Files
rocm-systems/.github/workflows/opensuse.yml
T
Jonathan R. Madsen 45be03906a RCCL support (#93)
* Initial support for RCCL

* OMNITRACE_USE_RCCLP + sampling tweaks

- also OMNITRACE_SAMPLING_KEEP_INTERNAL option
- minor modifications to sampling to use keep internal option + discard funlockfile

* Update docker and workflows to download RCCL

* Update CPack DEB with rocprofiler dependency

* Rework rccl into library and library/components folder

- add tpls/rccl/rccl/rccl.h

* Fix timemory includes

* rcclp inline definitions when disabled

* Tweaks to ubuntu-focal-external-rocm

- disable ompt
- enable building testing

* Tweaks to ubuntu-focal-external-rocm

- ctest exclude

* Tweak ubuntu-focal.yml

- remove source /.../setup-env.sh, replace with $GITHUB_ENV

* Fix ubuntu-focal-rocm + OMPI + root

* Improved rocm-smi error handling

- Recover from rocm-smi errors
- Disabling rocm-smi after recovering from errors
- Werror in developer mode
- Remove State::DelayedInit
- Add State::Disabled

* formatting

* Fix merge of OMNITRACE_SAMPLING_KEEP_INTERNAL

* Update RCCL include directory

- based on ROCm version we need with <rccl/rccl.h> or <rccl.h>

* RCCL Testing

- updated tests to use configuration files
- many tests generate a configuration file
- tests how have GPU option
- enable ncclCommCount, disable ncclGetVersion
- add testing for RCCLP via rccl-tests
- working directory of tests is PROJECT_BINARY_DIR
- add nccl/rccl functions to get_whole_function_names
- some clang compiler fixes

* Handle RCCL include w/o HIP

* RCCL requires HIP

* Update OMNITRACE_SAMPLING_CPUS for testing

* Update tests/CMakeLists.txt

* Debug settings

* Install MPI even when USE_MPI=OFF

* exclude printf

* skip mpi tests w/o USE_MPI or USE_MPI_HEADERS

* update ubuntu rocm workflow

* Fix configure env step for ubuntu rocm
2022-07-25 12:16:11 -05:00

127 wiersze
3.7 KiB
YAML

name: OpenSUSE 15 (GCC, Python)
on:
push:
branches: [ main, develop ]
pull_request:
branches: [ main, develop ]
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
env:
BUILD_TYPE: Release
OMNITRACE_VERBOSE: 1
OMNITRACE_CI: ON
jobs:
opensuse:
runs-on: ubuntu-20.04
container:
image: jrmadsen/omnitrace:ci-base-opensuse-${{ matrix.os-release }}
strategy:
matrix:
compiler: ['g++']
os-release: [ '15.2', '15.3' ]
steps:
- uses: actions/checkout@v2
- name: Install Packages
timeout-minutes: 5
run:
for i in 6 7 8 9 10; do /opt/conda/envs/py3.${i}/bin/python -m pip install numpy perfetto dataclasses; done
- name: Configure Env
run:
echo "CC=$(echo '${{ matrix.compiler }}' | sed 's/+/c/g')" >> $GITHUB_ENV &&
echo "CXX=${{ matrix.compiler }}" >> $GITHUB_ENV &&
echo "/opt/omnitrace/bin:${HOME}/.local/bin" >> $GITHUB_PATH &&
echo "LD_LIBRARY_PATH=/opt/omnitrace/lib:${LD_LIBRARY_PATH}" >> $GITHUB_ENV
- name: Configure CMake
timeout-minutes: 10
run:
git config --global --add safe.directory ${PWD} &&
cmake --version &&
cmake -B build
-DCMAKE_C_COMPILER=$(echo '${{ matrix.compiler }}' | sed 's/+/c/g')
-DCMAKE_CXX_COMPILER=${{ matrix.compiler }}
-DCMAKE_BUILD_TYPE=${{ env.BUILD_TYPE }}
-DCMAKE_INSTALL_PREFIX=/opt/omnitrace
-DOMNITRACE_BUILD_TESTING=ON
-DOMNITRACE_USE_MPI=OFF
-DOMNITRACE_USE_HIP=OFF
-DOMNITRACE_USE_OMPT=OFF
-DOMNITRACE_USE_PYTHON=ON
-DOMNITRACE_PYTHON_PREFIX=/opt/conda/envs
-DOMNITRACE_PYTHON_ENVS="py3.6;py3.7;py3.8;py3.9;py3.10"
-DOMNITRACE_CI_MPI_RUN_AS_ROOT=ON
-DOMNITRACE_MAX_THREADS=32
- name: Build
timeout-minutes: 60
run:
cmake --build build --target all --parallel 2 -- VERBOSE=1
- name: Install
timeout-minutes: 5
run:
cmake --build build --target install --parallel 2
- name: Test
timeout-minutes: 45
run:
cd build &&
ldd ./bin/omnitrace &&
./bin/omnitrace --help &&
ctest -V -N -O omnitrace-ctest-${{ github.job }}-commands.log &&
ctest -V --output-log omnitrace-ctest-${{ github.job }}.log --stop-on-failure
- name: Test Install
timeout-minutes: 10
run: |
set -v
export OMNITRACE_DEBUG=ON
which omnitrace-avail
ldd $(which omnitrace-avail)
omnitrace-avail --help
omnitrace-avail -a
which omnitrace-critical-trace
ldd $(which omnitrace-critical-trace)
which omnitrace
ldd $(which omnitrace)
omnitrace --help
omnitrace -e -v 1 -o ls.inst --simulate -- ls
for i in omnitrace-ls.inst-output/*; do echo -e "\n\n --> ${i} \n\n"; cat ${i}; done
omnitrace -e -v 1 -o ls.inst -- ls
./ls.inst
omnitrace -e -v 1 --simulate -- ls
for i in omnitrace-ls-output/*; do echo -e "\n\n --> ${i} \n\n"; cat ${i}; done
omnitrace -e -v 1 -- ls
- name: Test User API
timeout-minutes: 10
run: |
set -v
./scripts/test-find-package.sh --install-dir /opt/omnitrace
- name: CTest Artifacts
if: success() || failure()
uses: actions/upload-artifact@v2
with:
name: ctest-${{ github.job }}-log
path: |
build/*.log
- name: Data Artifacts
if: success() || failure()
uses: actions/upload-artifact@v2
with:
name: data-${{ github.job }}-files
path: |
build/omnitrace-tests-config/*.cfg
build/omnitrace-tests-output/**/*.txt
build/omnitrace-tests-output/**/*-instr*.json