Merge branch 'develop' into feature/bowen/add-clang-format

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

@@ -21,7 +21,7 @@ variables:
 # Project specific variants for ruby
   PROJECT_RUBY_VARIANTS: "~shared +openmp +vectorization +tests"
 # Project specific deps for ruby
-  PROJECT_RUBY_DEPS: "^blt@develop "
+  PROJECT_RUBY_DEPS:
 
 # Poodle
 # Arguments for top level allocation
@@ -31,7 +31,7 @@ variables:
 # Project specific variants for poodle
   PROJECT_POODLE_VARIANTS: "~shared +openmp +vectorization +tests"
 # Project specific deps for poodle
-  PROJECT_POODLE_DEPS: "^blt@develop "
+  PROJECT_POODLE_DEPS:
 
 # Corona
 # Arguments for top level allocation
@@ -41,7 +41,7 @@ variables:
 # Project specific variants for corona
   PROJECT_CORONA_VARIANTS: "~shared ~openmp +vectorization +tests"
 # Project specific deps for corona
-  PROJECT_CORONA_DEPS: "^blt@develop "
+  PROJECT_CORONA_DEPS:
 
 # Tioga
 # Arguments for top level allocation
@@ -51,7 +51,7 @@ variables:
 # Project specific variants for corona
   PROJECT_TIOGA_VARIANTS: "~shared +openmp +vectorization +tests"
 # Project specific deps for corona
-  PROJECT_TIOGA_DEPS: "^blt@develop "
+  PROJECT_TIOGA_DEPS:
 
 # Lassen and Butte use a different job scheduler (spectrum lsf) that does not
 # allow pre-allocation the same way slurm does.
@@ -60,7 +60,7 @@ variables:
 # Project specific variants for lassen
   PROJECT_LASSEN_VARIANTS: "~shared +openmp +vectorization +tests cuda_arch=70"
 # Project specific deps for lassen
-  PROJECT_LASSEN_DEPS: "^blt@develop "
+  PROJECT_LASSEN_DEPS:
 
 # Configuration shared by build and test jobs specific to this project.
 # Not all configuration can be shared. Here projects can fine tune the

.gitlab/jobs/corona.yml

@@ -26,14 +26,14 @@
 # ${PROJECT_<MACHINE>_DEPS} in the extra jobs. There is no reason not to fully
 # describe the spec here.
 
-rocmcc_5_7_0_hip_desul_atomics:
+rocmcc_5_7_1_hip_desul_atomics:
   variables:
-    SPEC: " ~shared +rocm ~openmp +tests +desul amdgpu_target=gfx906 %rocmcc@=5.7.0 ^[email protected].0 ^blt@develop"
+    SPEC: " ~shared +rocm ~openmp +tests +desul amdgpu_target=gfx906 %rocmcc@=5.7.1 ^[email protected].1"
   extends: .job_on_corona
 
 clang_19_0_0_sycl_gcc_10_3_1_rocmcc_5_7_1_hip:
   variables:
-    SPEC: " ~shared +sycl ~openmp +tests %clang@=19.0.0 cxxflags==\"-w -fsycl -fsycl-unnamed-lambda -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906\" ^blt@develop"
+    SPEC: " ~shared +sycl ~openmp +tests %clang@=19.0.0 cxxflags==\"-w -fsycl -fsycl-unnamed-lambda -fsycl-targets=amdgcn-amd-amdhsa -Xsycl-target-backend --offload-arch=gfx906\""
     MODULE_LIST: "rocm/5.7.1"
   extends: .job_on_corona
 

.gitlab/jobs/lassen.yml

@@ -17,15 +17,7 @@
 # project. 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
-# Warning: allowed to fail because of a bug in Spack > 0.20.3
-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 ^[email protected]+allow-unsupported-compilers ${PROJECT_LASSEN_DEPS} ^blt@develop"
-    MODULE_LIST: "cuda/11.2.0"
-    LASSEN_JOB_ALLOC: "1 -W 60 -q pci"
-  extends: .job_on_lassen
-  allow_failure: true
+# No overridden jobs so far.
 
 ############
 # Extra jobs
@@ -36,14 +28,14 @@ xl_2022_08_19_gcc_8_3_1_cuda_11_2_0:
 
 gcc_8_3_1_omptask:
   variables:
-    SPEC: " ~shared +openmp +omptask +tests %gcc@=8.3.1 ^blt@develop"
+    SPEC: " ~shared +openmp +omptask +tests %gcc@=8.3.1 ${PROJECT_LASSEN_DEPS}"
   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 +tests +cuda %gcc@=8.3.1 cuda_arch=70 ^cuda@11.5.0+allow-unsupported-compilers ^blt@develop"
-    MODULE_LIST: "cuda/11.5.0"
+    SPEC: " ~shared +openmp +tests +cuda %gcc@=8.3.1 cuda_arch=70 ^cuda@11.7.0+allow-unsupported-compilers ${PROJECT_LASSEN_DEPS}"
+    MODULE_LIST: "cuda/11.7.0"
     LASSEN_JOB_ALLOC: "1 --atsdisable -W 30 -q pci"
 
 ##########
@@ -52,7 +44,7 @@ gcc_8_3_1_cuda_11_5_0_ats_disabled:
 
 clang_13_0_1_libcpp:
   variables:
-    SPEC: " ~shared +openmp +tests %clang@=13.0.1 cflags==\"-DGTEST_HAS_CXXABI_H_=0\" cxxflags==\"-stdlib=libc++ -DGTEST_HAS_CXXABI_H_=0\" ^blt@develop"
+    SPEC: " ~shared +openmp +tests %clang@=13.0.1 cflags==\"-DGTEST_HAS_CXXABI_H_=0\" cxxflags==\"-stdlib=libc++ -DGTEST_HAS_CXXABI_H_=0\""
   extends: .job_on_lassen
 
 #clang_14_0_5_asan:
@@ -62,16 +54,17 @@ clang_13_0_1_libcpp:
 #    LSAN_OPTIONS: "suppressions=${CI_PROJECT_DIR}/suppressions.asan"
 #  extends: .job_on_lassen
 
-gcc_8_3_1_cuda_10_1_243_desul_atomics:
+gcc_8_3_1_cuda_11_7_desul_atomics:
   variables:
-    SPEC: " ~shared +openmp +tests +cuda +desul %gcc@=8.3.1 cuda_arch=70 ^[email protected]+allow-unsupported-compilers ^blt@develop"
+    SPEC: " ~shared +openmp +tests +cuda +desul %gcc@=8.3.1 cuda_arch=70 ^[email protected]+allow-unsupported-compilers"
+    MODULE_LIST: "cuda/11.7.0"
   extends: .job_on_lassen
 
 # Warning: Allowed to fail temporarily
 # Deactivated due to issues with OpenMP Target and various tests and compilers.
 clang_16_0_6_ibm_omptarget:
   variables:
-    SPEC: " ~shared +openmp +omptarget +tests %clang@=16.0.6.ibm.gcc.8.3.1 ^blt@develop"
+    SPEC: " ~shared +openmp +omptarget +tests %clang@=16.0.6.ibm.gcc.8.3.1"
     ON_LASSEN: "OFF"
   extends: .job_on_lassen
   allow_failure: true

.gitlab/jobs/poodle.yml

@@ -17,6 +17,14 @@
 # project. We keep ${PROJECT_<MACHINE>_VARIANTS} and ${PROJECT_<MACHINE>_DEPS}
 # when possible so that the comparison with the original job is easier.
 
+# Known issue currently under investigation
+# https://github.com/LLNL/RAJA/pull/1712#issuecomment-2292006843
+intel_2023_2_1:
+  variables:
+    SPEC: "${PROJECT_POODLE_VARIANTS} %intel@=2023.2.1 ${PROJECT_POODLE_DEPS}"
+  extends: .job_on_poodle
+  allow_failure: true
+
 # Identical to shared job, but use OpenMP tasks and no vectorization
 clang_14_0_6:
   variables:
@@ -29,21 +37,6 @@ gcc_10_3_1:
     SPEC: " ~shared +openmp +omptask +tests %gcc@=10.3.1 ${PROJECT_POODLE_DEPS}"
   extends: .job_on_poodle
 
-# Identical to shared job, but use OpenMP tasks and no vectorization
-# Deactivated (too long on poodle)
-intel_19_1_2_gcc_10_3_1:
-  variables:
-    ON_POODLE: "OFF"
-    SPEC: " ~shared +openmp +omptask +tests %intel@=19.1.2.gcc.10.3.1 ${PROJECT_POODLE_DEPS}"
-  extends: .job_on_poodle
-
-# Allowed to fail
-intel_2022_1_0:
-  variables:
-    SPEC: "${PROJECT_POODLE_VARIANTS} %intel@=2022.1.0 ${PROJECT_POODLE_DEPS}"
-  allow_failure: true
-  extends: .job_on_poodle
-
 ############
 # Extra jobs
 ############
@@ -53,16 +46,16 @@ intel_2022_1_0:
 
 clang_14_0_6_openmp_off:
   variables:
-    SPEC: " ~shared ~openmp +tests %clang@=14.0.6 ^blt@develop"
+    SPEC: " ~shared ~openmp +tests %clang@=14.0.6"
   extends: .job_on_poodle
 
 gcc_10_3_1_openmp_default:
   variables:
-    SPEC: " ~shared +tests %gcc@=10.3.1 ^blt@develop"
+    SPEC: " ~shared +tests %gcc@=10.3.1"
   extends: .job_on_poodle
 
 # OTHERS
 clang_14_0_6_gcc_10_3_1_desul_atomics:
   variables:
-    SPEC: " ~shared +openmp +tests +desul %clang@=14.0.6.gcc.10.3.1 ^blt@develop"
+    SPEC: " ~shared +openmp +tests +desul %clang@=14.0.6.gcc.10.3.1"
   extends: .job_on_poodle

.gitlab/jobs/ruby.yml

@@ -29,18 +29,13 @@ gcc_10_3_1:
     SPEC: " ~shared +openmp +omptask +tests %gcc@=10.3.1 ${PROJECT_RUBY_DEPS}"
   extends: .job_on_ruby
 
-# Identical to shared job, but use OpenMP tasks and no vectorization
-intel_19_1_2_gcc_10_3_1:
+# Known issue currently under investigation
+# https://github.com/LLNL/RAJA/pull/1712#issuecomment-2292006843
+intel_2023_2_1:
   variables:
-    SPEC: " ~shared +openmp +omptask +tests %intel@=19.1.2.gcc.10.3.1 ${PROJECT_RUBY_DEPS}"
+    SPEC: "${PROJECT_RUBY_VARIANTS} %intel@=2023.2.1 ${PROJECT_RUBY_DEPS}"
   extends: .job_on_ruby
-
-# Allowed to fail
-intel_2022_1_0:
-  variables:
-    SPEC: "${PROJECT_RUBY_VARIANTS} %intel@=2022.1.0 ${PROJECT_RUBY_DEPS}"
   allow_failure: true
-  extends: .job_on_ruby
 
 ############
 # Extra jobs
@@ -51,16 +46,16 @@ intel_2022_1_0:
 
 clang_14_0_6_openmp_off:
   variables:
-    SPEC: " ~shared ~openmp +tests %clang@=14.0.6 ^blt@develop"
+    SPEC: " ~shared ~openmp +tests %clang@=14.0.6"
   extends: .job_on_ruby
 
 gcc_10_3_1_openmp_default:
   variables:
-    SPEC: " ~shared +tests %gcc@=10.3.1 ^blt@develop"
+    SPEC: " ~shared +tests %gcc@=10.3.1"
   extends: .job_on_ruby
 
 # OTHERS
 clang_14_0_6_gcc_10_3_1_desul_atomics:
   variables:
-    SPEC: " ~shared +openmp +tests +desul %clang@=14.0.6.gcc.10.3.1 ^blt@develop"
+    SPEC: " ~shared +openmp +tests +desul %clang@=14.0.6.gcc.10.3.1"
   extends: .job_on_ruby

.gitlab/jobs/tioga.yml

@@ -17,7 +17,13 @@
 # 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.
+# Compiler error preventing a test to succeed.
+# https://github.com/LLNL/RAJA/pull/1712#issuecomment-2316335119
+cce_18_0_0:
+  variables:
+    SPEC: "${PROJECT_TIOGA_VARIANTS} %cce@=18.0.0 ${PROJECT_TIOGA_DEPS}"
+  extends: .job_on_tioga
+  allow_failure: true
 
 ############
 # Extra jobs
@@ -26,12 +32,17 @@
 # ${PROJECT_<MACHINE>_DEPS} in the extra jobs. There is no reason not to fully
 # describe the spec here.
 
-rocmcc_6_1_1_hip_desul_atomics:
+cce_17_0_1:
+  variables:
+    SPEC: "${PROJECT_TIOGA_VARIANTS} %cce@=17.0.1 ${PROJECT_TIOGA_DEPS}"
+  extends: .job_on_tioga
+
+rocmcc_6_2_0_hip_desul_atomics:
   variables:
-    SPEC: "~shared +rocm ~openmp +desul +tests amdgpu_target=gfx90a %rocmcc@=6.1.1 ^hip@6.1.1 ^blt@develop"
+    SPEC: "~shared +rocm ~openmp +desul +tests amdgpu_target=gfx90a %rocmcc@=6.2.0 ^hip@6.2.0"
   extends: .job_on_tioga
 
-rocmcc_6_1_1_hip_openmp:
+rocmcc_6_2_0_hip_openmp:
   variables:
-    SPEC: "~shared +rocm +openmp +omptask +tests amdgpu_target=gfx90a %rocmcc@=6.1.1 ^hip@6.1.1 ^blt@develop"
+    SPEC: "~shared +rocm +openmp +omptask +tests amdgpu_target=gfx90a %rocmcc@=6.2.0 ^hip@6.2.0"
   extends: .job_on_tioga

README.md

@@ -71,8 +71,8 @@ More details about RAJA configuration options are located in the RAJA User Guide
 We also maintain a [**RAJA Template Project**](https://github.com/LLNL/RAJA-project-template) that shows how to use RAJA in a CMake project, either as a Git
 submodule or as an installed library.
 
-User Documentation
--------------------
+User Documentation and Tutorials
+--------------------------------
 
 The RAJA User Guide is the best place to start learning about RAJA and how to
 use it.
@@ -81,6 +81,8 @@ The most recent version of the User Guide (RAJA develop branch): https://raja.re
 
 To access docs for other RAJA released versions: https://readthedocs.org/projects/raja/
 
+We maintain a repository for the RAJA portaility suite tutorial material: https://github.com/LLNL/raja-suite-tutorial
+
 To cite RAJA, please use the following references:
 
 * RAJA Performance Portability Layer. https://github.com/LLNL/RAJA

benchmark/CMakeLists.txt

@@ -11,10 +11,17 @@ if (RAJA_ENABLE_CUDA)
     SOURCES host-device-lambda-benchmark.cpp)
 endif()
 
+if (RAJA_ENABLE_DESUL)
 raja_add_benchmark(
   NAME benchmark-atomic
   SOURCES benchmark-atomic.cpp)
+endif()
+
+#TODO: Fix build issues
+#raja_add_benchmark(
+#  NAME ltimes
+#  SOURCES ltimes.cpp)
 
 raja_add_benchmark(
-  NAME ltimes
-  SOURCES ltimes.cpp)
+  NAME raja_view_blur
+  SOURCES raja_view_blur.cpp)