Automate include grouping order with clang format (#491)

Author: PointKernel

.clang-format

@@ -15,7 +15,7 @@ AlignTrailingComments: true
 AllowAllArgumentsOnNextLine: true
 AllowAllConstructorInitializersOnNextLine: true
 AllowAllParametersOfDeclarationOnNextLine: true
-AllowShortBlocksOnASingleLine: true 
+AllowShortBlocksOnASingleLine: true
 AllowShortCaseLabelsOnASingleLine: true
 AllowShortEnumsOnASingleLine: true
 AllowShortFunctionsOnASingleLine: All
@@ -27,7 +27,7 @@ AlwaysBreakAfterDefinitionReturnType: None
 AlwaysBreakAfterReturnType: None
 AlwaysBreakBeforeMultilineStrings: true
 AlwaysBreakTemplateDeclarations: Yes
-BinPackArguments:  false       
+BinPackArguments:  false
 BinPackParameters: false
 BraceWrapping:
   AfterClass:            false
@@ -71,8 +71,24 @@ ForEachMacros:
   - foreach
   - Q_FOREACH
   - BOOST_FOREACH
-IncludeBlocks: Preserve
-IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeBlocks: Regroup
+IncludeCategories:
+  - Regex:           '^"' # quoted includes
+    Priority:        1
+  - Regex:           '^<(benchmark_defaults|benchmark_utils|test_utils)' # benchmark/test includes
+    Priority:        2
+  - Regex:           '^<cuco/' # cuco includes
+    Priority:        3
+  - Regex:           '^<nvbench/' # nvbench includes
+    Priority:        4
+  - Regex:           '^<(thrust|cub|cuda)/' # CCCL includes
+    Priority:        5
+  - Regex:           '^<(cooperative_groups|cuda.h|cuda_runtime|device_types|math_constants|nvtx3)' # CUDA includes
+    Priority:        6
+  - Regex:           '^<.*\..*' # other system includes (e.g. with a '.')
+    Priority:        7
+  - Regex:           '^<[^.]+' # STL includes (no '.')
+    Priority:        8
 IndentCaseLabels: true
 IndentPPDirectives: None
 IndentWidth:     2

benchmarks/defaults.hpp renamed to benchmarks/benchmark_defaults.hpp

@@ -14,20 +14,19 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
-#include <utils.hpp>
+#include <benchmark_defaults.hpp>
+#include <benchmark_utils.hpp>
 
 #include <cuco/distinct_count_estimator.cuh>
 #include <cuco/static_set.cuh>
 #include <cuco/utility/key_generator.cuh>
 
 #include <nvbench/nvbench.cuh>
 
+#include <cuda/functional>
 #include <thrust/device_vector.h>
 #include <thrust/iterator/transform_iterator.h>
 
-#include <cuda/functional>
-
 #include <cmath>
 #include <cstddef>
 

benchmarks/utils.hpp renamed to benchmarks/benchmark_utils.hpp

@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
+#include <benchmark_defaults.hpp>
 
 #include <cuco/hash_functions.cuh>
 

benchmarks/distinct_count_estimator_bench.cu

@@ -14,8 +14,8 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
-#include <utils.hpp>
+#include <benchmark_defaults.hpp>
+#include <benchmark_utils.hpp>
 
 #include <cuco/dynamic_map.cuh>
 #include <cuco/utility/key_generator.cuh>

benchmarks/hash_bench.cu

@@ -14,8 +14,8 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
-#include <utils.hpp>
+#include <benchmark_defaults.hpp>
+#include <benchmark_utils.hpp>
 
 #include <cuco/dynamic_map.cuh>
 #include <cuco/utility/key_generator.cuh>

benchmarks/hash_table/dynamic_map/contains_bench.cu

@@ -14,8 +14,8 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
-#include <utils.hpp>
+#include <benchmark_defaults.hpp>
+#include <benchmark_utils.hpp>
 
 #include <cuco/dynamic_map.cuh>
 #include <cuco/utility/key_generator.cuh>

benchmarks/hash_table/dynamic_map/erase_bench.cu

@@ -14,8 +14,8 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
-#include <utils.hpp>
+#include <benchmark_defaults.hpp>
+#include <benchmark_utils.hpp>
 
 #include <cuco/dynamic_map.cuh>
 #include <cuco/utility/key_generator.cuh>

benchmarks/hash_table/dynamic_map/find_bench.cu

@@ -14,8 +14,8 @@
  * limitations under the License.
  */
 
-#include <defaults.hpp>
-#include <utils.hpp>
+#include <benchmark_defaults.hpp>
+#include <benchmark_utils.hpp>
 
 #include <cuco/static_map.cuh>
 #include <cuco/utility/key_generator.cuh>