Merge Release 1.9.0

The Ginkgo team is proud to announce the new Ginkgo minor release 1.9.0.

This release brings new features such as:
- Support for half precision (IEEE FP16). The type `gko::half` can now be selected in most instances as the value type
  of a matrix, solver, preconditioner, etc. If the selected backend supports FP16 as a native type, the native type is
  used within the kernels, otherwise an overhead might occur. The new behavior is enabled by default, but it can be
  turned off during configuration.
- New implementations of the ILU and IC factorization for CUDA, HIP, OpenMP, and Reference backends. These are
  available in addition to the existing implementations based on the vendor libraries cuSPARSE and hipSPARSE.
- New (S)SOR and Gauss-Seidel preconditioners.
- Simplifyied distributed matrix assembly by exchanging local rows between neighboring processes.

And more!

See [the Changelog](./CHANGELOG.md) for more information.

.clang-format

@@ -58,7 +58,30 @@ ForEachMacros:
   - foreach
   - Q_FOREACH
   - BOOST_FOREACH
-IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeBlocks: Regroup
+IncludeCategories:
+  - Regex:    '^<oneapi/dpl.*'  # needs to be on top
+    Priority: -2
+  - Regex:    '<[^.]+>'  # standard library
+    Priority: 1
+  - Regex:    '(^<(hip/hip_runtime|cuda(_runtime)?)\.h)|common/cuda_hip/base/runtime\.hpp$'
+    Priority: 2
+    SortPriority: 2
+  - Regex:    '^<(omp|cu|hip|oneapi|thrust|CL/|cooperative|mpi|nvToolsExt|Kokkos).*'
+    Priority: 2
+    SortPriority: 3
+  - Regex:    '^<(nlohmann|gflags|gtest|sde_lib|papi).*'
+    Priority: 4
+  - Regex:    '<ginkgo/ginkgo.hpp>'
+    Priority: 6
+  - Regex:    '^<ginkgo/.*'
+    Priority: 7
+  - Regex:    '^<.*'  # other library includes
+    Priority: 5
+  - Regex:    '^.*'
+    Priority: 8
+IncludeIsMainRegex: '(_(stub|kernels|kernels2|test))?$'
+IncludeIsMainSourceRegex: '\.cu$|_kernels\.hpp$|\.dp\.cpp$'
 IndentCaseLabels: false
 IndentWidth:     4
 IndentWrappedFunctionNames: false

.github/bot-pr-base.sh

@@ -3,8 +3,6 @@
 source .github/bot-base.sh
 
 EXTENSION_REGEX='\.(cuh?|hpp|hpp\.inc?|cpp)$'
-FORMAT_HEADER_REGEX='^(benchmark|core|cuda|hip|include/ginkgo/core|omp|reference|dpcpp|common/unified|test)/'
-FORMAT_REGEX='^(common|examples)/'
 CLANG_FORMAT=clang-format-14
 
 echo -n "Collecting information on triggering PR"

.github/bot-pr-format-base.sh

@@ -14,9 +14,7 @@ git config user.name "ginkgo-bot"
 
 # save scripts from develop
 cp .clang-format .pre-commit-config.yaml /tmp
-pushd dev_tools/scripts || exit 1
-cp format_header.sh update_ginkgo_header.sh /tmp
-popd || exit 1
+cp dev_tools/scripts/update_ginkgo_header.sh /tmp
 
 # checkout current PR head
 LOCAL_BRANCH=format-tmp-$HEAD_BRANCH
@@ -25,7 +23,6 @@ git checkout -b $LOCAL_BRANCH fork/$HEAD_BRANCH
 # restore files from develop
 cp /tmp/.clang-format .
 cp /tmp/.pre-commit-config.yaml .
-cp /tmp/format_header.sh dev_tools/scripts/
 cp /tmp/update_ginkgo_header.sh dev_tools/scripts/
 
 # make base pre-commit config available

.github/workflows/intel.yml

@@ -33,20 +33,20 @@ jobs:
     - name: configure
       run: |
         source /etc/profile
-        module load intel-oneapi-compilers intel-oneapi-dpl intel-oneapi-mkl intel-oneapi-tbb cmake
+        module load intel-oneapi-compilers intel-oneapi-dpl intel-oneapi-mkl cmake
         mkdir build
         cd build
         cmake .. -DCMAKE_INSTALL_PREFIX=install_ginkgo -DCMAKE_CXX_FLAGS="-Wpedantic -ffp-model=precise" -DCMAKE_CXX_COMPILER=${{ matrix.config.compiler }} -DCMAKE_BUILD_TYPE=${{ matrix.config.build_type }} -DGINKGO_MIXED_PRECISION=${{ matrix.config.mixed }} -DGINKGO_BUILD_CUDA=OFF -DGINKGO_BUILD_HIP=OFF -DGINKGO_BUILD_MPI=OFF -DGINKGO_DPCPP_SINGLE_MODE=ON
         make -j8
         ONEAPI_DEVICE_SELECTOR=level_zero:gpu ctest -j10 --output-on-failure
-
+ 
     - name: install
       run: |
         source /etc/profile
-        module load intel-oneapi-compilers intel-oneapi-dpl intel-oneapi-mkl intel-oneapi-tbb cmake
+        module load intel-oneapi-compilers intel-oneapi-dpl intel-oneapi-mkl cmake
         cd build
         SYCL_DEVICE_FILTER=level_zero:gpu make install
         export GINKGO_PATH="$(pwd)/install_ginkgo/lib"
-        export LIBRARY_PATH=${GINKGO_PATH}:$LIBRARY_PATH
-        export LD_LIBRARY_PATH=${GINKGO_PATH}:$LD_LIBRARY_PATH
+        export LIBRARY_PATH=${ICL_INTEL_TBB_ROOT}/lib64:${GINKGO_PATH}:$LIBRARY_PATH
+        export LD_LIBRARY_PATH=${ICL_INTEL_TBB_ROOT}/lib64:${GINKGO_PATH}:$LD_LIBRARY_PATH
         SYCL_DEVICE_FILTER=level_zero:gpu make test_install