Add gcov-based test pruning with coverage cache #4997

Workflow file for this run

	name: 'Test Suite'

	on:
	push:
	branches: [master]
	pull_request:
	types: [opened, synchronize, reopened, ready_for_review]
	workflow_dispatch:

	concurrency:
	group: ${{ github.workflow }}-${{ github.ref }}
	cancel-in-progress: true

	jobs:
	lint-gate:
	name: Lint Gate
	runs-on: ubuntu-latest
	steps:
	- name: Clone
	uses: actions/checkout@v4

	- name: Setup Python
	uses: actions/setup-python@v5
	with:
	python-version: '3.12'

	- name: Initialize MFC
	run: ./mfc.sh init

	- name: Check Formatting
	run: \|
	./mfc.sh format -j "$(nproc)"
	git diff --exit-code \|\| (echo "::error::Code is not formatted. Run './mfc.sh format' locally." && exit 1)

	- name: Spell Check
	run: ./mfc.sh spelling

	- name: Lint Toolchain
	run: ./mfc.sh lint

	- name: Lint Source - No Raw Directives
	run: \|
	! grep -iR '!\$acc\\|!\$omp' --exclude="parallel_macros.fpp" --exclude="acc_macros.fpp" --exclude="omp_macros.fpp" --exclude="shared_parallel_macros.fpp" --exclude="syscheck.fpp" ./src/*

	- name: Lint Source - No Double Precision Intrinsics
	run: \|
	! grep -iR 'double_precision\\|dsqrt\\|dexp\\|dlog\\|dble\\|dabs\\|double\ precision\\|real(8)\\|real(4)\\|dprod\\|dmin\\|dmax\\|dfloat\\|dreal\\|dcos\\|dsin\\|dtan\\|dsign\\|dtanh\\|dsinh\\|dcosh\\|d0' --exclude-dir=syscheck --exclude="nvtx" --exclude="precision_select" ./src/*

	- name: Lint Source - No Junk Code
	run: \|
	! grep -iR -e '\.\.\.' -e '\-\-\-' -e '===' ./src/*

	- name: Lint Docs
	run: python3 toolchain/mfc/lint_docs.py

	file-changes:
	name: Detect File Changes
	runs-on: 'ubuntu-latest'
	outputs:
	checkall: ${{ steps.changes.outputs.checkall }}
	cases_py: ${{ steps.changes.outputs.cases_py }}
	dep_changed: ${{ steps.dep-check.outputs.dep_changed }}
	steps:
	- name: Clone
	uses: actions/checkout@v4

	- name: Detect Changes
	uses: dorny/paths-filter@v3
	id: changes
	with:
	filters: ".github/file-filter.yml"

	- name: Check for Fortran dependency changes
	id: dep-check
	env:
	GH_TOKEN: ${{ github.token }}
	run: \|
	# Detect added/removed use/include statements that change the
	# Fortran dependency graph, which would make the coverage cache stale.
	if [ "${{ github.event_name }}" = "pull_request" ]; then
	DIFF=$(gh pr diff ${{ github.event.pull_request.number }})
	elif [ "${{ github.event_name }}" = "push" ]; then
	DIFF=$(git diff ${{ github.event.before }}..${{ github.event.after }} 2>/dev/null \|\| echo "")
	else
	DIFF=""
	fi
	if echo "$DIFF" \| \
	grep -qP '^\+\s*(use[\s,]+\w\|#:include\s\|include\s+['"'"'"])'; then
	echo "dep_changed=true" >> "$GITHUB_OUTPUT"
	echo "Fortran dependency change detected — will rebuild coverage cache."
	else
	echo "dep_changed=false" >> "$GITHUB_OUTPUT"
	fi

	rebuild-cache:
	name: Rebuild Coverage Cache
	needs: [lint-gate, file-changes]
	if: >-
	github.repository == 'MFlowCode/MFC' &&
	(
	(github.event_name == 'pull_request' &&
	(needs.file-changes.outputs.cases_py == 'true' \|\|
	needs.file-changes.outputs.dep_changed == 'true')) \|\|
	(github.event_name == 'push' &&
	(needs.file-changes.outputs.cases_py == 'true' \|\|
	needs.file-changes.outputs.dep_changed == 'true')) \|\|
	github.event_name == 'workflow_dispatch'
	)
	timeout-minutes: 240
	runs-on:
	group: phoenix
	labels: gt
	permissions:
	contents: write
	steps:
	- name: Clone
	uses: actions/checkout@v4
	with:
	ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha \|\| github.sha }}
	clean: false

	- name: Rebuild Cache via SLURM
	run: bash .github/workflows/phoenix/submit.sh .github/workflows/phoenix/rebuild-cache.sh cpu none

	- name: Print Logs
	if: always()
	run: cat rebuild-cache-cpu-none.out

	- name: Upload Cache Artifact
	if: github.event_name == 'pull_request'
	uses: actions/upload-artifact@v4
	with:
	name: coverage-cache
	path: toolchain/mfc/test/test_coverage_cache.json.gz
	retention-days: 1

	- name: Commit Cache to Master
	if: github.event_name == 'push' \|\| github.event_name == 'workflow_dispatch'
	run: \|
	git config user.name "github-actions[bot]"
	git config user.email "github-actions[bot]@users.noreply.github.com"
	git add toolchain/mfc/test/test_coverage_cache.json.gz
	if git diff --cached --quiet; then
	echo "Coverage cache unchanged."
	else
	git commit -m "Regenerate gcov coverage cache [skip ci]"
	git push
	fi

	github:
	name: Github
	needs: [lint-gate, file-changes, rebuild-cache]
	if: >-
	always() &&
	needs.lint-gate.result == 'success' &&
	needs.file-changes.result == 'success' &&
	needs.rebuild-cache.result != 'cancelled' &&
	needs.file-changes.outputs.checkall == 'true'
	strategy:
	matrix:
	os: ['ubuntu', 'macos']
	mpi: ['mpi']
	precision: ['']
	debug: ['debug', 'no-debug']
	intel: [true, false]
	exclude:
	- os: macos
	intel: true

	include:
	- os: ubuntu
	mpi: no-mpi
	precision: single
	debug: no-debug
	intel: false

	fail-fast: false
	runs-on: ${{ matrix.os }}-latest

	steps:
	- name: Clone
	uses: actions/checkout@v4

	- name: Fetch master for coverage diff
	run: \|
	git fetch origin master:master --depth=1
	git fetch --deepen=200
	continue-on-error: true

	- name: Download Coverage Cache
	if: needs.rebuild-cache.result == 'success'
	uses: actions/download-artifact@v4
	with:
	name: coverage-cache
	path: toolchain/mfc/test
	continue-on-error: true

	- name: Setup MacOS
	if: matrix.os == 'macos'
	run: \|
	brew update
	brew upgrade
	brew install coreutils python fftw hdf5 gcc@15 boost open-mpi lapack
	echo "FC=gfortran-15" >> $GITHUB_ENV
	echo "BOOST_INCLUDE=/opt/homebrew/include/" >> $GITHUB_ENV

	- name: Setup Ubuntu
	if: matrix.os == 'ubuntu' && matrix.intel == false
	run: \|
	sudo apt update -y
	sudo apt install -y cmake gcc g++ python3 python3-dev hdf5-tools \
	libfftw3-dev libhdf5-dev openmpi-bin libopenmpi-dev \
	libblas-dev liblapack-dev

	- name: Setup Ubuntu (Intel)
	if: matrix.os == 'ubuntu' && matrix.intel == true
	run: \|
	wget https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
	sudo apt-key add GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB
	sudo add-apt-repository "deb https://apt.repos.intel.com/oneapi all main"
	sudo apt-get update
	sudo apt-get install -y intel-oneapi-compiler-fortran intel-oneapi-mpi intel-oneapi-mpi-devel
	source /opt/intel/oneapi/setvars.sh
	printenv >> $GITHUB_ENV

	- name: Set up Python 3.14
	uses: actions/setup-python@v5
	with:
	python-version: '3.14'

	- name: Get system info for cache key
	id: sys-info
	run: \|
	{
	uname -m
	cat /proc/cpuinfo 2>/dev/null \| grep 'model name' \| head -1 \|\| sysctl -n machdep.cpu.brand_string 2>/dev/null \|\| true
	if command -v ifx &>/dev/null; then ifx --version 2>/dev/null \| head -1; else ${FC:-gfortran} --version 2>/dev/null \| head -1 \|\| true; fi
	${CC:-gcc} --version 2>/dev/null \| head -1 \|\| true
	} \| (sha256sum 2>/dev/null \|\| shasum -a 256) \| cut -c1-16 > /tmp/sys-hash
	echo "sys-hash=$(cat /tmp/sys-hash)" >> "$GITHUB_OUTPUT"

	- name: Restore Build Cache
	uses: actions/cache@v4
	with:
	path: build
	key: mfc-build-${{ matrix.os }}-${{ matrix.mpi }}-${{ matrix.debug }}-${{ matrix.precision }}-${{ matrix.intel }}-${{ steps.sys-info.outputs.sys-hash }}-${{ hashFiles('CMakeLists.txt', 'toolchain/dependencies/', 'toolchain/cmake/', 'src/*/.fpp', 'src/*/.f90') }}

	- name: Build
	run: \|
	/bin/bash mfc.sh test -v --dry-run -j "$(nproc)" --${{ matrix.debug }} --${{ matrix.mpi }} $PRECISION $TEST_ALL
	env:
	TEST_ALL: ${{ matrix.mpi == 'mpi' && '--test-all' \|\| '' }}
	PRECISION: ${{ matrix.precision != '' && format('--{0}', matrix.precision) \|\| '' }}

	- name: Test
	run: \|
	rm -f tests/failed_uuids.txt
	TEST_EXIT=0
	/bin/bash mfc.sh test -v --max-attempts 3 -j "$(nproc)" $ONLY_CHANGES $TEST_ALL $TEST_PCT \|\| TEST_EXIT=$?

	# Retry only if a small number of tests failed (sporadic failures)
	if [ -s tests/failed_uuids.txt ]; then
	NUM_FAILED=$(wc -l < tests/failed_uuids.txt)
	if [ "$NUM_FAILED" -le 5 ]; then
	FAILED=$(tr '\n' ' ' < tests/failed_uuids.txt)
	echo ""
	echo "=== Retrying $NUM_FAILED failed test(s): $FAILED ==="
	echo ""
	/bin/bash mfc.sh test -v --max-attempts 3 -j "$(nproc)" --only $FAILED $TEST_ALL \|\| exit $?
	else
	echo "Too many failures ($NUM_FAILED) to retry — likely a real issue."
	exit 1
	fi
	elif [ "$TEST_EXIT" -ne 0 ]; then
	exit $TEST_EXIT
	fi
	env:
	TEST_ALL: ${{ matrix.mpi == 'mpi' && '--test-all' \|\| '' }}
	TEST_PCT: ${{ matrix.debug == 'debug' && '-% 20' \|\| '' }}
	ONLY_CHANGES: ${{ github.event_name == 'pull_request' && '--only-changes' \|\| '' }}

	self:
	name: "${{ matrix.cluster_name }} (${{ matrix.device }}${{ matrix.interface != 'none' && format('-{0}', matrix.interface) \|\| '' }}${{ matrix.shard != '' && format(' [{0}]', matrix.shard) \|\| '' }})"
	needs: [lint-gate, file-changes, rebuild-cache]
	if: >-
	always() &&
	needs.lint-gate.result == 'success' &&
	needs.file-changes.result == 'success' &&
	needs.rebuild-cache.result != 'cancelled' &&
	github.repository == 'MFlowCode/MFC' &&
	needs.file-changes.outputs.checkall == 'true' &&
	github.event.pull_request.draft != true
	continue-on-error: false
	timeout-minutes: 480
	strategy:
	matrix:
	include:
	# Phoenix (GT) — build+test combined in SLURM job
	- runner: 'gt'
	cluster: 'phoenix'
	cluster_name: 'Georgia Tech \| Phoenix'
	device: 'gpu'
	interface: 'acc'
	- runner: 'gt'
	cluster: 'phoenix'
	cluster_name: 'Georgia Tech \| Phoenix'
	device: 'gpu'
	interface: 'omp'
	- runner: 'gt'
	cluster: 'phoenix'
	cluster_name: 'Georgia Tech \| Phoenix'
	device: 'cpu'
	interface: 'none'
	# Frontier (ORNL) — build on login node, GPU tests sharded for batch partition
	- runner: 'frontier'
	cluster: 'frontier'
	cluster_name: 'Oak Ridge \| Frontier'
	device: 'gpu'
	interface: 'acc'
	shard: '1/2'
	- runner: 'frontier'
	cluster: 'frontier'
	cluster_name: 'Oak Ridge \| Frontier'
	device: 'gpu'
	interface: 'acc'
	shard: '2/2'
	- runner: 'frontier'
	cluster: 'frontier'
	cluster_name: 'Oak Ridge \| Frontier'
	device: 'gpu'
	interface: 'omp'
	shard: '1/2'
	- runner: 'frontier'
	cluster: 'frontier'
	cluster_name: 'Oak Ridge \| Frontier'
	device: 'gpu'
	interface: 'omp'
	shard: '2/2'
	- runner: 'frontier'
	cluster: 'frontier'
	cluster_name: 'Oak Ridge \| Frontier'
	device: 'cpu'
	interface: 'none'
	# Frontier AMD — build on login node, GPU tests sharded for batch partition
	- runner: 'frontier'
	cluster: 'frontier_amd'
	cluster_name: 'Oak Ridge \| Frontier (AMD)'
	device: 'gpu'
	interface: 'omp'
	shard: '1/2'
	- runner: 'frontier'
	cluster: 'frontier_amd'
	cluster_name: 'Oak Ridge \| Frontier (AMD)'
	device: 'gpu'
	interface: 'omp'
	shard: '2/2'
	- runner: 'frontier'
	cluster: 'frontier_amd'
	cluster_name: 'Oak Ridge \| Frontier (AMD)'
	device: 'cpu'
	interface: 'none'
	runs-on:
	group: phoenix
	labels: ${{ matrix.runner }}
	env:
	NODE_OPTIONS: ${{ matrix.cluster == 'phoenix' && '--max-old-space-size=2048' \|\| '' }}
	steps:
	- name: Clone
	uses: actions/checkout@v4
	with:
	clean: false

	- name: Download Coverage Cache
	if: needs.rebuild-cache.result == 'success'
	uses: actions/download-artifact@v4
	with:
	name: coverage-cache
	path: toolchain/mfc/test
	continue-on-error: true

	- name: Build
	if: matrix.cluster != 'phoenix'
	uses: nick-fields/retry@ce71cc2ab81d554ebbe88c79ab5975992d79ba08 # v3
	with:
	max_attempts: 3
	retry_wait_seconds: 60
	timeout_minutes: 60
	command: bash .github/workflows/${{ matrix.cluster }}/build.sh ${{ matrix.device }} ${{ matrix.interface }}
	on_retry_command: ./mfc.sh clean

	- name: Test
	run: bash .github/workflows/${{ matrix.cluster }}/submit.sh .github/workflows/${{ matrix.cluster }}/test.sh ${{ matrix.device }} ${{ matrix.interface }} ${{ matrix.shard }}

	- name: Compute Log Slug
	if: always()
	id: log
	run: \|
	SLUG="test-${{ matrix.device }}-${{ matrix.interface }}"
	SHARD="${{ matrix.shard }}"
	if [ -n "$SHARD" ]; then
	SLUG="${SLUG}-$(echo "$SHARD" \| sed 's\|/\|-of-\|')"
	fi
	echo "slug=${SLUG}" >> "$GITHUB_OUTPUT"

	- name: Print Logs
	if: always()
	run: cat ${{ steps.log.outputs.slug }}.out

	- name: Archive Logs
	uses: actions/upload-artifact@v4
	if: matrix.cluster != 'phoenix'
	with:
	name: logs-${{ strategy.job-index }}-${{ steps.log.outputs.slug }}
	path: ${{ steps.log.outputs.slug }}.out

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add gcov-based test pruning with coverage cache #4997

Workflow file

Add gcov-based test pruning with coverage cache #4997

Uh oh!

Workflow file for this run