Merge branch 'main' into alex/2585

intel · Nov 22, 2024 · b64be96 · b64be96
2 parents ae3ba41 + 816d7ef
commit b64be96
Show file tree

Hide file tree

Showing 40 changed files with 1,104 additions and 515 deletions.
diff --git a/.github/actions/setup-pytorch/action.yml b/.github/actions/setup-pytorch/action.yml
@@ -83,7 +83,7 @@ runs:
       uses: ./.github/actions/load
       env:
         # Increase this value to reset cache
-        CACHE_NUMBER: 12
+        CACHE_NUMBER: 14
       with:
         path: pytorch
         key: pytorch-$PYTORCH_CACHE_KEY-$CACHE_NUMBER
@@ -120,7 +120,7 @@ runs:
         cd pytorch
         pip install wheel
         pip install -r requirements.txt
-        python setup.py bdist_wheel
+        USE_STATIC_MKL=1 python setup.py bdist_wheel
 
     - name: Install PyTorch (built from source)
       if: ${{ inputs.mode == 'source' }}

diff --git a/.github/workflows/integration-tests.yml b/.github/workflows/integration-tests.yml
@@ -21,10 +21,12 @@ concurrency:
   cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
 permissions: read-all
 env:
+  TRITON_BUILD_WITH_CCACHE: "true"
   TRITON_BUILD_WITH_CLANG_LLD: "TRUE"
   TRITON_USE_ASSERT_ENABLED_LLVM: "TRUE"
   TRITON_DISABLE_LINE_INFO: 1
   PROTON_SKIP_PC_SAMPLING_TEST: 1
+  CCACHE_COMPRESS: "true"
 jobs:
   Runner-Preparation:
     runs-on: ubuntu-latest
@@ -39,6 +41,11 @@ jobs:
         if: github.event_name == 'pull_request'
         run: |
           echo "enable_integration=true" >> $GITHUB_ENV
+      - name: Decide manual trigger integration test enablement
+        # Always enable integration tests when manually triggered
+        if: github.event_name == 'workflow_dispatch'
+        run: |
+          echo "enable_integration=true" >> $GITHUB_ENV
       - name: Checkout post-submit commits
         if: github.event_name == 'push'
         uses: actions/checkout@v4
@@ -154,6 +161,8 @@ jobs:
     strategy:
       matrix:
         runner: ${{fromJson(needs.Runner-Preparation.outputs.matrix-CUDA)}}
+    env:
+      RUNNER_TYPE: ${{ matrix.runner[0] }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -199,22 +208,28 @@ jobs:
         # "restore" step.  This is to prevent the caches from accumulating stale
         # files over time.
         name: Restore cache of ccache and Triton compilation artifacts
-        if: github.event_name != 'push'
+        id: restore-build-cache
+        if: github.ref != 'refs/heads/main'
         uses: actions/cache/restore@v4
         with:
           path: |
             ~/.triton/cache
-            ~/.cache/ccache
+            ~/.ccache
           # Restore the most recent cache entry.
-          restore-keys: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-
+          restore-keys: |
+            triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-
+            triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-
           # We expect this cache key never to hit and for us to fall back
           # unconditionally to the restore-key, so it doesn't actually matter
           # what we put here (so long as it doesn't hit an existing key).
-          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
-      - name: Inspect cache directory
+          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
+      - name: Inspect cache directories
         run: |
           mkdir -p ~/.triton
-          ls -alh ~/.triton
+          du -h -d 1 ~/.triton
+
+          mkdir -p ~/.ccache
+          du -h -d 1 ~/.ccache
       - name: Update PATH
         run: |
           echo "$HOME/.local/bin" >> $GITHUB_PATH
@@ -224,12 +239,14 @@ jobs:
           python3 -m pip install cython setuptools wheel cmake==3.24 ninja pytest-forked pytest-xdist lit
       - name: Install Triton
         env:
-          TRITON_BUILD_WITH_CCACHE: "true"
           CUDA_HOME: "/usr/local/cuda"
         run: |
           echo "PATH is '$PATH'"
           cd python
-          python3 -m pip install '.[tests]'
+          ccache --zero-stats
+          python3 -m pip install -v '.[tests]'
+      - name: CCache Stats
+        run: ccache --print-stats
       - name: Run lit tests
         run: |
           cd python
@@ -278,6 +295,13 @@ jobs:
           cd third_party/proton/test
           python3 -m pytest -s .
           cd ..
+      - name: Inspect cache directories
+        run: |
+          mkdir -p ~/.triton
+          du -h -d 1 ~/.triton
+
+          mkdir -p ~/.ccache
+          du -h -d 1 ~/.ccache
       - # If we're on branch `main`, save the ccache Triton compilation artifacts
         # to the cache so they can be used by other (non-main) CI runs.
         #
@@ -287,22 +311,17 @@ jobs:
         if: github.ref == 'refs/heads/main'
         uses: actions/cache/save@v4
         with:
-          path: ~/.triton/cache ~/.cache/ccache
-          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
-      - name: Inspect cache directories
-        run: |
-          mkdir -p ~/.triton
-          ls -alh ~/.triton
-          du -sh ~/.triton/**
-
-          mkdir -p ~/.cache/ccache
-          ls -alh ~/.cache/ccache
-          du -sh ~/.cache/ccache
+          path: |
+            ~/.triton/cache
+            ~/.ccache
+          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
   Integration-Tests-AMD:
     needs: Runner-Preparation
     if: needs.Runner-Preparation.outputs.matrix-HIP != ''
     runs-on: ${{ matrix.runner }}
     timeout-minutes: 30
+    env:
+      RUNNER_TYPE: ${{ matrix.runner[1] }}
     strategy:
       matrix:
         runner: ${{fromJson(needs.Runner-Preparation.outputs.matrix-HIP)}}
@@ -355,40 +374,53 @@ jobs:
         # "restore" step.  This is to prevent the caches from accumulating stale
         # files over time.
         name: Restore cache of ccache and Triton compilation artifacts
-        if: github.event_name != 'push'
+        id: restore-build-cache
+        if: github.ref != 'refs/heads/main'
         uses: actions/cache/restore@v4
         with:
           path: |
             ~/.triton/cache
-            ~/.cache/ccache
+            ~/.ccache
           # Restore the most recent cache entry.
-          restore-keys: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-
+          restore-keys: |
+            triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-
+            triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-
           # We expect this cache key never to hit and for us to fall back
           # unconditionally to the restore-key, so it doesn't actually matter
           # what we put here (so long as it doesn't hit an existing key).
-          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
-      - name: Inspect cache directory
+          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
+      - name: Inspect cache directories
         run: |
           mkdir -p ~/.triton
-          ls -alh ~/.triton
+          du -h -d 1 ~/.triton
+
+          mkdir -p ~/.ccache
+          du -h -d 1 ~/.ccache
       - name: Update PATH
         run: |
           echo "/opt/rocm/llvm/bin" >> $GITHUB_PATH
       - name: Install pip dependencies
         run: |
           python3 -m pip install --upgrade pip
           python3 -m pip install lit
+      - name: Install apt dependencies
+        run: |
+          apt update
+          apt install ccache
       - name: Install Triton
         id: amd-install-triton
         run: |
           echo "PATH is '$PATH'"
           pip uninstall -y triton
           cd python
+          ccache --zero-stats
           pip install -v -e '.[tests]'
       - name: Clean up after an unsuccessful build
         if: ${{ !success() && steps.amd-install-triton.outcome != 'success' }}
         run: |
           rm -rf ~/.triton
+      - name: CCache Stats
+        run: ccache --print-stats
       - name: Run lit tests
         run: |
           cd python
@@ -431,6 +463,13 @@ jobs:
           cd python
           cd "build/$(ls build | grep -i cmake)"
           ctest -j32
+      - name: Inspect cache directories
+        run: |
+          mkdir -p ~/.triton
+          du -h -d 1 ~/.triton
+
+          mkdir -p ~/.ccache
+          du -h -d 1 ~/.ccache
       - # If we're on branch `main`, save the ccache Triton compilation artifacts
         # to the cache so they can be used by other (non-main) CI runs.
         #
@@ -440,28 +479,23 @@ jobs:
         if: github.ref == 'refs/heads/main'
         uses: actions/cache/save@v4
         with:
-          path: ~/.triton/cache ~/.cache/ccache
-          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
-      - name: Inspect cache directories
-        run: |
-          mkdir -p ~/.triton
-          ls -alh ~/.triton
-          du -sh ~/.triton/**
-
-          mkdir -p ~/.cache/ccache
-          ls -alh ~/.cache/ccache
-          du -sh ~/.cache/ccache
+          path: |
+            ~/.triton/cache
+            ~/.ccache
+          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
       - name: Clean up caches
         run: |
           rm -rf ~/.triton/cache
   Build-Tests:
     needs: Runner-Preparation
     if: needs.Runner-Preparation.outputs.matrix-MACOS != ''
     runs-on: ${{ matrix.runner }}
-    timeout-minutes: 30
+    timeout-minutes: 40
     strategy:
       matrix:
         runner: ${{fromJson(needs.Runner-Preparation.outputs.matrix-MACOS)}}
+    env:
+      RUNNER_TYPE: ${{ matrix.runner[0] }}
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -470,7 +504,7 @@ jobs:
       - name: Install brew dependencies
         run: |
           brew update
-          brew install ccache llvm@19 lld
+          brew install ccache llvm@19 lld coreutils
       - name: Compute cache keys
         id: cache-key
         run: |
@@ -511,22 +545,28 @@ jobs:
         # "restore" step.  This is to prevent the caches from accumulating stale
         # files over time.
         name: Restore cache of ccache and Triton compilation artifacts
-        if: github.event_name != 'push'
+        id: restore-build-cache
+        if: github.ref != 'refs/heads/main'
         uses: actions/cache/restore@v4
         with:
           path: |
             ~/.triton/cache
-            ~/.cache/ccache
+            ~/.ccache
           # Restore the most recent cache entry.
-          restore-keys: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-
+          restore-keys: |
+            triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-
+            triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-
           # We expect this cache key never to hit and for us to fall back
           # unconditionally to the restore-key, so it doesn't actually matter
           # what we put here (so long as it doesn't hit an existing key).
-          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
-      - name: Inspect cache directory
+          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
+      - name: Inspect cache directories
         run: |
           mkdir -p ~/.triton
-          ls -alh ~/.triton
+          du -h -d 1 ~/.triton
+
+          mkdir -p ~/.ccache
+          du -h -d 1 ~/.ccache
       - name: Update PATH
         run: |
           echo "$HOME/.local/bin" >> $GITHUB_PATH
@@ -539,7 +579,6 @@ jobs:
           python3 -m pip install cython setuptools wheel cmake==3.24 ninja pytest-xdist lit pybind11
       - name: Install Triton
         env:
-          TRITON_BUILD_WITH_CCACHE: "true"
           TRITON_BUILD_WITH_O1: "true"
           # macos-latest has 3 vcpus and 7GB DRAM, to save memory we limit the number of jobs to 3
           # https://docs.github.com/en/actions/using-github-hosted-runners/about-github-hosted-runners/about-github-hosted-runners#standard-github-hosted-runners-for-public-repositories
@@ -548,7 +587,17 @@ jobs:
           source ~/.venv/bin/activate
           echo "PATH is '$PATH'"
           cd python
-          python3 -m pip install --no-build-isolation .
+          ccache --zero-stats
+          python3 -m pip install -v --no-build-isolation .
+      - name: CCache Stats
+        run: ccache --print-stats
+      - name: Inspect cache directories
+        run: |
+          mkdir -p ~/.triton
+          du -h -d 1 ~/.triton
+
+          mkdir -p ~/.ccache
+          du -h -d 1 ~/.ccache
       - # If we're on branch `main`, save the ccache Triton compilation artifacts
         # to the cache so they can be used by other (non-main) CI runs.
         #
@@ -558,14 +607,7 @@ jobs:
         if: github.ref == 'refs/heads/main'
         uses: actions/cache/save@v4
         with:
-          path: ~/.triton/cache ~/.cache/ccache
-          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ runner.name }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}
-      - name: Inspect cache directories
-        run: |
-          mkdir -p ~/.triton
-          ls -alh ~/.triton
-          du -sh ~/.triton/**
-
-          mkdir -p ~/.cache/ccache
-          ls -alh ~/.cache/ccache
-          du -sh ~/.cache/ccache
+          path: |
+            ~/.triton/cache
+            ~/.ccache
+          key: triton-artifacts-${{ runner.os }}-${{ runner.arch }}-${{ env.RUNNER_TYPE }}-llvm-${{ steps.cache-key.outputs.llvm }}-${{ steps.cache-key.outputs.datetime }}