Merge remote-tracking branch 'NVIDIA/develop' into nvdisasm_search

NVIDIA · Aug 1, 2024 · 8efe772 · 8efe772
2 parents 7abcd36 + 2ecc60d
commit 8efe772
Show file tree

Hide file tree

Showing 29 changed files with 2,703 additions and 126 deletions.
diff --git a/.flake8 b/.flake8
@@ -0,0 +1,52 @@
+[flake8]
+ignore =
+    # Extra space in brackets
+    E20,
+    # Multiple spaces around ","
+    E231,E241,
+    # Comments
+    E26,
+    # Assigning lambda expression
+    E731,
+    # Ambiguous variable names
+    E741,
+    # line break before binary operator
+    W503,
+    # line break after binary operator
+    W504,
+max-line-length = 80
+
+exclude =
+    __pycache__
+    .git
+    *.pyc
+    *~
+    *.o
+    *.so
+    *.cpp
+    *.c
+    *.h
+
+per-file-ignores =
+    # Slightly long line in the standard version file
+    numba_cuda/_version.py: E501
+    # "Unused" imports / potentially undefined names in init files
+    numba_cuda/numba/cuda/__init__.py:F401,F403,F405
+    numba_cuda/numba/cuda/simulator/__init__.py:F401,F403
+    numba_cuda/numba/cuda/simulator/cudadrv/__init__.py:F401
+    # Ignore star imports, unused imports, and "may be defined by star imports"
+    # errors in device_init because its purpose is to bring together a lot of
+    # the public API to be star-imported in numba.cuda.__init__
+    numba_cuda/numba/cuda/device_init.py:F401,F403,F405
+    # libdevice.py is an autogenerated file containing stubs for all the device
+    # functions. Some of the lines in docstrings are a little over-long, as they
+    # contain the URLs of the reference pages in the online libdevice
+    # documentation.
+    numba_cuda/numba/cuda/libdevice.py:E501
+    # Ignore too-long lines in the doc examples, prioritising readability
+    # in the docs over line length in the example source (especially given that
+    # the test code is already indented by 8 spaces)
+    numba_cuda/numba/cuda/tests/doc_examples/test_random.py:E501
+    numba_cuda/numba/cuda/tests/doc_examples/test_cg.py:E501
+    numba_cuda/numba/cuda/tests/doc_examples/test_matmul.py:E501
+    numba_cuda/numba/tests/doc_examples/test_interval_example.py:E501
diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml
diff --git a/.github/workflows/conda-python-build.yaml b/.github/workflows/conda-python-build.yaml
@@ -0,0 +1,125 @@
+on:
+  workflow_call:
+    inputs:
+      build_type:
+        required: true
+        type: string
+      branch:
+        type: string
+      date:
+        type: string
+      sha:
+        type: string
+      repo:
+        type: string
+      node_type:
+        type: string
+        default: "cpu8"
+      script:
+        type: string
+        default: "ci/build_python.sh"
+      matrix_filter:
+        type: string
+        default: "."
+      upload_to_anaconda:
+        type: boolean
+        required: false
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  actions: read
+  checks: none
+  contents: read
+  deployments: none
+  discussions: none
+  id-token: write
+  issues: none
+  packages: read
+  pages: none
+  pull-requests: read
+  repository-projects: none
+  security-events: none
+  statuses: none
+
+jobs:
+  compute-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      MATRIX: ${{ steps.compute-matrix.outputs.MATRIX }}
+    steps:
+      - name: Compute Build Matrix
+        id: compute-matrix
+        run: |
+          set -eo pipefail
+
+          # please keep the matrices sorted in ascending order by the following:
+          #
+          #     [ARCH, PY_VER, CUDA_VER, LINUX_VER]
+          #
+          export MATRIX="
+          # amd64
+          - { ARCH: 'amd64', PY_VER: '3.9',  CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'amd64', PY_VER: '3.9',  CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'amd64', PY_VER: '3.10', CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'amd64', PY_VER: '3.10', CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'amd64', PY_VER: '3.11', CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'amd64', PY_VER: '3.11', CUDA_VER: '12.2.2', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'amd64', PY_VER: '3.11', CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04' }
+          # arm64
+          - { ARCH: 'arm64', PY_VER: '3.9',  CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'arm64', PY_VER: '3.9',  CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'arm64', PY_VER: '3.10', CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'arm64', PY_VER: '3.10', CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'arm64', PY_VER: '3.11', CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'arm64', PY_VER: '3.11', CUDA_VER: '12.2.2', LINUX_VER: 'ubuntu22.04' }
+          - { ARCH: 'arm64', PY_VER: '3.11', CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04' }
+          "
+
+          MATRIX="$(
+            yq -n -o json 'env(MATRIX)' | \
+            jq -c '${{ inputs.matrix_filter }} | if (. | length) > 0 then {include: .} else "Error: Empty matrix\n" | halt_error(1) end'
+          )"
+
+          echo "MATRIX=${MATRIX}" | tee --append "${GITHUB_OUTPUT}"
+  build:
+    needs: compute-matrix
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.compute-matrix.outputs.MATRIX) }}
+    runs-on: "linux-${{ matrix.ARCH }}-${{ inputs.node_type }}"
+    env:
+      RAPIDS_ARTIFACTS_DIR: ${{ github.workspace }}/artifacts
+    container:
+      image: rapidsai/ci-conda:cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}
+      env:
+        RAPIDS_BUILD_TYPE: ${{ inputs.build_type }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          repository: ${{ inputs.repo }}
+          ref: ${{ inputs.sha }}
+          fetch-depth: 0
+      - name: Standardize repository information
+        run: |
+          echo "RAPIDS_REPOSITORY=${{ inputs.repo || github.repository }}" >> "${GITHUB_ENV}"
+          echo "RAPIDS_SHA=$(git rev-parse HEAD)" >> "${GITHUB_ENV}"
+          echo "RAPIDS_REF_NAME=${{ inputs.branch || github.ref_name }}" >> "${GITHUB_ENV}"
+          echo "RAPIDS_NIGHTLY_DATE=${{ inputs.date }}" >> "${GITHUB_ENV}"
+      - name: Python build
+        run: ${{ inputs.script }}
+        env:
+          GH_TOKEN: ${{ github.token }}
+      - name: Upload conda repo
+        if: "!cancelled()"
+        uses: actions/upload-artifact@v4
+        with:
+          name: conda-repo
+          path: "/tmp/conda-bld-output"
+      - name: Publish conda package
+        if: inputs.upload_to_anaconda
+        run: "ci/upload_conda.sh"
+        env:
+          CONDA_TOKEN: ${{ secrets.NVIDIA_CONDA_TOKEN }}
diff --git a/.github/workflows/conda-python-tests.yaml b/.github/workflows/conda-python-tests.yaml
@@ -0,0 +1,155 @@
+on:
+  workflow_call:
+    inputs:
+      build_type:
+        required: true
+        type: string
+      branch:
+        type: string
+      date:
+        type: string
+      sha:
+        type: string
+      repo:
+        type: string
+      script:
+        type: string
+        default: "ci/test_python.sh"
+      run_codecov:
+        type: boolean
+        default: true
+      matrix_filter:
+        type: string
+        default: "."
+      container-options:
+        required: false
+        type: string
+        default: "-e _NOOP"
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  actions: read
+  checks: none
+  contents: read
+  deployments: none
+  discussions: none
+  id-token: write
+  issues: none
+  packages: read
+  pages: none
+  pull-requests: read
+  repository-projects: none
+  security-events: none
+  statuses: none
+
+jobs:
+  compute-matrix:
+    runs-on: ubuntu-latest
+    env:
+      BUILD_TYPE: ${{ inputs.build_type }}
+    outputs:
+      MATRIX: ${{ steps.compute-matrix.outputs.MATRIX }}
+    steps:
+      - name: Validate Test Type
+        run: |
+          if [[ "$BUILD_TYPE" != "pull-request" ]] && [[ "$BUILD_TYPE" != "nightly" ]]; then
+              echo "Invalid build type! Must be 'nightly' or 'pull-request'."
+              exit 1
+          fi
+      - name: Compute Python Test Matrix
+        id: compute-matrix
+        run: |
+          set -eo pipefail
+
+          # please keep the matrices sorted in ascending order by the following:
+          #
+          #     [ARCH, PY_VER, CUDA_VER, LINUX_VER, GPU, DRIVER]
+          #
+          export MATRICES="
+            pull-request:
+              # amd64
+              - { ARCH: 'amd64', PY_VER: '3.9',  CUDA_VER: '11.8.0', LINUX_VER: 'rockylinux8', GPU: 'v100', DRIVER: 'earliest' }
+              - { ARCH: 'amd64', PY_VER: '3.11', CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04', GPU: 'v100', DRIVER: 'latest'   }
+              # arm64
+              - { ARCH: 'arm64', PY_VER: '3.10', CUDA_VER: '12.0.1', LINUX_VER: 'ubuntu20.04', GPU: 'a100', DRIVER: 'latest'   }
+            nightly:
+              # amd64
+              - { ARCH: 'amd64', PY_VER: '3.9',  CUDA_VER: '11.4.3', LINUX_VER: 'rockylinux8', GPU: 'v100', DRIVER: 'earliest' }
+              - { ARCH: 'amd64', PY_VER: '3.9',  CUDA_VER: '11.4.3', LINUX_VER: 'ubuntu20.04', GPU: 'v100', DRIVER: 'latest'   }
+              - { ARCH: 'amd64', PY_VER: '3.10', CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04', GPU: 'v100', DRIVER: 'latest'   }
+              - { ARCH: 'amd64', PY_VER: '3.10', CUDA_VER: '12.0.1', LINUX_VER: 'rockylinux8', GPU: 'v100', DRIVER: 'latest'   }
+              - { ARCH: 'amd64', PY_VER: '3.11', CUDA_VER: '12.5.1', LINUX_VER: 'ubuntu22.04', GPU: 'v100', DRIVER: 'latest'   }
+              # arm64
+              - { ARCH: 'arm64', PY_VER: '3.9',  CUDA_VER: '11.4.3', LINUX_VER: 'ubuntu20.04', GPU: 'a100', DRIVER: 'latest'   }
+              - { ARCH: 'arm64', PY_VER: '3.10', CUDA_VER: '12.0.1', LINUX_VER: 'ubuntu22.04', GPU: 'a100', DRIVER: 'latest'   }
+              - { ARCH: 'arm64', PY_VER: '3.11', CUDA_VER: '11.8.0', LINUX_VER: 'ubuntu22.04', GPU: 'a100', DRIVER: 'latest'   }
+              - { ARCH: 'arm64', PY_VER: '3.11', CUDA_VER: '12.2.2', LINUX_VER: 'rockylinux8', GPU: 'a100', DRIVER: 'latest'   }
+          "
+
+          TEST_MATRIX=$(yq -n 'env(MATRICES) | .[strenv(BUILD_TYPE)]')
+          export TEST_MATRIX
+
+          MATRIX="$(
+            yq -n -o json 'env(TEST_MATRIX)' | \
+            jq -c '${{ inputs.matrix_filter }} | if (. | length) > 0 then {include: .} else "Error: Empty matrix\n" | halt_error(1) end'
+          )"
+
+          echo "MATRIX=${MATRIX}" | tee --append "${GITHUB_OUTPUT}"
+  tests:
+    needs: compute-matrix
+    strategy:
+      fail-fast: false
+      matrix: ${{ fromJSON(needs.compute-matrix.outputs.MATRIX) }}
+    runs-on: "linux-${{ matrix.ARCH }}-gpu-${{ matrix.GPU }}-${{ matrix.DRIVER }}-1"
+    env:
+      RAPIDS_COVERAGE_DIR: ${{ github.workspace }}/coverage-results
+      RAPIDS_TESTS_DIR: ${{ github.workspace }}/test-results
+      RAPIDS_ARTIFACTS_DIR: ${{ github.workspace }}/artifacts
+    container:
+      image: rapidsai/ci-conda:cuda${{ matrix.CUDA_VER }}-${{ matrix.LINUX_VER }}-py${{ matrix.PY_VER }}
+      options: ${{ inputs.container-options }}
+      env:
+        RAPIDS_BUILD_TYPE: ${{ inputs.build_type }}
+        NVIDIA_VISIBLE_DEVICES: ${{ env.NVIDIA_VISIBLE_DEVICES }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          repository: ${{ inputs.repo }}
+          ref: ${{ inputs.sha }}
+          fetch-depth: 0
+      - uses: actions/download-artifact@v4
+        name: conda-repo
+      - name: Display structure of downloaded files
+        run: ls -R
+      - name: Standardize repository information
+        run: |
+          echo "RAPIDS_REPOSITORY=${{ inputs.repo || github.repository }}" >> "${GITHUB_ENV}"
+          echo "RAPIDS_SHA=$(git rev-parse HEAD)" >> "${GITHUB_ENV}"
+          echo "RAPIDS_REF_NAME=${{ inputs.branch || github.ref_name }}" >> "${GITHUB_ENV}"
+          echo "RAPIDS_NIGHTLY_DATE=${{ inputs.date }}" >> "${GITHUB_ENV}"
+      - name: Python tests
+        run: ${{ inputs.script }}
+        env:
+          GH_TOKEN: ${{ github.token }}
+      - name: Generate test report
+        uses: test-summary/[email protected]
+        with:
+          paths: "${{ env.RAPIDS_TESTS_DIR }}/*.xml"
+        if: always()
+      - name: Run codecov
+        if: inputs.run_codecov
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+        run: |
+          codecovcli \
+            -v \
+            upload-process \
+            -C ${{ github.sha }} \
+            -s "${RAPIDS_COVERAGE_DIR}" \
+            --handle-no-reports-found
+      - name: Upload additional artifacts
+        if: "!cancelled()"
+        run: rapids-upload-artifacts-dir cuda${RAPIDS_CUDA_VERSION%%.*}_$(arch)_py${RAPIDS_PY_VERSION//.}