Skip to content

FBGEMM_GPU-ROCm CI #342

FBGEMM_GPU-ROCm CI

FBGEMM_GPU-ROCm CI #342

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.
# This workflow is used for FBGEMM_GPU-ROCm CI as well as nightly builds of
# FBGEMM_GPU-ROCm against PyTorch-ROCm Nightly.
name: FBGEMM_GPU-ROCm CI
on:
# PR Trigger (enabled for regression checks and debugging)
#
pull_request:
branches:
- main
# Push Trigger (enable to catch errors coming out of multiple merges)
#
push:
branches:
- main
# Cron Trigger (UTC)
#
# Based on the Conda page for PyTorch-nightly, the GPU nightly releases appear
# around 02:30 PST every day (roughly 2 hours after the CPU releases)
#
schedule:
- cron: '45 12 * * *'
# Manual Trigger
#
workflow_dispatch:
inputs:
publish_to_pypi:
description: Publish Artifact to PyPI
type: boolean
required: false
default: false
concurrency:
# Cancel previous runs in the PR if a new commit is pushed
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
# Build on CPU hosts and upload to GHA
build_artifact:
runs-on: ${{ matrix.host-machine.instance }}
container:
image: ${{ matrix.container-image }}
options: --user root
defaults:
run:
shell: bash
env:
PRELUDE: .github/scripts/setup_env.bash
BUILD_ENV: build_binary
strategy:
fail-fast: false
matrix:
host-machine: [
{ arch: x86, instance: "linux.24xlarge" },
]
container-image: [ "ubuntu:20.04" ]
python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ]
rocm-version: [ "6.0.2" ]
compiler: [ "gcc", "clang" ]
steps:
- name: Setup Build Container
run: |
apt update -y
apt install -y binutils git pciutils sudo wget
git config --global --add safe.directory '*'
- name: Checkout the Repository
uses: actions/checkout@v4
- name: Display System Info
run: . $PRELUDE; print_system_info
- name: Display GPU Info
run: . $PRELUDE; print_gpu_info
- name: Free Disk Space
run: . $PRELUDE; free_disk_space
- name: Setup Miniconda
run: . $PRELUDE; setup_miniconda $HOME/miniconda
- name: Create Conda Environment
run: . $PRELUDE; create_conda_environment $BUILD_ENV ${{ matrix.python-version }}
- name: Install C/C++ Compilers
run: . $PRELUDE; install_cxx_compiler $BUILD_ENV ${{ matrix.compiler }}
- name: Install Build Tools
run: . $PRELUDE; install_build_tools $BUILD_ENV
- name: Install ROCm
run: . $PRELUDE; install_rocm_ubuntu $BUILD_ENV ${{ matrix.rocm-version }}
- name: Install PyTorch-ROCm Nightly
run: . $PRELUDE; install_pytorch_pip $BUILD_ENV nightly rocm/${{ matrix.rocm-version }}
- name: Collect PyTorch Environment Info
if: ${{ success() || failure() }}
run: if . $PRELUDE && which conda; then collect_pytorch_env_info $BUILD_ENV; fi
- name: Prepare FBGEMM_GPU Build
run: . $PRELUDE; cd fbgemm_gpu; prepare_fbgemm_gpu_build $BUILD_ENV
- name: Build FBGEMM_GPU Wheel
run: . $PRELUDE; cd fbgemm_gpu; build_fbgemm_gpu_package $BUILD_ENV nightly rocm
- name: Upload Built Wheel as GHA Artifact
uses: actions/upload-artifact@v4
with:
name: fbgemm_gpu_nightly_rocm_${{ matrix.host-machine.arch }}_${{ matrix.compiler }}_py${{ matrix.python-version }}_rocm${{ matrix.rocm-version }}.whl
path: fbgemm_gpu/dist/fbgemm_gpu_nightly_rocm-*.whl
# Download the built artifact from GHA, test on GPU, and push to PyPI
test_and_publish_artifact:
runs-on: ${{ matrix.host-machine.instance }}
container:
image: "rocm/dev-ubuntu-20.04:${{ matrix.rocm-version }}-complete"
options: --user root --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size 16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined
defaults:
run:
shell: bash
env:
PRELUDE: .github/scripts/setup_env.bash
BUILD_ENV: build_binary
ENFORCE_ROCM_DEVICE: 1
strategy:
fail-fast: false
matrix:
host-machine: [
{ arch: x86, instance: "rocm" },
]
# ROCm machines are limited, so we only test a subset of Python versions
python-version: [ "3.12" ]
rocm-version: [ "6.0.2" ]
compiler: [ "gcc", "clang" ]
needs: build_artifact
steps:
- name: Setup Build Container
run: |
apt update -y
apt install -y git wget
git config --global --add safe.directory '*'
- name: Checkout the Repository
uses: actions/checkout@v3
- name: Download Wheel Artifact from GHA
uses: actions/download-artifact@v4
with:
name: fbgemm_gpu_nightly_rocm_${{ matrix.host-machine.arch }}_${{ matrix.compiler }}_py${{ matrix.python-version }}_rocm${{ matrix.rocm-version }}.whl
- name: Display System Info
run: . $PRELUDE; print_system_info
- name: Display GPU Info
run: . $PRELUDE; print_gpu_info
- name: Free Disk Space
run: . $PRELUDE; free_disk_space
- name: Setup Miniconda
run: . $PRELUDE; setup_miniconda $HOME/miniconda
- name: Create Conda Environment
run: . $PRELUDE; create_conda_environment $BUILD_ENV ${{ matrix.python-version }}
- name: Install PyTorch-ROCm Nightly
run: . $PRELUDE; install_pytorch_pip $BUILD_ENV nightly rocm/${{ matrix.rocm-version }}
- name: Collect PyTorch Environment Info
if: ${{ success() || failure() }}
run: if . $PRELUDE && which conda; then collect_pytorch_env_info $BUILD_ENV; fi
- name: Prepare FBGEMM_GPU Build
run: . $PRELUDE; cd fbgemm_gpu; prepare_fbgemm_gpu_build $BUILD_ENV
- name: Install FBGEMM_GPU Wheel
run: . $PRELUDE; install_fbgemm_gpu_wheel $BUILD_ENV *.whl
- name: Test with PyTest
timeout-minutes: 20
run: . $PRELUDE; cd fbgemm_gpu/test; run_fbgemm_gpu_tests $BUILD_ENV rocm