Merge remote-tracking branch 'upstream/sycl' into sycl_prof_tool

* upstream/sycl: (2757 commits)
  [SYCL][Doc] Fixing incorrect merge of community Readme.md with our version (intel#5636)
  [SYCL] Change USM pooling parameters. (intel#5457)
  [CI] Fix cache location on Windows (intel#5603)
  [SYCL][NFC] Fix a warning about uninitialized struct members (intel#5610)
  [Buildbot] Update Windows GPU version to 101.1340 (intel#5620)
  Fix SPIRV -> OCL barrier call argument attributes
  Move SPV_INTEL_memory_access_aliasing tokens from spirv_internal
  [SYCL][ESIMD] Add support for named barrier APIs (intel#5583)
  [SYCL][L0] Remove ZeModule when program build failed (intel#5541)
  [SYCL] Silence "unknown attribute" warning for `device_indirectly_callable` (intel#5591)
  [SYCL][DOC] Introductory material for extensions (intel#5605)
  [SYCL][DOC] Change extension names to lower case (intel#5607)
  [SYCL] Improve get_kernel_bundle performance (intel#5496)
  [SYCL] Do not build device code for sub-devices (intel#5240)
  [sycl-post-link] Fix a crash during spec-constant properties generation (intel#5538)
  [SYCL][DOC] Move SPIR-V and OpenCL extensions (intel#5578)
  [SYCL][ESIMD][EMU] Update memory intrinsics for ESIMD_EMU plugin (intel#4748)
  [CI] Allow stale issue bot to analyze more issues (intel#5602)
  [SYCL][L0] Honor property::queue::enable_profiling (intel#5543)
  [OpenMP] Properly save strings when doing LTO
  ...

.clang-tidy

@@ -6,6 +6,10 @@ CheckOptions:
     value:           CamelCase
   - key:             readability-identifier-naming.FunctionCase
     value:           camelBack
+  # Exclude from scanning as this is an exported symbol used for fuzzing
+  # throughout the code base.
+  - key:             readability-identifier-naming.FunctionIgnoredRegexp
+    value:           "LLVMFuzzerTestOneInput"
   - key:             readability-identifier-naming.MemberCase
     value:           CamelCase
   - key:             readability-identifier-naming.ParameterCase

.github/workflows/closed-issues.yml

@@ -0,0 +1,13 @@
+name: Labeling closed issues
+on:
+  issues:
+    types: ['closed']
+
+jobs:
+  automate-issues-labels:
+    runs-on: ubuntu-latest
+    if: github.repository == 'llvm/llvm-project'
+    steps:
+      - uses: andymckay/labeler@1.0.4
+        with:
+          remove-labels: "awaiting-review"

.github/workflows/issue-release-workflow.yml

@@ -0,0 +1,84 @@
+# This contains the workflow definitions that allow users to test backports
+# to the release branch using comments on issues.
+#
+# /cherry-pick <commit> <...>
+#
+# This comment will attempt to cherry-pick the given commits to the latest
+# release branch (release/Y.x) and if successful push the result to a branch
+# on github.
+#
+# /branch <owner>/<repo>/<branch>
+#
+# This comment will create a pull request from <branch> to the latest release
+# branch.
+
+name: Issue Release Workflow
+
+on:
+  issue_comment:
+    types:
+      - created
+      - edited
+
+env:
+  COMMENT_BODY: ${{ github.event.comment.body }}
+
+jobs:
+  backport-commits:
+    name: Backport Commits
+    runs-on: ubuntu-20.04
+    if: >-
+        (github.repository == 'llvm/llvm-project') &&
+        !startswith(github.event.comment.body, '<!--IGNORE-->') &&
+        contains(github.event.comment.body, '/cherry-pick')
+    steps:
+      - name: Fetch LLVM sources
+        uses: actions/checkout@v2
+        with:
+          repository: llvm/llvm-project
+          # GitHub stores the token used for checkout and uses it for pushes
+          # too, but we want to use a different token for pushing, so we need
+          # to disable persist-credentials here.
+          persist-credentials: false
+          fetch-depth: 0
+
+      - name: Setup Environment
+        run: |
+          pip install -r ./llvm/utils/git/requirements.txt
+          ./llvm/utils/git/github-automation.py --token ${{ github.token }} setup-llvmbot-git
+
+      - name: Backport Commits
+        run: |
+          printf "$COMMENT_BODY" |
+          ./llvm/utils/git/github-automation.py \
+          --repo $GITHUB_REPOSITORY \
+          --token ${{ secrets.RELEASE_WORKFLOW_PUSH_SECRET }} \
+          release-workflow \
+          --issue-number ${{ github.event.issue.number }} \
+          auto
+
+  create-pull-request:
+    name: Create Pull Request
+    runs-on: ubuntu-20.04
+    if: >-
+        (github.repository == 'llvm/llvm-project') &&
+        !startswith(github.event.comment.body, '<!--IGNORE-->') &&
+        contains(github.event.comment.body, '/branch')
+
+    steps:
+      - name: Fetch LLVM sources
+        uses: actions/checkout@v2
+
+      - name: Setup Environment
+        run:  |
+          pip install -r ./llvm/utils/git/requirements.txt
+
+      - name: Create Pull Request
+        run: |
+          printf "$COMMENT_BODY" |
+          ./llvm/utils/git/github-automation.py \
+          --repo $GITHUB_REPOSITORY \
+          --token ${{ secrets.RELEASE_WORKFLOW_PUSH_SECRET }} \
+          release-workflow \
+          --issue-number ${{ github.event.issue.number }} \
+          auto

.github/workflows/issue-subscriber.yml

@@ -13,8 +13,9 @@ jobs:
     - name: Setup Automation Script
       run:  |
         curl -O -L https://raw.githubusercontent.com/$GITHUB_REPOSITORY/$GITHUB_SHA/llvm/utils/git/github-automation.py
+        curl -O -L https://raw.githubusercontent.com/$GITHUB_REPOSITORY/$GITHUB_SHA/llvm/utils/git/requirements.txt
         chmod a+x github-automation.py
-        pip install PyGithub
+        pip install -r requirements.txt
 
     - name: Update watchers
       run: |

.github/workflows/sycl_containers.yaml

@@ -107,6 +107,15 @@ jobs:
         uses: actions/checkout@v2
         with:
           fetch-depth: 2
+      - name: Get dependencies configuration
+        id: deps
+        run: |
+          DEPS=`cat devops/dependencies.json`
+          DEPS="${DEPS//'%'/'%25'}"
+          DEPS="${DEPS//$'\n'/'%0A'}"
+          DEPS="${DEPS//$'\r'/'%0D'}"
+          echo $DEPS
+          echo "::set-output name=deps::$DEPS"
       - name: Build and Push Container
         uses: ./devops/actions/build_container
         with:
@@ -117,4 +126,10 @@ jobs:
           tags: |
             ghcr.io/${{ github.repository }}/ubuntu2004_intel_drivers:unstable-${{ github.sha }}
             ghcr.io/${{ github.repository }}/ubuntu2004_intel_drivers:unstable
+          build-args: |
+            compute_runtime_tag=${{fromJson(steps.deps.outputs.deps).linux_staging.compute_runtime.github_tag}}
+            igc_tag=${{fromJson(steps.deps.outputs.deps).linux_staging.igc.github_tag}}
+            tbb_tag=${{fromJson(steps.deps.outputs.deps).linux_staging.tbb.github_tag}}
+            fpgaemu_tag=${{fromJson(steps.deps.outputs.deps).linux_staging.fpgaemu.github_tag}}
+            cpu_tag=${{fromJson(steps.deps.outputs.deps).linux_staging.oclcpu.github_tag}}
 

.github/workflows/sycl_linux_build_and_test.yml

@@ -40,7 +40,7 @@ on:
       build_configure_extra_args:
         type: string
         required: false
-        default: "--hip --hip-amd-arch=gfx906 --cuda"
+        default: "--hip --cuda"
       build_artifact_suffix:
         type: string
         required: true
@@ -86,7 +86,7 @@ jobs:
               \"build_cache_root\":\"/__w/\",
               \"build_cache_suffix\":\"default\",
               \"build_cache_size\":\"2G\",
-              \"build_configure_extra_args\":\"--hip --hip-amd-arch=gfx906 --cuda\",
+              \"build_configure_extra_args\":\"--hip --cuda\",
               \"build_artifact_suffix\":\"default\",
               \"build_upload_artifact\":\"false\",
               \"intel_drivers_image\":\"ghcr.io/intel/llvm/ubuntu2004_intel_drivers:latest\",
@@ -150,33 +150,34 @@ jobs:
           --cmake-opt="-DLLVM_INSTALL_UTILS=ON" \
           --cmake-opt="-DSYCL_PI_TESTS=OFF"
     - name: Compile
+      id: build
       run: cmake --build $GITHUB_WORKSPACE/build
     # TODO allow to optionally disable in-tree checks
     - name: check-llvm
-      if: always()
+      if: ${{ always() && !cancelled() && steps.build.outcome == 'success' }}
       run: |
         cmake --build $GITHUB_WORKSPACE/build --target check-llvm
     - name: check-clang
-      if: always()
+      if: ${{ always() && !cancelled() && steps.build.outcome == 'success' }}
       run: |
         export XDG_CACHE_HOME=$GITHUB_WORKSPACE/os_cache
         cmake --build $GITHUB_WORKSPACE/build --target check-clang
     - name: check-sycl
-      if: always()
+      if: ${{ always() && !cancelled() && steps.build.outcome == 'success' }}
       run: |
         # TODO consider moving this to Dockerfile
         export LD_LIBRARY_PATH=/usr/local/cuda/compat/:/usr/local/cuda/lib64:$LD_LIBRARY_PATH
         cmake --build $GITHUB_WORKSPACE/build --target check-sycl
     - name: check-llvm-spirv
-      if: always()
+      if: ${{ always() && !cancelled() && steps.build.outcome == 'success' }}
       run: |
         cmake --build $GITHUB_WORKSPACE/build --target check-llvm-spirv
     - name: check-xptifw
-      if: always()
+      if: ${{ always() && !cancelled() && steps.build.outcome == 'success' }}
       run: |
         cmake --build $GITHUB_WORKSPACE/build --target check-xptifw
     - name: check-libclc
-      if: always()
+      if: ${{ always() && !cancelled() && steps.build.outcome == 'success' }}
       run: |
         cmake --build $GITHUB_WORKSPACE/build --target check-libclc
     - name: Install

.github/workflows/sycl_nightly.yml

@@ -18,6 +18,13 @@ jobs:
       build_github_cache: true
       build_cache_root: "/__w/"
       build_artifact_suffix: default
+      lts_config: "ocl_gen9;ocl_x64;hip_amdgpu"
+
+  windows_default:
+    name: Windows (experimental)
+    if: github.repository == 'intel/llvm'
+    uses: ./.github/workflows/sycl_windows_build_and_test.yml
+
   ubuntu2004_docker_build_push:
     if: github.repository == 'intel/llvm'
     runs-on: ubuntu-latest
@@ -54,4 +61,14 @@ jobs:
         tags: |
           ghcr.io/${{ github.repository }}/sycl_ubuntu2004_nightly:no-drivers-${{ github.sha }}
           ghcr.io/${{ github.repository }}/sycl_ubuntu2004_nightly:no-drivers
-
+  ubuntu2004_build_test_new_pm:
+    # Default Linux building and LIT testing using new Pass Manager by default
+    if: github.repository == 'intel/llvm'
+    uses: intel/llvm/.github/workflows/sycl_linux_build_and_test.yml@sycl
+    with:
+      build_runs_on: build
+      build_cache_root: "/__w/"
+      build_cache_suffix: new_pm
+      build_artifact_suffix: new_pm
+      build_configure_extra_args: '--hip --cuda --cmake-opt=-DLLVM_ENABLE_NEW_PASS_MANAGER=ON'
+      lts_config: "hip_amdgpu;ocl_x64"

.github/workflows/sycl_precommit.yml

@@ -30,4 +30,4 @@ jobs:
       build_cache_size: "8G"
       build_artifact_suffix: "default"
       build_cache_suffix: "default"
-      lts_config: "hip_amdgpu;ocl_x64"
+      lts_config: "hip_amdgpu;ocl_x64;ocl_gen9;l0_gen9"

.github/workflows/sycl_stale_issues.yml

@@ -0,0 +1,21 @@
+name: Stale Issues
+
+on:
+  schedule:
+    - cron: '30 1 * * *'
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/stale@v4
+      with:
+        stale-issue-message: 'This issue is stale because it has been open 180 days with no activity. Remove stale label or comment or this will be automatically closed in 30 days.'
+        close-issue-message: 'This issue was closed because it has been stalled for 30 days with no activity. Please, re-open if the issue still exists.'
+        days-before-stale: 180
+        days-before-close: 30
+        exempt-issue-labels: 'confirmed,hip,cuda,enhancement,help wanted,upstream'
+        stale-issue-label: 'stale'
+        exempt-all-issue-assignees: true
+        operations-per-run: 200
+

.github/workflows/sycl_windows_build_and_test.yml

@@ -0,0 +1,65 @@
+name: SYCL Windows Test
+
+on:
+  workflow_call:
+
+jobs:
+  build:
+    name: Build
+    runs-on: windows-2022
+    steps:
+    - uses: actions/checkout@v2
+      with:
+        path: src
+        fetch-depth: 1
+    - name: Install dependencies
+      shell: cmd
+      run: |
+        choco install -y cuda --version 11.6.0.51123
+        choco install -y ninja
+        choco install -y sccache --version 0.2.15
+        refreshenv
+        echo CUDA_PATH=%CUDA_PATH%
+        echo CUDA_PATH=%CUDA_PATH% >> %GITHUB_ENV%
+    - uses: ilammy/msvc-dev-cmd@9f8ae839b01883414208f29e3e24524387f48e1f
+      with:
+        arch: amd64
+    - name: Setup Cache
+      uses: actions/cache@v2
+      if: ${{ github.event_name != 'pull_request' }}
+      id: cache
+      with:
+        path: cache
+        key: sycl-win-build-${{ github.sha }}
+        restore-keys: |
+          sycl-win-build-
+    - name: Build
+      shell: cmd
+      env:
+        CUDA_PATH: 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6'
+        CUDA_TOOLKIT_ROOT_DIR: 'C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6'
+      # TODO switch to clang-cl and lld when this is fixed https://github.com/oneapi-src/level-zero/issues/83
+      # TODO enable sccache, when problems with PDB are resolved
+      run: |
+        mkdir build
+        mkdir install
+        IF NOT EXIST cache MKDIR cache
+        set SCCACHE_DIR=%GITHUB_WORKSPACE%\cache
+        set PATH=C:\ProgramData\chocolatey\lib\sccache\tools\sccache-v0.2.15-x86_64-pc-windows-msvc;%PATH%
+        python.exe src/buildbot/configure.py -o build ^
+          --cmake-opt="-DCMAKE_C_COMPILER=cl" ^
+          --cmake-opt="-DCMAKE_CXX_COMPILER=cl" ^
+          --cmake-opt="-DCMAKE_INSTALL_PREFIX=%GITHUB_WORKSPACE%\install" ^
+          --cmake-opt="-DCMAKE_CXX_COMPILER_LAUNCHER=sccache" ^
+          --cmake-opt="-DCMAKE_C_COMPILER_LAUNCHER=sccache" ^
+          --cuda
+        cmake --build build --target sycl-toolchain
+        sccache --show-stats
+    - name: Install
+      shell: cmd
+      run: cmake --build build --target deploy-sycl-toolchain
+    - name: Upload toolchain
+      uses: actions/upload-artifact@v2
+      with:
+        name: sycl_windows_default
+        path: install/**/*

bolt/docs/Heatmaps.md

@@ -23,11 +23,10 @@ $ perf record -e cycles:u -j any,u [-p PID|-a] -- sleep <interval>
 Note that at the moment running with LBR (`-j any,u` or `-b`) is
 a requirement.
 
-Once the run is complete, and `perf.data` is generated, run BOLT in
-a heatmap mode:
+Once the run is complete, and `perf.data` is generated, run llvm-bolt-heatmap:
 
 ```bash
-$ llvm-bolt heatmap -p perf.data <executable>
+$ llvm-bolt-heatmap -p perf.data <executable>
 ```
 
 By default the heatmap will be dumped to *stdout*. You can change it

bolt/docs/OptimizingClang.md

@@ -41,7 +41,7 @@ Collecting accurate profile requires running `perf` on a hardware that
 implements taken branch sampling (`-b/-j` flag). For that reason, it may not be possible to
 collect the accurate profile in a virtualized environment, e.g. in the cloud.
 We do support regular sampling profiles, but the performance
-improvements are expected to be more modest. 
+improvements are expected to be more modest.
 
 ```bash
 $ mkdir ${TOPLEV}/stage3
@@ -211,7 +211,8 @@ $ cd ${TOPLEV}/stage1
 $ cmake -G Ninja ${TOPLEV}/llvm-project/llvm -DLLVM_TARGETS_TO_BUILD=X86 \
       -DCMAKE_BUILD_TYPE=Release \
       -DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++ -DCMAKE_ASM_COMPILER=gcc \
-      -DLLVM_ENABLE_PROJECTS="clang;lld;compiler-rt" \
+      -DLLVM_ENABLE_PROJECTS="clang;lld" \
+      -DLLVM_ENABLE_RUNTIMES="compiler-rt" \
       -DCOMPILER_RT_BUILD_SANITIZERS=OFF -DCOMPILER_RT_BUILD_XRAY=OFF \
       -DCOMPILER_RT_BUILD_LIBFUZZER=OFF \
       -DCMAKE_INSTALL_PREFIX=${TOPLEV}/stage1/install

bolt/include/bolt/Core/BinaryBasicBlock.h

@@ -31,6 +31,7 @@ class MCCodeEmitter;
 namespace bolt {
 
 class BinaryFunction;
+class JumpTable;
 
 class BinaryBasicBlock {
 public:
@@ -623,6 +624,10 @@ class BinaryBasicBlock {
   /// remove the conditional successor and branch instruction.
   void removeDuplicateConditionalSuccessor(MCInst *CondBranch);
 
+  /// Update successors of the basic block based on the jump table instruction.
+  /// The block must end with a jump table instruction.
+  void updateJumpTableSuccessors();
+
   /// Test if BB is a predecessor of this block.
   bool isPredecessor(const BinaryBasicBlock *BB) const {
     auto Itr = std::find(Predecessors.begin(), Predecessors.end(), BB);
@@ -909,7 +914,12 @@ class BinaryBasicBlock {
     return Index;
   }
 
-  bool hasJumpTable() const;
+  /// Return jump table if the block contains a jump table instruction or
+  /// nullptr otherwise.
+  const JumpTable *getJumpTable() const;
+
+  /// Check if the block has a jump table instruction.
+  bool hasJumpTable() const { return getJumpTable() != nullptr; }
 
 private:
   void adjustNumPseudos(const MCInst &Inst, int Sign);