtractToDirectory('C:\temp-download\xz.zip', 'C:\xz-utils'); \ 
+    # --- 2. Download and decompress Clang --- \
+    Invoke-WebRequest -Uri "http://github.com/llvm/llvm-project/releases/download/llvmorg-21.1.2/clang+llvm-21.1.2-x86_64-pc-windows-msvc.tar.xz" -OutFile "clang+llvm-21.1.2-x86_64-pc-windows-msvc.tar.xz" ; \
+    (Get-FileHash -Path "C:\temp-download\clang+llvm-21.1.2-x86_64-pc-windows-msvc.tar.xz" -Algorithm MD5).Hash -eq '0ae1d3effd9ab9d323f7fa595777f0a2' ; \
+    C:\xz-utils\bin_x86-64\xz.exe -d -qq clang+llvm-21.1.2-x86_64-pc-windows-msvc.tar.xz ; \
+    # --- 3. Extract clang --- \
+    C:\Windows\System32\tar.exe -xf clang+llvm-21.1.2-x86_64-pc-windows-msvc.tar -C C:\clang ; \
+    # --- 4. Clean up --- \
+    Set-Location C:\ ; \
+    Remove-Item C:\temp-download -Recurse -Force; \
+    Remove-Item C:\xz-utils -Recurse -Force; \
+    # -- 5. Shorten path to clang files & remove unnecessary files -- \
+    Set-Location C:\clang ; \
+    Rename-Item -Path "C:\clang\clang+llvm-21.1.2-x86_64-pc-windows-msvc" -NewName "C:\clang\clang-msvc" ; \
+    Set-Location C:\clang\clang-msvc ; \
+    Remove-Item -Path C:\clang\clang-msvc\libexec -Recurse -Force ; \
+    Remove-Item -Path C:\clang\clang-msvc\share -Recurse -Force ; \
+    Rename-Item -Path "C:\clang\clang-msvc\bin" -NewName "C:\clang\clang-msvc\bin-full" ; \
+    New-Item -Path "C:\clang\clang-msvc\bin" -ItemType Directory -Force ; \
+    Set-Location C:\clang\clang-msvc\bin ; \
+    Copy-Item -Path C:\clang\clang-msvc\bin-full\*.dll -Destination C:\clang\clang-msvc\bin\. ; \
+    Copy-Item -Path C:\clang\clang-msvc\bin-full\clang-cl.exe -Destination C:\clang\clang-msvc\bin\. ; \
+    Copy-Item -Path C:\clang\clang-msvc\bin-full\lld-link.exe -Destination C:\clang\clang-msvc\bin\. ; \
+    Set-Location C:\clang\clang-msvc ; \
+    Remove-Item -Path C:\clang\clang-msvc\bin-full -Recurse -Force ;

.github/workflows/libcxx-run-benchmarks.yml

@@ -64,17 +64,21 @@ jobs:
           path: repo # Avoid nuking the workspace, where we have the Python virtualenv
 
       - name: Run baseline
+        env:
+          BENCHMARKS: ${{ steps.vars.outputs.benchmarks }}
         run: |
           source .venv/bin/activate && cd repo
           python -m pip install -r libcxx/utils/requirements.txt
           baseline_commit=$(git merge-base ${{ steps.vars.outputs.pr_base }} ${{ steps.vars.outputs.pr_head }})
-          ./libcxx/utils/test-at-commit --commit ${baseline_commit} -B build/baseline -- -sv -j1 --param optimization=speed ${{ steps.vars.outputs.benchmarks }}
+          ./libcxx/utils/test-at-commit --commit ${baseline_commit} -B build/baseline -- -sv -j1 --param optimization=speed "$BENCHMARKS"
           ./libcxx/utils/consolidate-benchmarks build/baseline | tee baseline.lnt
 
       - name: Run candidate
+        env:
+          BENCHMARKS: ${{ steps.vars.outputs.benchmarks }}
         run: |
           source .venv/bin/activate && cd repo
-          ./libcxx/utils/test-at-commit --commit ${{ steps.vars.outputs.pr_head }} -B build/candidate -- -sv -j1 --param optimization=speed ${{ steps.vars.outputs.benchmarks }}
+          ./libcxx/utils/test-at-commit --commit ${{ steps.vars.outputs.pr_head }} -B build/candidate -- -sv -j1 --param optimization=speed "$BENCHMARKS"
           ./libcxx/utils/consolidate-benchmarks build/candidate | tee candidate.lnt
 
       - name: Compare baseline and candidate runs

.github/workflows/premerge.yaml

@@ -193,7 +193,7 @@ jobs:
         uses: llvm/actions/install-ninja@main
       - name: Build and Test
         run: |
-          source <(git diff --name-only HEAD~2..HEAD | python3 .ci/compute_projects.py)
+          source <(git diff --name-only HEAD~1...HEAD | python3 .ci/compute_projects.py)
 
           if [[ "${projects_to_build}" == "" ]]; then
             echo "No projects to build"

.github/workflows/release-binaries.yml

@@ -58,7 +58,6 @@ jobs:
       ref: ${{ steps.vars.outputs.ref }}
       upload: ${{ steps.vars.outputs.upload }}
       target-cmake-flags: ${{ steps.vars.outputs.target-cmake-flags }}
-      ccache: ${{ steps.vars.outputs.ccache }}
       build-flang: ${{ steps.vars.outputs.build-flang }}
       release-binary-basename: ${{ steps.vars.outputs.release-binary-basename }}
       release-binary-filename: ${{ steps.vars.outputs.release-binary-filename }}
@@ -123,13 +122,6 @@ jobs:
         echo "release-binary-filename=$release_binary_basename.tar.xz" >> $GITHUB_OUTPUT
 
         target="$RUNNER_OS-$RUNNER_ARCH"
-        # The hendrikmuhs/ccache-action action does not support installing sccache
-        # on arm64 Linux.
-        if [ "$target" = "Linux-ARM64" ]; then
-          echo ccache=ccache >> $GITHUB_OUTPUT
-        else
-          echo ccache=sccache >> $GITHUB_OUTPUT
-        fi
 
         # The macOS builds try to cross compile some libraries so we need to
         # add extra CMake args to disable them.
@@ -222,15 +214,12 @@ jobs:
     - name: Configure
       id: build
       shell: bash
-      env:
-        CCACHE_BIN: ${{ needs.prepare.outputs.ccache }}
       run: |
         # There were some issues on the ARM64 MacOS runners with trying to build x86 object,
         # so we need to set some extra cmake flags to disable this.
         cmake -G Ninja -S llvm -B ${{ steps.setup-stage.outputs.build-prefix }}/build \
             ${{ needs.prepare.outputs.target-cmake-flags }} \
             -C clang/cmake/caches/Release.cmake \
-            -DBOOTSTRAP_LLVM_PARALLEL_LINK_JOBS=1 \
             -DBOOTSTRAP_BOOTSTRAP_CPACK_PACKAGE_FILE_NAME="${{ needs.prepare.outputs.release-binary-basename }}"
 
     - name: Build

.github/workflows/release-documentation.yml

@@ -25,6 +25,10 @@ on:
         description: 'Upload documentation'
         required: false
         type: boolean
+    secrets:
+      WWW_RELEASES_TOKEN:
+        description: "Secret used to create a PR with the documentation changes."
+        required: false
 
 jobs:
   release-documentation:

.github/workflows/release-tasks.yml

@@ -54,6 +54,9 @@ jobs:
     with:
       release-version: ${{ needs.validate-tag.outputs.release-version }}
       upload: true
+    # Called workflows don't have access to secrets by default, so we need to explicitly pass secrets that we use.
+    secrets:
+      WWW_RELEASES_TOKEN: ${{ secrets.WWW_RELEASES_TOKEN }}
 
   release-doxygen:
     name: Build and Upload Release Doxygen

bolt/README.md

@@ -164,7 +164,7 @@ $ perf2bolt -p perf.data -o perf.fdata <executable>
 This command will aggregate branch data from `perf.data` and store it in a
 format that is both more compact and more resilient to binary modifications.
 
-If the profile was collected without brstacks, you will need to add `-nl` flag to
+If the profile was collected without brstacks, you will need to add `-ba` flag to
 the command line above.
 
 ### Step 3: Optimize with BOLT

bolt/docs/Heatmaps.md

@@ -21,7 +21,7 @@ $ perf record -e cycles:u -j any,u [-p PID|-a] -- sleep <interval>
 ```
 
 Running with brstack (`-j any,u` or `-b`) is recommended. Heatmaps can be generated
-from basic events by using the llvm-bolt-heatmap option `-nl` (no brstack) but
+from basic events by using the llvm-bolt-heatmap option `-ba` (basic events) but
 such heatmaps do not have the coverage provided by brstack and may only be useful
 for finding event hotspots at larger code block granularities.
 

bolt/docs/index.rst

@@ -205,8 +205,8 @@ This command will aggregate branch data from ``perf.data`` and store it
 in a format that is both more compact and more resilient to binary
 modifications.
 
-If the profile was collected without LBRs, you will need to add ``-nl``
-flag to the command line above.
+If the profile was collected without brstacks, you will need to add `-ba` flag to
+the command line above.
 
 Step 3: Optimize with BOLT
 ~~~~~~~~~~~~~~~~~~~~~~~~~~

bolt/include/bolt/Core/BinaryFunction.h

@@ -2142,8 +2142,9 @@ class BinaryFunction {
   }
 
   /// Detects whether \p Address is inside a data region in this function
-  /// (constant islands).
-  bool isInConstantIsland(uint64_t Address) const {
+  /// (constant islands), and optionally return the island size starting
+  /// from the given \p Address.
+  bool isInConstantIsland(uint64_t Address, uint64_t *Size = nullptr) const {
     if (!Islands)
       return false;
 
@@ -2161,10 +2162,15 @@ class BinaryFunction {
     DataIter = std::prev(DataIter);
 
     auto CodeIter = Islands->CodeOffsets.upper_bound(Offset);
-    if (CodeIter == Islands->CodeOffsets.begin())
+    if (CodeIter == Islands->CodeOffsets.begin() ||
+        *std::prev(CodeIter) <= *DataIter) {
+      if (Size)
+        *Size = (CodeIter == Islands->CodeOffsets.end() ? getMaxSize()
+                                                        : *CodeIter) -
+                Offset;
       return true;
-
-    return *std::prev(CodeIter) <= *DataIter;
+    }
+    return false;
   }
 
   uint16_t getConstantIslandAlignment() const;