Resolve degenerate performance in create_structs_data

cpp/benchmarks/CMakeLists.txt

@@ -1,5 +1,5 @@
 # =============================================================================
-# Copyright (c) 2018-2023, NVIDIA CORPORATION.
+# Copyright (c) 2018-2024, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
 # in compliance with the License. You may obtain a copy of the License at
@@ -183,6 +183,11 @@ ConfigureNVBench(
   sort/sort_lists.cpp sort/sort_structs.cpp
 )
 
+# ##################################################################################################
+# * create benchmark
+# --------------------------------------------------------------------------------
+ConfigureNVBench(CREATE_NVBENCH create/create_structs.cpp)
+
 # ##################################################################################################
 # * quantiles benchmark
 # --------------------------------------------------------------------------------

cpp/benchmarks/create/create_structs.cpp

@@ -0,0 +1,31 @@
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <benchmarks/common/generate_nested_types.hpp>
+
+#include <nvbench/nvbench.cuh>
+
+void nvbench_create_structs(nvbench::state& state)
+{
+  state.exec(nvbench::exec_tag::sync,
+             [&](nvbench::launch& launch) { auto const table_ptr = create_structs_data(state); });
+}
+
+NVBENCH_BENCH(nvbench_create_structs)
+  .set_name("create_structs")
+  .add_int64_power_of_two_axis("NumRows", {10, 18, 26})
+  .add_int64_axis("Depth", {1, 8, 16})
+  .add_int64_axis("Nulls", {0, 1});

cpp/src/structs/utilities.cpp

@@ -17,6 +17,7 @@
 #include <cudf/column/column_factories.hpp>
 #include <cudf/detail/copy.hpp>
 #include <cudf/detail/null_mask.hpp>
+#include <cudf/detail/nvtx/ranges.hpp>
 #include <cudf/detail/structs/utilities.hpp>
 #include <cudf/detail/unary.hpp>
 #include <cudf/structs/structs_column_view.hpp>
@@ -229,6 +230,7 @@ std::unique_ptr<column> superimpose_nulls_no_sanitize(bitmask_type const* null_m
                                                       rmm::cuda_stream_view stream,
                                                       rmm::mr::device_memory_resource* mr)
 {
+  CUDF_FUNC_RANGE();
   if (input->type().id() == cudf::type_id::EMPTY) {
     // EMPTY columns should not have a null mask,
     // so don't superimpose null mask on empty columns.