Fix GHA caches #267
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: CI Linux | |
| on: | |
| workflow_call: | |
| workflow_dispatch: | |
| pull_request: | |
| merge_group: | |
| push: | |
| branches: | |
| - main | |
| schedule: | |
| # At minute 0 past every 6th hour. (see https://crontab.guru) | |
| # this job is to keep the ccache cache warm | |
| - cron: '0 */6 * * *' | |
| concurrency: | |
| # A PR number if a pull request and otherwise the commit hash. This cancels | |
| # queued and in-progress runs for the same PR (presubmit) or commit | |
| # (postsubmit). | |
| group: ci-build-test-cpp-linux-${{ github.event.number || github.sha }} | |
| cancel-in-progress: true | |
| permissions: | |
| contents: read | |
| # required to delete cache | |
| # https://docs.github.com/en/rest/actions/cache?apiVersion=2022-11-28#delete-github-actions-caches-for-a-repository-using-a-cache-key | |
| actions: write | |
| jobs: | |
| build_and_ctest: | |
| name: Build and Test (linux, ASSERTIONS) | |
| runs-on: nod-ai-shared-cpubuilder-manylinux-x86_64 | |
| strategy: | |
| fail-fast: true | |
| env: | |
| CACHE_DIR: ${{ github.workspace }}/.container-cache | |
| # either the PR number or `branch-N` where N always increments | |
| CACHE_KEY: linux-build-test-cpp-asserts-manylinux-v2-${{ github.event.number || format('{0}-{1}', github.ref_name, github.run_number) }} | |
| steps: | |
| - name: Set unified TZ | |
| uses: szenius/[email protected] | |
| with: | |
| # this is an arbitrary choice | |
| timezoneLinux: "Asia/Singapore" | |
| timezoneMacos: "Asia/Singapore" | |
| timezoneWindows: "Singapore Standard Time" | |
| - name: Configure local git mirrors | |
| run: | | |
| /gitmirror/scripts/trigger_update_mirrors.sh | |
| /gitmirror/scripts/git_config.sh | |
| - name: "Checking out repository" | |
| uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 | |
| with: | |
| submodules: recursive | |
| - name: Install deps | |
| run: | | |
| yum remove -y openssl-devel zlib-devel || true | |
| dnf install -y almalinux-release-devel | |
| type -p yum-config-manager >/dev/null || yum -y install yum-utils | |
| yum-config-manager -y --add-repo https://cli.github.com/packages/rpm/gh-cli.repo | |
| yum install -y protobuf-devel protobuf-compiler gh | |
| - name: Sync source deps | |
| run: | | |
| python ./sync_deps.py | |
| - name: Python deps | |
| run: | | |
| pip install "numpy<2" pyyaml "pybind11[global]==2.10.3" nanobind | |
| - name: Enable cache | |
| uses: actions/cache/restore@v3 | |
| with: | |
| path: ${{ env.CACHE_DIR }} | |
| key: ${{ env.CACHE_KEY }} | |
| restore-keys: linux-build-test-cpp- | |
| - name: Build packages | |
| run: | | |
| export cache_dir="${{ env.CACHE_DIR }}" | |
| bash build_tools/ci/build_test_cpp.sh | |
| - name: Create artifacts | |
| if: ${{ !cancelled() }} | |
| run: | | |
| tar cf iree-dist-linux.tar -C iree-install . | |
| - name: Upload artifacts | |
| uses: actions/upload-artifact@v4 | |
| if: ${{ !cancelled() }} | |
| with: | |
| name: linux_x86_64_release_packages | |
| path: iree-dist-linux.tar | |
| if-no-files-found: warn | |
| - name: Overwrite cache | |
| if: ${{ !cancelled() }} | |
| continue-on-error: true | |
| env: | |
| # required to run gh with privileges | |
| GH_TOKEN: ${{ github.token }} | |
| run: | | |
| gh extension install actions/gh-actions-cache | |
| gh actions-cache delete ${{ env.CACHE_KEY }} --confirm -R ${{ github.repository }} | |
| - name: Save cache | |
| uses: actions/cache/save@v3 | |
| if: ${{ !cancelled() }} | |
| with: | |
| path: ${{ env.CACHE_DIR }} | |
| key: ${{ env.CACHE_KEY }} | |
| test_linux: | |
| name: E2E Test linux | |
| needs: build_and_ctest | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| runs-on: [linux-phoenix] | |
| runs-on: ${{ matrix.runs-on }} | |
| env: | |
| XILINXD_LICENSE_FILE: /opt/xilinx/Xilinx.lic | |
| steps: | |
| - name: "Checking out repository" # for test scripts | |
| uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0 | |
| with: | |
| submodules: false # not required for testbench | |
| - name: Download artifacts | |
| uses: actions/download-artifact@v4 | |
| with: | |
| name: linux_x86_64_release_packages | |
| - name: Extract artifact | |
| run: | | |
| mkdir iree-install | |
| tar -xf iree-dist-linux.tar -C iree-install | |
| bash build_tools/download_peano.sh | |
| - name: Create venv and install dependencies | |
| run: | | |
| python3 -m venv .venv | |
| source .venv/bin/activate | |
| pip install -r tests/matmul/requirements.txt | |
| - name: E2E correctness matmul test | |
| run: | | |
| source .venv/bin/activate | |
| # Without this additional line an error like | |
| # | |
| # [XRT] ERROR: Failed to allocate host memory buffer (mmap(len=10616832, prot=3, flags=8193, offset=4294967296) | |
| # failed (err=11): Resource temporarily unavailable), make sure host bank is enabled (see xbutil configure --host-mem) | |
| # iree-amd-aie/runtime/src/iree-amd-aie/driver/xrt/direct_allocator.cc:179: RESOURCE_EXHAUSTED; could not allocate | |
| # memory for buffer; while invoking C++ function matmul_test.generate_random_matrix; while calling import; | |
| # | |
| # might be observed when too much memory is allocated. For example this | |
| # error was seen when running a bf16->f32 matmul with m=n=k=2304. | |
| # | |
| # This line was suggested at https://github.com/Xilinx/mlir-air/issues/566 | |
| # | |
| # Note that this is only half of the fix. It is also necessary that | |
| # the machine that CI is running on has permission to run this line. | |
| # | |
| # This permission can be adding by adding the line | |
| # ``` | |
| # %github ALL=(ALL) NOPASSWD: /usr/bin/prlimit * | |
| # ``` | |
| # | |
| # to the file /etc/sudoers.d/github, which can be done by running | |
| # ``` | |
| # sudo visudo -f /etc/sudoers.d/github | |
| # ``` | |
| # on the guthub CI machine. | |
| sudo prlimit -lunlimited --pid $$ | |
| source /opt/xilinx/xrt/setup.sh | |
| bash build_tools/ci/run_matmul_test.sh \ | |
| test_matmuls \ | |
| iree-install \ | |
| $PWD/llvm-aie \ | |
| /opt/xilinx/xrt \ | |
| /opt/Xilinx/Vitis/2024.2 | |
| - name : Smoke E2E comparison flag test | |
| run: | | |
| source .venv/bin/activate | |
| source /opt/xilinx/xrt/setup.sh | |
| python3 build_tools/ci/cpu_comparison/run_test.py \ | |
| test_aie_vs_cpu \ | |
| iree-install \ | |
| $PWD/llvm-aie \ | |
| --xrt-dir /opt/xilinx/xrt \ | |
| --test-set='Smoke' \ | |
| --do-not-run-aie | |
| # Assert that output.log is empty (because verbose=0) | |
| if [ -s output.log ]; then | |
| echo "output.log is not empty:" | |
| cat output.log | |
| exit 1 | |
| else | |
| echo "output.log is empty" | |
| fi | |
| - name : E2E comparison of AIE to llvm-cpu | |
| run: | | |
| source .venv/bin/activate | |
| source /opt/xilinx/xrt/setup.sh | |
| python3 build_tools/ci/cpu_comparison/run_test.py \ | |
| test_aie_vs_cpu \ | |
| $PWD/iree-install \ | |
| $PWD/llvm-aie \ | |
| --xrt-dir /opt/xilinx/xrt \ | |
| --vitis-dir /opt/Xilinx/Vitis/2024.2 \ | |
| --reset-npu-between-runs -v | |
| - name: Printing IR from aie2xclbin | |
| run: | | |
| source .venv/bin/activate | |
| source /opt/xilinx/xrt/setup.sh | |
| bash build_tools/ci/print_ir_aie2xclbin/print_ir_aie2xclbin.sh \ | |
| iree-install \ | |
| print_ir_aie2xclbin_results \ | |
| $PWD/llvm-aie |