# Linux variant of the SPIRV CI: builds LLVM/Clang/translator/Comgr in
# one job and runs SPIRV-relevant test suites in parallel test jobs that
# consume a GHA artifact uploaded by the build job.

name: SPIRV Compiler CI - Linux

on:
  workflow_call:

jobs:
  # =====================================================================
  # Build LLVM + Clang + amd-llvm-spirv + device-libs + Comgr.
  # Strip binaries and upload the build trees as a single artifact for
  # the test jobs to consume.
  # =====================================================================
  build:
    name: Build
    runs-on: azure-linux-scale-rocm
    timeout-minutes: 120
    container:
      image: ghcr.io/rocm/therock_build_manylinux_x86_64@sha256:702a5133851e6d1daf1207d2c9fbb01c2667914a5b6dc5a01faeb3ce66ea6421
    outputs:
      llvm_project_sha: ${{ steps.resolve_llvm_sha.outputs.sha }}

    steps:
      # ---- Checkout ---------------------------------------------------------
      # llvm-project at amd-staging tip provides the host LLVM/Clang/LLD plus
      # the amd/ subprojects (device-libs, comgr). The SPIRV translator PR
      # head is overlaid in-tree under llvm/projects/.
      - name: Checkout llvm-project (amd-staging)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          repository: ROCm/llvm-project
          ref: amd-staging
          path: llvm-project
          fetch-depth: 1
          persist-credentials: false

      # Capture the resolved amd-staging SHA so test jobs can pin to the
      # exact commit this build used. Without this, test jobs re-resolve
      # `amd-staging` and may land on a newer commit if upstream merged
      # mid-run, triggering a cascade rebuild against an older build.ninja.
      - name: Resolve llvm-project SHA
        id: resolve_llvm_sha
        run: |
          SHA=$(git -C llvm-project rev-parse HEAD)
          echo "sha=$SHA" >> "$GITHUB_OUTPUT"
          echo "Pinned llvm-project SHA for test jobs: $SHA"

      - name: Checkout SPIRV-LLVM-Translator (PR head)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          path: llvm-project/llvm/projects/SPIRV-LLVM-Translator
          fetch-depth: 1
          persist-credentials: false

      # ---- Build LLVM + Clang + LLD + in-tree SPIRV translator --------------
      - name: Configure LLVM
        run: |
          cmake -G Ninja -S llvm-project/llvm -B build \
            -DCMAKE_BUILD_TYPE=Release \
            -DLLVM_ENABLE_ASSERTIONS=ON \
            -DLLVM_ENABLE_PROJECTS="clang;lld" \
            -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86;SPIRV" \
            -DLLVM_INCLUDE_TESTS=ON \
            -DLLVM_INSTALL_GTEST=ON \
            -DLLVM_LIT_ARGS="-sv --no-progress-bar"

      - name: Build LLVM + Clang + amd-llvm-spirv + test deps
        # *-test-depends pull in all tools needed for lit (FileCheck, not,
        # llc, llvm-*, clang, opt, etc.) and stay current with upstream.
        run: ninja -C build llvm-test-depends clang-test-depends amd-llvm-spirv

      # ---- Build device-libs (standalone, against built LLVM) --------------
      - name: Configure device-libs
        run: |
          cmake -G Ninja -S llvm-project/amd/device-libs -B build-device-libs \
            -DCMAKE_BUILD_TYPE=Release \
            -DCMAKE_PREFIX_PATH=$PWD/build \
            -DLLVM_DIR=$PWD/build/lib/cmake/llvm

      - name: Build device-libs
        run: ninja -C build-device-libs

      # ---- Build Comgr (standalone, against built LLVM + device-libs) ------
      - name: Configure Comgr
        # LLVM_EXTERNAL_SPIRV_LLVM_TRANSLATOR_SOURCE_DIR points Comgr at
        # the in-tree translator headers so COMGR_SPIRV_TRANSLATOR_AVAILABLE
        # turns ON (otherwise translator-dependent lit tests are UNSUPPORTED).
        run: |
          cmake -G Ninja -S llvm-project/amd/comgr -B build-comgr \
            -DCMAKE_BUILD_TYPE=Release \
            -DCMAKE_PREFIX_PATH="$PWD/build;$PWD/build-device-libs" \
            -DLLVM_DIR=$PWD/build/lib/cmake/llvm \
            -DLLVM_EXTERNAL_SPIRV_LLVM_TRANSLATOR_SOURCE_DIR=$PWD/llvm-project/llvm/projects/SPIRV-LLVM-Translator \
            -DBUILD_TESTING=ON

      - name: Build Comgr
        run: ninja -C build-comgr amd_comgr

      # ---- Strip + upload artifact -----------------------------------------
      # Strip binaries to keep the artifact under GHA's 10GB cap and shorten
      # upload/download time. Tests don't need debug symbols. `--strip-unneeded`
      # preserves dynamic symbols needed at link/load time.
      - name: Strip binaries
        run: |
          find build build-comgr build-device-libs \
            -type f \( -executable -o -name '*.so*' -o -name '*.a' \) \
            -exec strip --strip-unneeded {} + 2>/dev/null || true

      # Tar before upload: actions/upload-artifact@v4 strips +x bits and
      # excludes hidden files (loses FetchContent .git dirs).
      - name: Tar build trees
        run: tar -cf linux-build-tree.tar build build-comgr build-device-libs

      - name: Upload build tree artifact
        uses: actions/upload-artifact@v4
        with:
          name: linux-build-tree
          path: linux-build-tree.tar
          retention-days: 1
          compression-level: 6
          if-no-files-found: error

  # =====================================================================
  # Test - SPIRV translator lit (with PR-head vs amd-staging baseline diff)
  # =====================================================================
  # Non-blocking: upstream Khronos breaks ~1 translator lit test per week
  # (spirv-val drift, LLVM IR changes vs DebugInfo tests, DCE). Their fixes
  # typically land within a day; our daily upstream-merge cron pulls them
  # in. Blocking here would gate unrelated PRs during those windows. The
  # baseline run partitions failures into new / fixed / pre-existing so
  # AMD-side regressions stay visible.
  test_translator_lit:
    name: Test SPIRV translator lit
    needs: build
    runs-on: azure-linux-scale-rocm
    timeout-minutes: 30
    container:
      image: ghcr.io/rocm/therock_build_manylinux_x86_64@sha256:702a5133851e6d1daf1207d2c9fbb01c2667914a5b6dc5a01faeb3ce66ea6421

    steps:
      - name: Checkout llvm-project (pinned to Build job SHA)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          repository: ROCm/llvm-project
          ref: ${{ needs.build.outputs.llvm_project_sha }}
          path: llvm-project
          fetch-depth: 1
          persist-credentials: false

      - name: Checkout SPIRV-LLVM-Translator (PR head)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          path: llvm-project/llvm/projects/SPIRV-LLVM-Translator
          fetch-depth: 1
          persist-credentials: false

      - name: Download build tree artifact
        uses: actions/download-artifact@v4
        with:
          name: linux-build-tree

      # touch build.ninja so it's newer than CMakeCache.txt — without it
      # tar -m's per-file mtimes can trigger a cmake regen + cascade rebuild.
      - name: Untar build trees
        run: |
          tar -xmf linux-build-tree.tar
          touch build/build.ninja build-comgr/build.ninja build-device-libs/build.ninja

      - name: Test - SPIRV Translator (check-amd-llvm-spirv) [PR head]
        id: check_spirv_xlator
        continue-on-error: true
        run: |
          set -o pipefail
          ninja -C build check-amd-llvm-spirv 2>&1 | tee build/check-amd-llvm-spirv.log

      - name: Capture PR head translator failures
        if: always()
        run: |
          grep -oE '^FAIL: LLVM_SPIRV :: \S+' build/check-amd-llvm-spirv.log \
            | sort -u > build/spirv-fails-pr.txt || true
          echo "PR head failures:"; cat build/spirv-fails-pr.txt

      - name: Switch translator to amd-staging tip for baseline
        if: always()
        run: |
          cd llvm-project/llvm/projects/SPIRV-LLVM-Translator
          git fetch --depth=1 origin amd-staging
          git checkout FETCH_HEAD

      - name: Test - SPIRV Translator [baseline amd-staging]
        # Re-run the lit suite with the translator at amd-staging tip so the
        # gating step can flag only PR-introduced failures (filtering out
        # pre-existing baseline failures). Incremental rebuild — only
        # translator objects change.
        if: always()
        id: check_spirv_baseline
        continue-on-error: true
        run: |
          set -o pipefail
          # Re-configure to pick up any CMakeLists / file-list changes in the swap
          cmake -G Ninja -S llvm-project/llvm -B build
          ninja -C build check-amd-llvm-spirv 2>&1 \
            | tee build/check-amd-llvm-spirv-baseline.log

      - name: Capture baseline translator failures
        # Split from the lit step so a non-zero ninja exit (lit failures +
        # set -o pipefail under bash -e) doesn't skip this grep.
        if: always()
        run: |
          grep -oE '^FAIL: LLVM_SPIRV :: \S+' build/check-amd-llvm-spirv-baseline.log \
            | sort -u > build/spirv-fails-baseline.txt || true
          echo "Baseline failures:"; cat build/spirv-fails-baseline.txt

      # Fail the job on real regressions (PR head FAILs that aren't on
      # amd-staging baseline). Pre-existing baseline failures don't block.
      - name: Gate - new translator lit failures
        if: always()
        run: |
          if [ ! -f build/spirv-fails-pr.txt ] || [ ! -f build/spirv-fails-baseline.txt ]; then
            echo "::warning::Could not compute new-failure delta (missing pr.txt or baseline.txt); not gating."
            exit 0
          fi
          new=$(comm -23 build/spirv-fails-pr.txt build/spirv-fails-baseline.txt)
          if [ -n "$new" ]; then
            count=$(printf '%s\n' "$new" | wc -l)
            echo "::error::$count new translator lit failure(s) introduced by this PR:"
            printf '%s\n' "$new" | sed 's/^/::error::  /'
            exit 1
          fi
          echo "No new translator lit failures vs amd-staging baseline."

  # =====================================================================
  # Test - LLVM SPIRV codegen lit suite
  # =====================================================================
  test_codegen:
    name: Test LLVM SPIRV codegen
    needs: build
    runs-on: azure-linux-scale-rocm
    timeout-minutes: 15
    container:
      image: ghcr.io/rocm/therock_build_manylinux_x86_64@sha256:702a5133851e6d1daf1207d2c9fbb01c2667914a5b6dc5a01faeb3ce66ea6421

    steps:
      - name: Checkout llvm-project (pinned to Build job SHA)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          repository: ROCm/llvm-project
          ref: ${{ needs.build.outputs.llvm_project_sha }}
          path: llvm-project
          fetch-depth: 1
          persist-credentials: false

      - name: Checkout SPIRV-LLVM-Translator (PR head)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          path: llvm-project/llvm/projects/SPIRV-LLVM-Translator
          fetch-depth: 1
          persist-credentials: false

      - name: Download build tree artifact
        uses: actions/download-artifact@v4
        with:
          name: linux-build-tree

      # touch build.ninja so it's newer than CMakeCache.txt — without it
      # tar -m's per-file mtimes can trigger a cmake regen + cascade rebuild.
      - name: Untar build trees
        run: |
          tar -xmf linux-build-tree.tar
          touch build/build.ninja build-comgr/build.ninja build-device-libs/build.ninja

      - name: Test - LLVM SPIRV backend (check-llvm-codegen-spirv)
        run: ninja -C build check-llvm-codegen-spirv

  # =====================================================================
  # Test - Comgr (lit + gtest + ctest)
  # =====================================================================
  test_comgr:
    name: Test Comgr
    needs: build
    runs-on: azure-linux-scale-rocm
    timeout-minutes: 30
    container:
      image: ghcr.io/rocm/therock_build_manylinux_x86_64@sha256:702a5133851e6d1daf1207d2c9fbb01c2667914a5b6dc5a01faeb3ce66ea6421

    steps:
      - name: Checkout llvm-project (pinned to Build job SHA)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          repository: ROCm/llvm-project
          ref: ${{ needs.build.outputs.llvm_project_sha }}
          path: llvm-project
          fetch-depth: 1
          persist-credentials: false

      - name: Checkout SPIRV-LLVM-Translator (PR head)
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
        with:
          path: llvm-project/llvm/projects/SPIRV-LLVM-Translator
          fetch-depth: 1
          persist-credentials: false

      - name: Download build tree artifact
        uses: actions/download-artifact@v4
        with:
          name: linux-build-tree

      # touch build.ninja so it's newer than CMakeCache.txt — without it
      # tar -m's per-file mtimes can trigger a cmake regen + cascade rebuild.
      - name: Untar build trees
        run: |
          tar -xmf linux-build-tree.tar
          touch build/build.ninja build-comgr/build.ninja build-device-libs/build.ninja

      - name: Test - Comgr (check-comgr)
        # check-comgr depends on test-lit (runs lit suite) and test-unit
        # (runs gtest binaries via its COMMAND block), then runs ctest for
        # the legacy C tests. Single target = all three test layers.
        id: check_comgr
        run: ninja -C build-comgr check-comgr

      - name: Show failed Comgr ctest output
        # check-comgr invokes ctest without --output-on-failure, so failures
        # show "***Failed" with no stderr. Re-run any failed cases verbosely
        # and redirect comgr's internal log buffer to stderr so clang errors
        # from inside amd_comgr_do_action() surface (otherwise comgr just
        # returns AMD_COMGR_STATUS_ERROR with no detail).
        if: failure() && steps.check_comgr.conclusion == 'failure'
        env:
          AMD_COMGR_REDIRECT_LOGS: stderr
        run: ctest --test-dir build-comgr --output-on-failure --rerun-failed