Merge branch 'master' into tcclevenger/iop_as_atm

E3SM-Project · Nov 21, 2024 · 43eb9d7 · 43eb9d7
2 parents c5105d4 + 767c2a0
commit 43eb9d7
Show file tree

Hide file tree

Showing 343 changed files with 9,173 additions and 5,554 deletions.
diff --git a/.github/actions/check-skip-labels/README.md b/.github/actions/check-skip-labels/README.md
diff --git a/.github/actions/check-skip-labels/action.yml b/.github/actions/check-skip-labels/action.yml
diff --git a/.github/workflows/e3sm-gh-ci-cime-tests.yml b/.github/workflows/e3sm-gh-ci-cime-tests.yml
@@ -22,10 +22,14 @@ on:
 
   workflow_dispatch:
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
 
   ci:
-    if: false
+    if: ${{ github.repository == 'E3SM-Project/E3SM' }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -36,7 +40,7 @@ jobs:
           - SMS_D_Ln5_P4.ne4pg2_oQU480.F2010-SCREAMv1-MPASSI.ghci-oci_gnu
           - ERS_Ld5_P4.ne4pg2_oQU480.F2010-SCREAMv1-MPASSI.ghci-oci_gnu.eamxx-prod
     container: 
-      image: ghcr.io/e3sm-project/containers-ghci:ghci-0.1.0
+      image: ghcr.io/e3sm-project/containers-ghci:ghci-0.2.0
 
     steps:
       - 

diff --git a/.github/workflows/e3sm-gh-ci-w-cime-tests.yml b/.github/workflows/e3sm-gh-ci-w-cime-tests.yml
@@ -1,4 +1,4 @@
-name: gh
+name: gh-w
 
 on:
   pull_request:
@@ -11,10 +11,14 @@ on:
 
   workflow_dispatch:
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
 
-  ci-w:
-    if: ${{ github.event.repository.name == 'e3sm' }}
+  ci:
+    if: ${{ github.repository == 'E3SM-Project/E3SM' }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -23,7 +27,7 @@ jobs:
           - SMS_D_Ld1_P8.ne4pg2_oQU480.WCYCL2010NS.ghci-oci_gnu
           - ERS_Ld3_P8.ne4pg2_oQU480.WCYCL2010NS.ghci-oci_gnu.allactive-wcprod_1850
     container: 
-      image: ghcr.io/e3sm-project/containers-ghci:ghci-0.1.0
+      image: ghcr.io/e3sm-project/containers-ghci:ghci-0.2.0
 
     steps:
       - 

diff --git a/.github/workflows/e3sm-gh-md-linter.yml b/.github/workflows/e3sm-gh-md-linter.yml
@@ -10,8 +10,13 @@ on:
         # for now let's not lint files in eamxx
         - '!components/eamxx/**/*.md'
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   linter:
+    if: ${{ github.repository == 'E3SM-Project/E3SM' }}
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v4
@@ -22,7 +27,7 @@ jobs:
       with:
         files: '**/*.md'
         separator: ","
-    - uses: DavidAnson/markdownlint-cli2-action@v17
+    - uses: DavidAnson/markdownlint-cli2-action@v18
       if: steps.changed-files.outputs.any_changed == 'true'
       with:
         config: 'docs/.markdownlint.json'

diff --git a/.github/workflows/e3sm-gh-pages.yml b/.github/workflows/e3sm-gh-pages.yml
@@ -15,7 +15,7 @@ concurrency:
 
 jobs:
   Build-and-Deploy-docs:
-    if: ${{ github.event.repository.name == 'e3sm' }}
+    if: ${{ github.repository == 'E3SM-Project/E3SM' }}
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

diff --git a/.github/workflows/e3sm-gh-tools-mkatmsrffile-test.yml b/.github/workflows/e3sm-gh-tools-mkatmsrffile-test.yml
@@ -11,8 +11,13 @@ on:
     - cron: '00 15 * * 2'
   workflow_dispatch:
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   mkatmsrffile-test:
+    if: ${{ github.repository == 'E3SM-Project/E3SM' }}
     runs-on: ubuntu-latest
     defaults:
       run:
@@ -31,18 +36,15 @@ jobs:
         uses: conda-incubator/setup-miniconda@v3
         with:
           activate-environment: "envmkatmsrffile"
-          miniforge-variant: Mambaforge
           miniforge-version: latest
-          use-mamba: true
-          mamba-version: "*"
           channel-priority: strict
           auto-update-conda: true
           python-version: 3.11
       - 
         name: Install dependencies
         run: |
           echo $CONDA_PREFIX
-          mamba install -y nco xarray numba numpy netcdf4
+          conda install -y nco xarray numba numpy netcdf4 -c conda-forge
       - 
         name: Run tests
         working-directory: components/eam/tools/mkatmsrffile

diff --git a/.github/workflows/eamxx-gh-ci-standalone.yml b/.github/workflows/eamxx-gh-ci-standalone.yml
@@ -0,0 +1,60 @@
+name: gh-standalone
+
+on:
+  pull_request:
+    branches: [ master ]
+    paths:
+      # first, yes to these
+      - '.github/workflows/eamxx-gh-ci-standalone.yml'
+      - 'cime_config/machine/config_machines.xml'
+      - 'components/eamxx/**'
+      - 'components/homme/**'
+      # second, no to these
+      - '!components/eamxx/docs/**'
+      - '!components/eamxx/mkdocs.yml'
+
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event_name }}-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+
+  ci:
+    if: ${{ github.repository == 'E3SM-Project/E3SM' }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        test:
+          - sp
+          - opt
+          - dbg
+          - fpe
+    container: 
+      image: ghcr.io/e3sm-project/containers-standalone-ghci:standalone-ghci-0.1.0
+
+    steps:
+      - 
+        name: Checkout
+        uses: actions/checkout@v4
+        with:
+          show-progress: false
+          submodules: recursive
+      - 
+        name: standalone
+        env:
+          SHELL: sh
+        run: |
+          # TODO: get rid of this extra line if we can?
+          git config --global safe.directory '*'
+          ./components/eamxx/scripts/test-all-scream -m ghci-oci -t ${{ matrix.test }} -c BUILD_SHARED_LIBS=ON
+      - 
+        name: Artifacts
+        uses: actions/upload-artifact@v4
+        if: ${{ always() }}
+        with:
+          name: ${{ matrix.test }}
+          path: |
+            components/eamxx/ctest-build/*/Testing/Temporary/Last*.log
diff --git a/.github/workflows/eamxx-gh-pages.yml b/.github/workflows/eamxx-gh-pages.yml
@@ -34,7 +34,7 @@ concurrency:
 jobs:
 
   eamxx-docs:
-    if: ${{ github.event.repository.name == 'scream' }}
+    if: ${{ github.repository == 'E3SM-Project/scream' }}
     runs-on: ubuntu-latest
 
     steps:

diff --git a/.github/workflows/eamxx-sa-coverage.yml b/.github/workflows/eamxx-sa-coverage.yml
@@ -2,6 +2,11 @@ name: eamxx-sa-coverage
 
 on:
   workflow_dispatch:
+    inputs:
+      submit:
+        description: 'Force cdash submission'
+        required: true
+        type: boolean
 
   # Add schedule trigger for nightly runs at midnight MT (Standard Time)
   schedule:
@@ -13,7 +18,8 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  submit: ${{ github.event_name == 'schedule' && 'true' || 'false' }}  # Submit to cdash only for nightlies
+  # Submit to cdash only for nightlies or if the user explicitly forced a submission via workflow dispatch
+  submit: ${{ github.event_name == 'schedule' || (github.event_name == 'workflow_dispatch' && inputs.submit) }}
 
 jobs:
   gcc-openmp:
@@ -48,11 +54,40 @@ jobs:
           submodules: recursive
       - name: Show action trigger
         uses: ./.github/actions/show-workflow-trigger
+      - name: Get CUDA Arch
+        run: |
+          # Ensure nvidia-smi is available
+          if ! command -v nvidia-smi &> /dev/null; then
+              echo "nvidia-smi could not be found. Please ensure you have Nvidia drivers installed."
+              exit 1
+          fi
+
+          # Get the GPU model from nvidia-smi, and set env for next step
+          gpu_model=$(nvidia-smi --query-gpu=name --format=csv,noheader | head -n 1)
+          case "$gpu_model" in
+              *"H100"*)
+                  echo "Hopper=ON" >> $GITHUB_ENV
+                  echo "CUDA_ARCH=90" >> $GITHUB_ENV
+                  ARCH=90
+                  ;;
+              *"A100"*)
+                  echo "Ampere=ON" >> $GITHUB_ENV
+                  echo "CUDA_ARCH=80" >> $GITHUB_ENV
+                  ;;
+              *"V100"*)
+                  echo "Volta=ON" >> $GITHUB_ENV
+                  echo "CUDA_ARCH=70" >> $GITHUB_ENV
+                  ;;
+              *)
+                  echo "Unsupported GPU model: $gpu_model"
+                  exit 1
+                  ;;
+          esac
       - name: Run tests
         uses: ./.github/actions/test-all-scream
         with:
           build_type: cov
           machine: ghci-snl-cuda
           generate: false
           submit: ${{ env.submit }}
-          cmake-configs: Kokkos_ARCH_VOLTA70=ON;CMAKE_CUDA_ARCHITECTURES=70
+          cmake-configs: Kokkos_ARCH_HOPPER90=${{ env.Hopper }};Kokkos_ARCH_AMPERE80=${{ env.Ampere }};Kokkos_ARCH_VOLTA70=${{ env.Volta }};CMAKE_CUDA_ARCHITECTURES=${{ env.CUDA_ARCH }}