[Woptim] shared ci 2023.12.0 (#241)

* Update Shared CI and Spack Configs to add poodle * Activate poodle subpipeline * Reduce allocated time * Fine tune allocation duration * Fine tune allocation duration in CI * Comment alloc command choices * Update RSC to main * Fix missing poodle alloc info, update to radiuss Shared CI 2023.12.0, sync build_and_test script with RAJA * Update radiuss-spack-configs
LLNL · Feb 14, 2024 · 99c4f69 · 99c4f69
1 parent 7e8d43a
commit 99c4f69
Show file tree

Hide file tree

Showing 10 changed files with 227 additions and 74 deletions.
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
@@ -48,7 +48,11 @@ variables:
   GITHUB_PROJECT_NAME: "CHAI"
   GITHUB_PROJECT_ORG: "LLNL"
 # Set the build-and-test command.
-  JOB_CMD: "./scripts/gitlab/build_and_test.sh"
+# Nested variables are allowed and useful to customize the job command. We
+# prevent variable expansion so that you can define them at job level.
+  JOB_CMD:
+    value: "./scripts/gitlab/build_and_test.sh"
+    expand: false
 # Override the pattern describing branches that will skip the "draft PR filter
 # test".  Add protected branches here. See default value in
 # preliminary-ignore-draft-pr.yml.
@@ -69,7 +73,7 @@ stages:
     include:
       - local: '.gitlab/custom-jobs-and-variables.yml'
       - project: 'radiuss/radiuss-shared-ci'
-        ref: 'v2023.09.0'
+        ref: 'v2023.12.0'
         file: 'pipelines/${CI_MACHINE}.yml'
       - artifact: '${CI_MACHINE}-jobs.yml'
         job: 'generate-job-lists'
@@ -80,7 +84,7 @@ stages:
 include:
   # [Optional] checks preliminary to running the actual CI test
   #- project: 'radiuss/radiuss-shared-ci'
-  #  ref: 'v2023.09.0'
+  #  ref: 'v2023.12.0'
   #  file: 'preliminary-ignore-draft-pr.yml'
   # pipelines subscribed by the project
   - local: '.gitlab/subscribed-pipelines.yml'
diff --git a/.gitlab/custom-jobs-and-variables.yml b/.gitlab/custom-jobs-and-variables.yml
@@ -14,29 +14,41 @@ variables:
 
 # Ruby
 # Arguments for top level allocation
-  RUBY_SHARED_ALLOC: "--exclusive --reservation=ci --qos=ci_ruby --time=20 --nodes=1"
+  RUBY_SHARED_ALLOC: "--exclusive --reservation=ci --time=7 --nodes=1"
 # Arguments for job level allocation
-  RUBY_JOB_ALLOC: "--overlap --reservation=ci --time=20 --nodes=1"
+# Note: We repeat the reservation, necessary when jobs are manually re-triggered.
+  RUBY_JOB_ALLOC: "--overlap --reservation=ci --nodes=1"
 # Project specific variants for ruby
   PROJECT_RUBY_VARIANTS: "~shared +raja tests=basic "
 # Project specific deps for ruby
   PROJECT_RUBY_DEPS: ""
 
+# Poodle
+# Arguments for top level allocation
+  POODLE_SHARED_ALLOC: "--exclusive --partition=pdebug --time=7 --nodes=1"
+# Arguments for job level allocation
+# Note: We repeat the reservation, necessary when jobs are manually re-triggered.
+  POODLE_JOB_ALLOC: "--overlap --nodes=1"
+# Project specific variants for poodle
+  PROJECT_POODLE_VARIANTS: "~shared +raja tests=basic "
+# Project specific deps for poodle
+  PROJECT_POODLE_DEPS: ""
+
 # Corona
 # Arguments for top level allocation
-  CORONA_SHARED_ALLOC: "--exclusive --time-limit=45m --nodes=1"
+  CORONA_SHARED_ALLOC: "--exclusive --time-limit=7m --nodes=1"
 # Arguments for job level allocation
-  CORONA_JOB_ALLOC: "--time-limit=30m --nodes=1 --begin-time=+5s"
+  CORONA_JOB_ALLOC: "--nodes=1 --begin-time=+5s"
 # Project specific variants for corona
   PROJECT_CORONA_VARIANTS: "~shared +raja tests=basic "
 # Project specific deps for corona
   PROJECT_CORONA_DEPS: ""
 
 # Tioga
 # Arguments for top level allocation
-  TIOGA_SHARED_ALLOC: "--exclusive --time-limit=45m --nodes=1"
+  TIOGA_SHARED_ALLOC: "--exclusive --time-limit=14m --nodes=1"
 # Arguments for job level allocation
-  TIOGA_JOB_ALLOC: "--time-limit=30m --nodes=1 --begin-time=+5s"
+  TIOGA_JOB_ALLOC: "--nodes=1 --begin-time=+5s"
 # Project specific variants for tioga
   PROJECT_TIOGA_VARIANTS: "~shared +raja tests=basic "
 # Project specific deps for tioga
@@ -45,7 +57,7 @@ variables:
 # Lassen and Butte use a different job scheduler (spectrum lsf) that does not
 # allow pre-allocation the same way slurm does.
 # Arguments for job level allocation
-  LASSEN_JOB_ALLOC: "1 -W 120"
+  LASSEN_JOB_ALLOC: "1 -W 8"
 # Project specific variants for lassen
   PROJECT_LASSEN_VARIANTS: "~shared +raja cuda_arch=70 tests=basic"
 # Project specific deps for lassen

diff --git a/.gitlab/jobs/corona.yml b/.gitlab/jobs/corona.yml
@@ -5,5 +5,24 @@
 # SPDX-License-Identifier: (MIT)
 ##############################################################################
 
-variables:
-  INCLUDED_FILE_CANNOT_BE_EMPTY: "True"
+# Override reproducer section to define project specific variables.
+.corona_reproducer_vars: &corona_reproducer_vars
+    - |
+      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
+      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+
+########################
+# Overridden shared jobs
+########################
+# We duplicate the shared jobs description and add necessary changes for this
+# project. We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS}
+# So that the comparison with the original job is easier.
+
+# No overridden jobs so far.
+
+############
+# Extra jobs
+############
+# We do not recommend using ${PROJECT_<MACHINE>_VARIANTS} and
+# ${PROJECT_<MACHINE>_DEPS} in the extra jobs. There is no reason not to fully
+# describe the spec here.
diff --git a/.gitlab/jobs/lassen.yml b/.gitlab/jobs/lassen.yml
@@ -5,12 +5,27 @@
 # SPDX-License-Identifier: (MIT)
 ##############################################################################
 
+# Override reproducer section to define project specific variables.
+.lassen_reproducer_vars: &lassen_reproducer_vars
+    - |
+      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
+      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+
 ########################
 # Overridden shared jobs
 ########################
-# We duplicate the shared jobs description and add necessary changes for RAJA.
-# We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS} So that
-# the comparison with the original job is easier.
+# We duplicate the shared jobs description and add necessary changes for this
+# project. We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS}
+# So that the comparison with the original job is easier.
+
+# Overridden to increase allocation time
+xl_2022_08_19_gcc_8_3_1_cuda_11_2_0:
+  variables:
+    SPEC: "${PROJECT_LASSEN_VARIANTS} +cuda %[email protected] ^[email protected]+allow-unsupported-compilers ${PROJECT_LASSEN_DEPS}"
+    MODULE_LIST: "cuda/11.2.0"
+    LASSEN_JOB_ALLOC: "1 -W 12"
+  extends: .job_on_lassen
+
 
 # Override job with old cuda to allow it to fail.
 clang_12_0_1_ibm_gcc_8_3_1_cuda_10_1_243:

diff --git a/.gitlab/jobs/poodle.yml b/.gitlab/jobs/poodle.yml
@@ -0,0 +1,33 @@
+###############################################################################
+# Copyright (c) 2022-23, Lawrence Livermore National Security, LLC and RADIUSS
+# project contributors. See the COPYRIGHT file for details.
+#
+# SPDX-License-Identifier: (MIT)
+###############################################################################
+
+# Override reproducer section to define projet specific variables.
+.poodle_reproducer_vars: &poodle_reproducer_vars
+    - |
+      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
+      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+
+########################
+# Overridden shared jobs
+########################
+# We duplicate the shared jobs description and add necessary changes for this
+# project. We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS}
+# So that the comparison with the original job is easier.
+
+# No overridden jobs so far.
+
+############
+# Extra jobs
+############
+# We do not recommend using ${PROJECT_<MACHINE>_VARIANTS} and
+# ${PROJECT_<MACHINE>_DEPS} in the extra jobs. There is no reason not to fully
+# describe the spec here.
+
+clang_14_0_6_develop_tpls:
+  variables:
+    SPEC: " %[email protected] ^umpire@develop ^raja@develop ^camp@main"
+  extends: .job_on_poodle
diff --git a/.gitlab/jobs/ruby.yml b/.gitlab/jobs/ruby.yml
@@ -1,16 +1,22 @@
 ###############################################################################
-# Copyright (c) 2022, Lawrence Livermore National Security, LLC and RADIUSS
+# Copyright (c) 2022-23, Lawrence Livermore National Security, LLC and RADIUSS
 # project contributors. See the COPYRIGHT file for details.
 #
 # SPDX-License-Identifier: (MIT)
 ###############################################################################
 
+# Override reproducer section to define project specific variables.
+.ruby_reproducer_vars: &ruby_reproducer_vars
+    - |
+      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
+      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+
 ########################
 # Overridden shared jobs
 ########################
-# We duplicate the shared jobs description and add necessary changes for RAJA.
-# We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS} So that
-# the comparison with the original job is easier.
+# We duplicate the shared jobs description and add necessary changes for this
+# project. We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS}
+# So that the comparison with the original job is easier.
 
 # No overridden jobs so far.
 
@@ -25,4 +31,3 @@ clang_14_0_6_develop_tpls:
   variables:
     SPEC: " %[email protected] ^umpire@develop ^raja@develop ^camp@main"
   extends: .job_on_ruby
-
diff --git a/.gitlab/jobs/tioga.yml b/.gitlab/jobs/tioga.yml
@@ -1,9 +1,28 @@
 ##############################################################################
-# Copyright (c) 2022, Lawrence Livermore National Security, LLC and RADIUSS
+# Copyright (c) 2022-23, Lawrence Livermore National Security, LLC and RADIUSS
 # project contributors. See the COPYRIGHT file for details.
 #
 # SPDX-License-Identifier: (MIT)
 ##############################################################################
 
-variables:
-  INCLUDED_FILE_CANNOT_BE_EMPTY: "True"
+# Override reproducer section to define project specific variables.
+.tioga_reproducer_vars: &tioga_reproducer_vars
+    - |
+      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
+      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+
+########################
+# Overridden shared jobs
+########################
+# We duplicate the shared jobs description and add necessary changes for this
+# project. We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS}
+# So that the comparison with the original job is easier.
+
+# No overridden jobs so far.
+
+############
+# Extra jobs
+############
+# We do not recommend using ${PROJECT_<MACHINE>_VARIANTS} and
+# ${PROJECT_<MACHINE>_DEPS} in the extra jobs. There is no reason not to fully
+# describe the spec here.
diff --git a/.gitlab/subscribed-pipelines.yml b/.gitlab/subscribed-pipelines.yml
@@ -38,12 +38,14 @@ generate-job-lists:
     LOCAL_JOBS_PATH: ".gitlab/jobs"
   script:
     - cat ${RADIUSS_JOBS_PATH}/ruby.yml ${LOCAL_JOBS_PATH}/ruby.yml > ruby-jobs.yml
+    - cat ${RADIUSS_JOBS_PATH}/poodle.yml ${LOCAL_JOBS_PATH}/poodle.yml > poodle-jobs.yml
     - cat ${RADIUSS_JOBS_PATH}/lassen.yml ${LOCAL_JOBS_PATH}/lassen.yml > lassen-jobs.yml
     - cat ${RADIUSS_JOBS_PATH}/corona.yml ${LOCAL_JOBS_PATH}/corona.yml > corona-jobs.yml
     - cat ${RADIUSS_JOBS_PATH}/tioga.yml ${LOCAL_JOBS_PATH}/tioga.yml > tioga-jobs.yml
   artifacts:
     paths:
       - ruby-jobs.yml
+      - poodle-jobs.yml
       - lassen-jobs.yml
       - corona-jobs.yml
       - tioga-jobs.yml
@@ -60,6 +62,18 @@ ruby-build-and-test:
   needs: [ruby-up-check, generate-job-lists]
   extends: [.build-and-test]
 
+# POODLE
+poodle-up-check:
+  variables:
+    CI_MACHINE: "poodle"
+  extends: [.machine-check]
+
+poodle-build-and-test:
+  variables:
+    CI_MACHINE: "poodle"
+  needs: [poodle-up-check, generate-job-lists]
+  extends: [.build-and-test]
+
 # CORONA
 corona-up-check:
   variables: