Support lists of structs in row lexicographic comparator

cpp/benchmarks/sort/nested_types_common.hpp

@@ -28,17 +28,23 @@
 
 #include <random>
 
-inline std::unique_ptr<cudf::table> create_lists_data(nvbench::state& state)
+inline std::unique_ptr<cudf::table> create_lists_data(nvbench::state& state,
+                                                      cudf::size_type const num_columns = 1,
+                                                      cudf::size_type const min_val     = 0,
+                                                      cudf::size_type const max_val     = 5)
 {
   const size_t size_bytes(state.get_int64("size_bytes"));
   const cudf::size_type depth{static_cast<cudf::size_type>(state.get_int64("depth"))};
   auto const null_frequency{state.get_float64("null_frequency")};
 
   data_profile table_profile;
-  table_profile.set_distribution_params(cudf::type_id::LIST, distribution_id::UNIFORM, 0, 5);
+  table_profile.set_distribution_params(
+    cudf::type_id::LIST, distribution_id::UNIFORM, min_val, max_val);
   table_profile.set_list_depth(depth);
   table_profile.set_null_probability(null_frequency);
-  return create_random_table({cudf::type_id::LIST}, table_size_bytes{size_bytes}, table_profile);
+  return create_random_table(std::vector<cudf::type_id>(num_columns, cudf::type_id::LIST),
+                             table_size_bytes{size_bytes},
+                             table_profile);
 }
 
 inline std::unique_ptr<cudf::table> create_structs_data(nvbench::state& state,

cpp/benchmarks/sort/sort_lists.cpp

@@ -20,18 +20,82 @@
 
 #include <nvbench/nvbench.cuh>
 
-void nvbench_sort_lists(nvbench::state& state)
+namespace {
+constexpr cudf::size_type min_val = 0;
+constexpr cudf::size_type max_val = 100;
+
+void sort_multiple_lists(nvbench::state& state)
+{
+  auto const num_columns = static_cast<cudf::size_type>(state.get_int64("num_columns"));
+  auto const input_table = create_lists_data(state, num_columns, min_val, max_val);
+  auto const stream      = cudf::get_default_stream();
+
+  state.set_cuda_stream(nvbench::make_cuda_stream_view(stream.value()));
+  state.exec(nvbench::exec_tag::sync, [&](nvbench::launch& launch) {
+    cudf::detail::sorted_order(
+      *input_table, {}, {}, stream, rmm::mr::get_current_device_resource());
+  });
+}
+
+void sort_lists_of_structs(nvbench::state& state)
 {
-  auto const table = create_lists_data(state);
+  auto const num_columns = static_cast<cudf::size_type>(state.get_int64("num_columns"));
+  auto const lists_table = create_lists_data(state, num_columns, min_val, max_val);
 
+  // After having a table of (multiple) lists columns, convert those lists columns into lists of
+  // structs columns. The children of these structs columns are also children of the original lists
+  // columns.
+  // Such resulted lists-of-structs columns are very similar to the original lists-of-integers
+  // columns so their benchmarks can be somewhat comparable.
+  std::vector<cudf::column_view> lists_of_structs;
+  for (auto const& col : lists_table->view()) {
+    auto const child = col.child(cudf::lists_column_view::child_column_index);
+
+    // Put the child column under a struct column having the same null mask/null count.
+    auto const new_child = cudf::column_view{cudf::data_type{cudf::type_id::STRUCT},
+                                             child.size(),
+                                             nullptr,
+                                             child.null_mask(),
+                                             child.null_count(),
+                                             child.offset(),
+                                             {child}};
+    auto const converted_col =
+      cudf::column_view{cudf::data_type{cudf::type_id::LIST},
+                        col.size(),
+                        nullptr,
+                        col.null_mask(),
+                        col.null_count(),
+                        col.offset(),
+                        {col.child(cudf::lists_column_view::offsets_column_index), new_child}};
+    lists_of_structs.push_back(converted_col);
+  }
+
+  auto const input_table = cudf::table_view{lists_of_structs};
+  auto const stream      = cudf::get_default_stream();
+
+  state.set_cuda_stream(nvbench::make_cuda_stream_view(stream.value()));
   state.exec(nvbench::exec_tag::sync, [&](nvbench::launch& launch) {
     rmm::cuda_stream_view stream_view{launch.get_stream()};
-    cudf::detail::sorted_order(*table, {}, {}, stream_view, rmm::mr::get_current_device_resource());
+    cudf::detail::sorted_order(input_table, {}, {}, stream, rmm::mr::get_current_device_resource());
   });
 }
 
+}  // namespace
+
+void nvbench_sort_lists(nvbench::state& state)
+{
+  const auto has_lists_of_structs = state.get_int64("lists_of_structs") > 0;
+  if (has_lists_of_structs) {
+    sort_lists_of_structs(state);
+  } else {
+    sort_multiple_lists(state);
+  }
+}
+
 NVBENCH_BENCH(nvbench_sort_lists)
   .set_name("sort_list")
   .add_int64_power_of_two_axis("size_bytes", {10, 18, 24, 28})
   .add_int64_axis("depth", {1, 4})
+  .add_int64_axis("num_columns", {1})
+  .add_int64_axis("lists_of_structs", {0, 1})
   .add_float64_axis("null_frequency", {0, 0.2});

cpp/include/cudf/detail/sorting.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2022, NVIDIA CORPORATION.
+ * Copyright (c) 2019-2023, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -16,6 +16,7 @@
 
 #pragma once
 
+#include <cudf/sorting.hpp>
 #include <cudf/types.hpp>
 #include <cudf/utilities/default_stream.hpp>
 
@@ -61,6 +62,20 @@ std::unique_ptr<table> sort_by_key(table_view const& values,
                                    rmm::cuda_stream_view stream,
                                    rmm::mr::device_memory_resource* mr);
 
+/**
+ * @copydoc cudf::rank
+ *
+ * @param[in] stream CUDA stream used for device memory operations and kernel launches.
+ */
+std::unique_ptr<column> rank(column_view const& input,
+                             rank_method method,
+                             order column_order,
+                             null_policy null_handling,
+                             null_order null_precedence,
+                             bool percentage,
+                             rmm::cuda_stream_view stream,
+                             rmm::mr::device_memory_resource* mr);
+
 /**
  * @copydoc cudf::stable_sort_by_key
  *