Merge pull request #509 from LLNL/task/rc-v2025.03.0

Release Candidate v2025.03.0

Author: rhornung67

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,25 @@
+---
+name: Bug report
+about: Create a report to help us improve
+
+---
+
+**Describe the bug**
+
+A clear and concise description of what the bug is:
+
+**To Reproduce**
+
+Steps to reproduce the behavior:
+
+**Expected behavior**
+
+A clear and concise description of what you expected to happen:
+
+**Compilers & Libraries (please complete the following information):**
+ - Compiler & version: [e.g. GCC 4.9.3]:
+ - CUDA version (if applicable):
+
+**Additional context**
+
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,22 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+
+A clear and concise description of what the problem is.
+
+**Describe the solution you'd like**
+
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+
+Add any other context or information about the feature request here.
+

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +1,4 @@
-# Summary (Write a short headline summary of PR)
+# Summary
 
 - This PR is a (refactoring, bugfix, feature, something else)
 - It does the following (modify list as needed):

.github/workflows/build.yml

@@ -0,0 +1,77 @@
+on: push
+name: Build
+jobs:
+  build_docker:
+    strategy:
+      matrix:
+        target: [gcc12, gcc13, clang13, clang15, rocm6, rocm6_desul, intel2024, intel2024_debug, intel2024_sycl]
+    runs-on: ubuntu-latest
+    steps:
+    - run: |
+        sudo rm -rf /usr/share/dotnet
+        sudo rm -rf /usr/local/lib/android
+        sudo rm -rf /opt/ghc
+        sudo rm -rf /opt/hostedtoolcache/CodeQL
+        sudo docker image prune --all --force
+    - uses: actions/checkout@v2
+      with:
+        submodules: recursive
+    - uses: docker/setup-buildx-action@v3
+    - uses: docker/build-push-action@v6
+      with:
+        target: ${{ matrix.target }}
+  build_mac:
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          submodules: recursive
+      - uses: threeal/cmake-action@v1.3.0
+        with:
+          build-dir: build
+          options:
+            CMAKE_CXX_STANDARD=14
+            ENABLE_OPENMP=Off
+            CMAKE_BUILD_TYPE=Release
+          run-build: true
+          build-args: '--parallel 16'
+      - uses: threeal/ctest-action@v1.1.0
+  build_windows:
+    strategy:
+      matrix:
+        shared: 
+## ====================================
+## Shared library build generated undefined symbol errors that are not
+## understood -RDH
+##      - args: 
+##          BUILD_SHARED_LIBS=On 
+##          CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS=On
+        - args: BUILD_SHARED_LIBS=Off
+          
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          submodules: recursive
+## ====================================
+## Config and build action
+      - uses: threeal/cmake-action@v1.3.0
+        with:
+          build-dir: build
+          options:
+            ENABLE_WARNINGS_AS_ERRORS=Off
+            BLT_CXX_STD=c++17
+            CMAKE_BUILD_TYPE=Release
+            PERFSUITE_RUN_SHORT_TEST=On
+            ${{ matrix.shared.args }}
+          run-build: true
+          build-args: '--parallel 16'
+## ====================================
+## Print the contents of the test directory in the build space (debugging)
+##    - run: | 
+##        dir -r D:\a\RAJA\RAJA\build\test
+## ====================================
+## Run tests action
+      - uses: threeal/ctest-action@v1.1.0
+        with:
+          build-config: Debug

.gitlab-ci.yml

@@ -72,7 +72,7 @@ stages:
     include:
       - local: '.gitlab/custom-jobs-and-variables.yml'
       - project: 'radiuss/radiuss-shared-ci'
-        ref: 'v2024.06.0'
+        ref: 'v2024.12.0'
         file: 'pipelines/${CI_MACHINE}.yml'
       - artifact: '${CI_MACHINE}-jobs.yml'
         job: 'generate-job-lists'
@@ -85,7 +85,7 @@ include:
     file: 'id_tokens.yml'
   # [Optional] checks preliminary to running the actual CI test
   #- project: 'radiuss/radiuss-shared-ci'
-  #  ref: 'v2024.06.0'
+  #  ref: 'v2024.12.0'
   #  file: 'utilities/preliminary-ignore-draft-pr.yml'
   # pipelines subscribed by the project
   - local: '.gitlab/subscribed-pipelines.yml'

.gitlab/custom-jobs-and-variables.yml

@@ -1,5 +1,5 @@
 ###############################################################################
-# Copyright (c) 2017-24, Lawrence Livermore National Security, LLC
+# Copyright (c) 2017-25, Lawrence Livermore National Security, LLC
 # and RAJA Performance Suite project contributors.
 # See the RAJAPerf/LICENSE file for details.
 #
@@ -15,7 +15,7 @@ variables:
 
 # Ruby
 # Arguments for top level allocation
-  RUBY_SHARED_ALLOC: "--exclusive --reservation=ci --time=40 --nodes=1"
+  RUBY_SHARED_ALLOC: "--exclusive --reservation=ci --time=45 --nodes=1"
 # Arguments for job level allocation
 # Note: We repeat the reservation, necessary when jobs are manually re-triggered.
   RUBY_JOB_ALLOC: "--reservation=ci --nodes=1"
@@ -26,7 +26,7 @@ variables:
 
 # Poodle
 # Arguments for top level allocation
-  POODLE_SHARED_ALLOC: "--exclusive --time=40 --nodes=1"
+  POODLE_SHARED_ALLOC: "--exclusive --time=45 --nodes=1"
 # Arguments for job level allocation
   POODLE_JOB_ALLOC: "--nodes=1"
 # Project specific variants for poodle
@@ -36,7 +36,7 @@ variables:
 
 # Corona
 # Arguments for top level allocation
-  CORONA_SHARED_ALLOC: "--exclusive --time-limit=12m --nodes=1 -o per-resource.count=2"
+  CORONA_SHARED_ALLOC: "--exclusive --time-limit=25m --nodes=1 -o per-resource.count=2"
 # Arguments for job level allocation
   CORONA_JOB_ALLOC: "--nodes=1 --begin-time=+5s"
 # Project specific variants for corona
@@ -46,7 +46,7 @@ variables:
 
 # Tioga
 # Arguments for top level allocation
-  TIOGA_SHARED_ALLOC: "--queue=pci --exclusive --time-limit=26m --nodes=1 -o per-resource.count=2"
+  TIOGA_SHARED_ALLOC: "--queue=pci --exclusive --time-limit=31m --nodes=1 -o per-resource.count=2"
 # Arguments for job level allocation
   TIOGA_JOB_ALLOC: "--nodes=1 --begin-time=+5s"
 # Project specific variants for tioga
@@ -57,7 +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 20 -q pci"
+  LASSEN_JOB_ALLOC: "1 -W 25 -q pci"
 # Project specific variants for lassen
   PROJECT_LASSEN_VARIANTS: "~shared +openmp cuda_arch=70"
 # Project specific deps for lassen
@@ -71,3 +71,18 @@ variables:
   artifacts:
     reports:
       junit: junit.xml
+    name: "${CI_PROJECT_NAME}-${CI_MACHINE}-${CI_JOB_NAME}-${CI_PIPELINE_ID}"
+    paths:
+      - ./*.cmake
+
+.reproducer_vars:
+  script:
+    - |
+      echo -e "
+      # Required variables \n
+      export MODULE_LIST=\"${MODULE_LIST}\" \n
+      export SPEC=\"${SPEC//\"/\\\"}\" \n
+      # Allow to set job script for debugging (only this differs from CI) \n
+      export DEBUG_MODE=true \n
+      # Using the CI build cache is optional and requires a token. Set it like so: \n
+      # export REGISTRY_TOKEN=\"<your token here>\" \n"

.gitlab/jobs/corona.yml

@@ -1,5 +1,5 @@
 ###############################################################################
-# Copyright (c) 2017-24, Lawrence Livermore National Security, LLC
+# Copyright (c) 2017-25, Lawrence Livermore National Security, LLC
 # and RAJA Performance Suite project contributors.
 # See the RAJAPerf/LICENSE file for details.
 #
@@ -9,9 +9,7 @@
 # Override reproducer section to define project specific variables.
 .corona_reproducer_vars:
   script:
-    - |
-      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
-      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+    - !reference [.reproducer_vars, script]
 
 ########################
 # Overridden shared jobs
@@ -29,6 +27,10 @@
 # ${PROJECT_<MACHINE>_DEPS} in the extra jobs. There is no reason not to fully
 # describe the spec here.
 
-# With GitLab CI, included files cannot be empty.
-variables:
-  INCLUDED_FILE_CANNOT_BE_EMPTY: "True"
+clang_20_0_0_sycl_gcc_10_3_1_rocmcc_6_0_2_hip:
+  variables:
+    SPEC: " ~shared +sycl ~openmp tests=basic %clang@=20.0.0 cxxflags==\"-w -fsycl -fsycl-unnamed-lambda -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906\" ^blt@develop"
+    MODULE_LIST: "rocm/6.0.2"
+    SYCL_PATH: "/usr/WS2/raja-dev/clang_sycl_730cd3a5275f_hip_gcc10.3.1_rocm6.0.2/"
+    LD_LIBRARY_PATH: "${SYCL_PATH}/lib:${SYCL_PATH}/lib64:${LD_LIBRARY_PATH}"
+  extends: .job_on_corona

.gitlab/jobs/lassen.yml

@@ -1,5 +1,5 @@
 ###############################################################################
-# Copyright (c) 2017-24, Lawrence Livermore National Security, LLC
+# Copyright (c) 2017-25, Lawrence Livermore National Security, LLC
 # and RAJA Performance Suite project contributors.
 # See the RAJAPerf/LICENSE file for details.
 #
@@ -9,9 +9,7 @@
 # Override reproducer section to define project specific variables.
 .lassen_reproducer_vars:
   script:
-    - |
-      echo -e "export MODULE_LIST=\"${MODULE_LIST}\""
-      echo -e "export SPEC=\"${SPEC//\"/\\\"}\""
+    - !reference [.reproducer_vars, script]
 
 ########################
 # Overridden shared jobs
@@ -20,14 +18,7 @@
 # We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS} So that
 # the comparison with the original job is easier.
 
-# Overriding shared spec: Longer allocation + extra flags
-xl_2022_08_19_gcc_8_3_1_cuda_11_2_0:
-  variables:
-    SPEC: "${PROJECT_LASSEN_VARIANTS} +cuda cxxflags==\"-qthreaded -std=c++14 -O3 -qstrict -qxlcompatmacros -qlanglvl=extended0x -qalias=noansi -qhot -qpic -qsmp=omp -qsuppress=1500-029 -qsuppress=1500-036\" %xl@=16.1.1.12.gcc.8.3.1 ^cuda@11.2.0+allow-unsupported-compilers ${PROJECT_LASSEN_DEPS}"
-    MODULE_LIST: "cuda/11.2.0"
-    LASSEN_JOB_ALLOC: "1 -W 60 -q pci"
-  extends: .job_on_lassen
-
+# No jobs overridden
 
 ############
 # Extra jobs
@@ -38,21 +29,21 @@ xl_2022_08_19_gcc_8_3_1_cuda_11_2_0:
 
 gcc_8_3_1:
   variables:
-    SPEC: " ~shared +openmp %gcc@=8.3.1 ${PROJECT_LASSEN_DEPS}"
+    SPEC: " ~shared +openmp %gcc@=8.3.1 ^blt@develop"
   extends: .job_on_lassen
 
-gcc_8_3_1_cuda_11_5_0_ats_disabled:
+gcc_8_3_1_cuda_11_7_0_ats_disabled:
   extends: .job_on_lassen
   variables:
-    SPEC: " ~shared +openmp +cuda %gcc@=8.3.1 cuda_arch=70 ^cuda@11.5.0+allow-unsupported-compilers ${PROJECT_LASSEN_DEPS}"
-    MODULE_LIST: "cuda/11.5.0"
+    SPEC: " ~shared +openmp +cuda %gcc@=8.3.1 cuda_arch=70 ^cuda@11.7.0+allow-unsupported-compilers ^blt@develop"
+    MODULE_LIST: "cuda/11.7.0"
     LASSEN_JOB_ALLOC: "1 --atsdisable -W 30 -q pci"
 
-gcc_8_3_1_cuda_11_5_0_ats_disabled_mpi:
+gcc_8_3_1_cuda_11_7_0_ats_disabled_mpi:
   extends: .job_on_lassen
   variables:
-    SPEC: " ~shared +openmp +cuda +mpi %gcc@=8.3.1 cuda_arch=70 ^cuda@11.5.0+allow-unsupported-compilers ^spectrum-mpi ${PROJECT_LASSEN_DEPS}"
-    MODULE_LIST: "cuda/11.5.0"
+    SPEC: " ~shared +openmp +cuda +mpi %gcc@=8.3.1 cuda_arch=70 ^cuda@11.7.0+allow-unsupported-compilers ^spectrum-mpi ^blt@develop"
+    MODULE_LIST: "cuda/11.7.0"
     LASSEN_JOB_ALLOC: "1 --atsdisable -W 30 -q pci"
 
 ##########
@@ -61,7 +52,7 @@ gcc_8_3_1_cuda_11_5_0_ats_disabled_mpi:
 
 clang_13_0_1_libcpp:
   variables:
-    SPEC: " ~shared +openmp %clang@=13.0.1 cflags==\"-DGTEST_HAS_CXXABI_H_=0\" cxxflags==\"-stdlib=libc++ -DGTEST_HAS_CXXABI_H_=0\" ${PROJECT_LASSEN_DEPS}"
+    SPEC: " ~shared +openmp %clang@=13.0.1 cflags==\"-DGTEST_HAS_CXXABI_H_=0\" cxxflags==\"-stdlib=libc++ -DGTEST_HAS_CXXABI_H_=0\" ^blt@develop"
   extends: .job_on_lassen
 
 #clang_14_0_5_asan:
@@ -71,8 +62,7 @@ clang_13_0_1_libcpp:
 #    LSAN_OPTIONS: "suppressions=${CI_PROJECT_DIR}/tpl/RAJA/suppressions.asan"
 #  extends: .job_on_lassen
 
-# Activated in RAJA, but we don't use desul atomics here
-#gcc_8_3_1_cuda_10_1_168_desul_atomics:
-#  variables:
-#    SPEC: "+openmp +cuda +desul %gcc@=8.3.1 cuda_arch=70 cuda_arch=70 ^cuda@10.1.243+allow-unsupported-compilers ${PROJECT_LASSEN_DEPS}"
-#  extends: .job_on_lassen
+clang_16_0_6_omptarget:
+  variables:
+    SPEC: " ~shared +openmp +omptarget %clang@=16.0.6.cuda.11.8.0.gcc.11.2.1 ^blt@develop"
+  extends: .job_on_lassen