Files
TheRock/.github/workflows/multi_arch_ci_linux.yml
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

371 lines
15 KiB
YAML

# Copyright Advanced Micro Devices, Inc.
# SPDX-License-Identifier: MIT
name: Multi-Arch CI - Linux
on:
workflow_call:
inputs:
build_config:
type: string
description: >-
JSON object with build configuration for this platform. Fields:
artifact_group, per_family_info, dist_amdgpu_families,
build_variant_label, build_variant_cmake_preset,
build_variant_suffix, build_pytorch, build_jax,
build_native_linux, test_python_packages_matrix,
pytorch_build_matrix, jax_build_matrix,
prebuilt_stages, baseline_run_id.
test_labels:
type: string
rocm_package_version:
type: string
rocm_deb_package_version:
type: string
description: ROCm DEB package version for native packages
rocm_rpm_package_version:
type: string
description: ROCm RPM package version for native packages
test_type:
type: string
release_type:
description: 'Release type: "ci", "dev", "nightly", or "prerelease"'
type: string
default: ci
external_repo_config:
description: "JSON config for external repo checkout (repository, ref, checkout_path, source_package, fetch_sources_args)"
type: string
default: ""
changed_projects:
description: 'Comma-separated list of projects to test (e.g., "rocblas,hipblas" or "projects/rocblas"). Empty = run all tests.'
type: string
default: ""
repository:
description: "Repository to checkout. Defaults to github.repository."
type: string
default: ""
ref:
description: "Branch, tag, or SHA to checkout. Defaults to the triggering ref."
type: string
default: ""
permissions:
contents: read
jobs:
copy_prebuilt_stages:
name: Copy Prebuilt Stages
if: ${{ fromJSON(inputs.build_config).prebuilt_stages != '' && fromJSON(inputs.build_config).baseline_run_id != '' }}
runs-on: aws-linux-scale-rocm-prod-rc
permissions:
contents: read
id-token: write
container:
image: python:3.12-slim
steps:
- name: Checking out repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
with:
repository: ${{ inputs.repository || github.repository }}
ref: ${{ inputs.ref }}
- name: Install artifact manager dependencies
run: pip install boto3
- name: Configure AWS credentials for artifact uploads
uses: ./.github/actions/configure_aws_artifacts_credentials
with:
release_type: ${{ inputs.release_type }}
- name: Copy prebuilt stage artifacts
env:
GITHUB_TOKEN: ${{ github.token }}
RELEASE_TYPE: ${{ inputs.release_type }}
run: |
python build_tools/artifact_manager.py copy \
--source-run-id=${{ fromJSON(inputs.build_config).baseline_run_id }} \
--source-repository=${{ fromJSON(inputs.build_config).baseline_repository }} \
--stage="${{ fromJSON(inputs.build_config).prebuilt_stages }}" \
--amdgpu-families="${{ fromJSON(inputs.build_config).dist_amdgpu_families }}" \
--expand-family-to-targets
build_multi_arch_stages:
name: Build Multi-Arch Stages
needs: copy_prebuilt_stages
if: ${{ !cancelled() && !failure() }}
uses: ./.github/workflows/multi_arch_build_portable_linux.yml
secrets: inherit
with:
matrix_per_family_json: ${{ toJSON(fromJSON(inputs.build_config).per_family_info) }}
dist_amdgpu_families: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
artifact_group: ${{ fromJSON(inputs.build_config).artifact_group }}
build_variant_label: ${{ fromJSON(inputs.build_config).build_variant_label }}
build_variant_cmake_preset: ${{ fromJSON(inputs.build_config).build_variant_cmake_preset }}
build_variant_suffix: ${{ fromJSON(inputs.build_config).build_variant_suffix }}
prebuilt_stages: ${{ fromJSON(inputs.build_config).prebuilt_stages }}
build_runs_on: ${{ fromJSON(inputs.build_config).build_runs_on }}
rocm_package_version: ${{ inputs.rocm_package_version }}
release_type: ${{ inputs.release_type }}
external_repo_config: ${{ inputs.external_repo_config }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
validate_artifact_structure:
needs: [build_multi_arch_stages]
name: Validate Artifact Structure
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/test_artifacts_structure.yml
with:
amdgpu_families: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
platform: linux
release_type: ${{ inputs.release_type }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
test_artifacts_per_family:
needs: [copy_prebuilt_stages, build_multi_arch_stages]
name: Test ${{ matrix.family_info.amdgpu_family }}
if: ${{ !failure() && !cancelled() }}
strategy:
fail-fast: false
matrix:
family_info: ${{ fromJSON(inputs.build_config).per_family_info }}
uses: ./.github/workflows/test_artifacts.yml
with:
artifact_group: ${{ fromJSON(inputs.build_config).artifact_group }}
amdgpu_families: ${{ matrix.family_info.amdgpu_family }}
amdgpu_targets: ${{ matrix.family_info.amdgpu_targets }}
test_runs_on: ${{ matrix.family_info.test-runs-on }}
test_type: ${{ inputs.test_type }}
# Per-family test_labels override global test_labels when specified
# Convert array to JSON string for workflow input compatibility
test_labels: ${{ matrix.family_info.test_labels_for_family && toJSON(matrix.family_info.test_labels_for_family) || inputs.test_labels }}
sanity_check_only_for_family: ${{ matrix.family_info.sanity_check_only_for_family }}
changed_projects: ${{ inputs.changed_projects }}
release_type: ${{ inputs.release_type }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
build_native_deb_packages:
needs: [build_multi_arch_stages]
name: Build DEB Packages
if: ${{ !failure() && !cancelled() && fromJSON(inputs.build_config).build_native_linux == true }}
uses: ./.github/workflows/multi_arch_build_native_linux_packages.yml
with:
dist_amdgpu_families: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
rocm_version: ${{ inputs.rocm_deb_package_version || inputs.rocm_package_version }}
native_package_type: deb
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
build_native_rpm_packages:
needs: [build_multi_arch_stages]
name: Build RPM Packages
if: ${{ !failure() && !cancelled() && fromJSON(inputs.build_config).build_native_linux == true }}
uses: ./.github/workflows/multi_arch_build_native_linux_packages.yml
with:
dist_amdgpu_families: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
rocm_version: ${{ inputs.rocm_rpm_package_version || inputs.rocm_package_version }}
native_package_type: rpm
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
test_native_packages_ubuntu2404:
needs: [build_native_deb_packages]
name: Test DEB Install - ubuntu2404
if: ${{ !failure() && !cancelled() && fromJSON(inputs.build_config).build_native_linux == true }}
uses: ./.github/workflows/test_native_linux_packages_install.yml
with:
package_install_url: ${{ needs.build_native_deb_packages.outputs.package_repository_url }}
release_type: ci
os_profile: ubuntu2404
artifact_group: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
test_type: sanity
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
test_native_packages_rhel8:
needs: [build_native_rpm_packages]
name: Test RPM Install - rhel8
if: ${{ !failure() && !cancelled() && fromJSON(inputs.build_config).build_native_linux == true }}
uses: ./.github/workflows/test_native_linux_packages_install.yml
with:
package_install_url: ${{ needs.build_native_rpm_packages.outputs.package_repository_url }}
release_type: ci
os_profile: rhel8
artifact_group: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
test_type: sanity
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
test_native_packages_rhel10:
needs: [build_native_rpm_packages]
name: Test RPM Install - rhel10
if: ${{ !failure() && !cancelled() && fromJSON(inputs.build_config).build_native_linux == true }}
uses: ./.github/workflows/test_native_linux_packages_install.yml
with:
package_install_url: ${{ needs.build_native_rpm_packages.outputs.package_repository_url }}
release_type: ci
os_profile: rhel10
artifact_group: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
test_type: sanity
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
test_native_packages_sles16:
needs: [build_native_rpm_packages]
name: Test RPM Install - sles16
if: ${{ !failure() && !cancelled() && fromJSON(inputs.build_config).build_native_linux == true }}
uses: ./.github/workflows/test_native_linux_packages_install.yml
with:
package_install_url: ${{ needs.build_native_rpm_packages.outputs.package_repository_url }}
release_type: ci
os_profile: sles16
artifact_group: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
test_type: sanity
build_variant: ${{ fromJSON(inputs.build_config).build_variant_label }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
build_python_packages:
needs: [build_multi_arch_stages]
name: Build Python Packages
if: ${{ !failure() && !cancelled() }}
uses: ./.github/workflows/build_portable_linux_python_packages.yml
with:
artifact_group: ${{ fromJSON(inputs.build_config).artifact_group }}
amdgpu_families: ${{ fromJSON(inputs.build_config).dist_amdgpu_families }}
linux_amdgpu_families: ${{ fromJSON(inputs.build_config).linux_amdgpu_families }}
windows_amdgpu_families: ${{ fromJSON(inputs.build_config).windows_amdgpu_families }}
multiarch_index: true
package_version: ${{ inputs.rocm_package_version }}
release_type: ${{ inputs.release_type }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
test_python_packages_per_family:
needs: [build_python_packages]
name: Test Python
if: ${{ !failure() && !cancelled() && toJSON(fromJSON(inputs.build_config).test_python_packages_matrix) != '[]' }}
strategy:
fail-fast: false
matrix:
include: ${{ fromJSON(inputs.build_config).test_python_packages_matrix }}
uses: ./.github/workflows/test_rocm_wheels.yml
with:
amdgpu_family: ${{ matrix.amdgpu_family }}
test_runs_on: ${{ matrix.test_runs_on }}
# TODO: Simplify to just `needs.build_python_packages.outputs.package_find_links_url`
# once kpack split is always enabled.
package_find_links_url: >-
${{
needs.build_python_packages.outputs.kpack_split == 'true'
&& needs.build_python_packages.outputs.package_find_links_url
|| format('{0}/{1}/index.html',
needs.build_python_packages.outputs.package_find_links_url,
matrix.amdgpu_family)
}}
python_version: ${{ matrix.python_version }}
rocm_version: ${{ inputs.rocm_package_version }}
container_image_name: ${{ matrix.container_image_name }}
container_image_url: ${{ matrix.container_image_url }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
# Multi-arch PyTorch build: one fat wheel covering every target, then
# split into a host wheel + per-gfx device wheels via rocm-kpack.
# KPACK_SPLIT_ARTIFACTS is always ON in multi-arch CI (FLAGS.cmake
# default; build_configure.py's opt-out only fires in single-arch CI),
# so the split path is unconditional here. The split itself runs inline
# in multi_arch_build_portable_linux_pytorch_wheels_ci.yml based on
# inputs.kpack_split.
build_pytorch_wheel_fat:
needs: [build_python_packages]
name: Build PyTorch (fat + split)
if: >-
${{
!failure() &&
!cancelled() &&
fromJSON(inputs.build_config).build_pytorch == true &&
toJSON(fromJSON(inputs.build_config).pytorch_build_matrix) != '[]'
}}
strategy:
fail-fast: false
matrix:
include: ${{ fromJSON(inputs.build_config).pytorch_build_matrix }}
uses: ./.github/workflows/multi_arch_build_portable_linux_pytorch_wheels_ci.yml
with:
artifact_group: ${{ fromJSON(inputs.build_config).artifact_group }}
python_version: ${{ matrix.python_version }}
pytorch_git_ref: ${{ matrix.pytorch_git_ref }}
# The reusable workflow expands this to gfx targets via
# cmake/therock_amdgpu_targets.cmake.
amdgpu_families: ${{ matrix.amdgpu_families }}
kpack_split: ${{ needs.build_python_packages.outputs.kpack_split }}
rocm_package_find_links_url: ${{ needs.build_python_packages.outputs.package_find_links_url }}
rocm_version: ${{ inputs.rocm_package_version }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write
build_jax_wheels:
needs: [build_python_packages]
name: Build JAX Wheels
if: >-
${{
!failure() &&
!cancelled() &&
fromJSON(inputs.build_config).build_jax == true &&
toJSON(fromJSON(inputs.build_config).jax_build_matrix) != '[]'
}}
strategy:
fail-fast: false
matrix:
include: ${{ fromJSON(inputs.build_config).jax_build_matrix }}
uses: ./.github/workflows/multi_arch_build_linux_jax_wheels_ci.yml
with:
artifact_group: ${{ fromJSON(inputs.build_config).artifact_group }}
python_version: ${{ matrix.python_version }}
jax_repository: ${{ matrix.jax_repository }}
gfx_arch: ${{ matrix.gfx_arch }}
jax_ref: ${{ matrix.jax_ref }}
rocm_version: ${{ inputs.rocm_package_version }}
rocm_package_find_links_url: ${{ needs.build_python_packages.outputs.package_find_links_url }}
repository: ${{ inputs.repository }}
ref: ${{ inputs.ref }}
permissions:
contents: read
id-token: write