Add decimal types to cuIO benchmarks (#9776)

Closes #9769
Depends on #9775

Benchmarks now include decimal32/64/128 columns for all supported formats.
Also fixes an issue in distribution factory, which caused all normal distributions to generate `upper_bound` in many cases.

Authors:
  - Vukasin Milovanovic (https://github.com/vuule)
  - Jason Lowe (https://github.com/jlowe)

Approvers:
  - Devavret Makkar (https://github.com/devavret)
  - https://github.com/nvdbaranec

URL: #9776

cpp/benchmarks/common/generate_benchmark_input.cpp

@@ -161,8 +161,29 @@ struct random_value_fn<T, typename std::enable_if_t<cudf::is_chrono<T>()>> {
  */
 template <typename T>
 struct random_value_fn<T, typename std::enable_if_t<cudf::is_fixed_point<T>()>> {
-  random_value_fn(distribution_params<T> const&) {}
-  T operator()(std::mt19937& engine) { CUDF_FAIL("Not implemented"); }
+  using rep = typename T::rep;
+  rep const lower_bound;
+  rep const upper_bound;
+  distribution_fn<rep> dist;
+  std::optional<numeric::scale_type> scale;
+
+  random_value_fn(distribution_params<rep> const& desc)
+    : lower_bound{desc.lower_bound},
+      upper_bound{desc.upper_bound},
+      dist{make_distribution<rep>(desc.id, desc.lower_bound, desc.upper_bound)}
+  {
+  }
+
+  T operator()(std::mt19937& engine)
+  {
+    if (not scale.has_value()) {
+      int const max_scale = std::numeric_limits<rep>::digits10;
+      auto scale_dist     = make_distribution<int>(distribution_id::NORMAL, -max_scale, max_scale);
+      scale = numeric::scale_type{std::max(std::min(scale_dist(engine), max_scale), -max_scale)};
+    }
+    // Clamp the generated random value to the specified range
+    return T{std::max(std::min(dist(engine), upper_bound), lower_bound), *scale};
+  }
 };
 
 /**

cpp/benchmarks/common/generate_benchmark_input.hpp

@@ -216,6 +216,7 @@ class data_profile {
   distribution_params<cudf::string_view> string_dist_desc{{distribution_id::NORMAL, 0, 32}};
   distribution_params<cudf::list_view> list_dist_desc{
     cudf::type_id::INT32, {distribution_id::GEOMETRIC, 0, 100}, 2};
+  std::map<cudf::type_id, distribution_params<__uint128_t>> decimal_params;
 
   double bool_probability        = 0.5;
   double null_frequency          = 0.01;
@@ -284,9 +285,17 @@ class data_profile {
   }
 
   template <typename T, typename std::enable_if_t<cudf::is_fixed_point<T>()>* = nullptr>
-  distribution_params<T> get_distribution_params() const
+  distribution_params<typename T::rep> get_distribution_params() const
   {
-    CUDF_FAIL("Not implemented");
+    using rep = typename T::rep;
+    auto it   = decimal_params.find(cudf::type_to_id<T>());
+    if (it == decimal_params.end()) {
+      auto const range = default_range<rep>();
+      return distribution_params<rep>{default_distribution_id<rep>(), range.first, range.second};
+    } else {
+      auto& desc = it->second;
+      return {desc.id, static_cast<rep>(desc.lower_bound), static_cast<rep>(desc.upper_bound)};
+    }
   }
 
   auto get_bool_probability() const { return bool_probability; }

cpp/benchmarks/common/random_distribution_factory.hpp

@@ -21,19 +21,24 @@
 #include <memory>
 #include <random>
 
+/**
+ * @brief Generates a normal(binomial) distribution between zero and upper_bound.
+ */
 template <typename T, typename std::enable_if_t<std::is_integral<T>::value, T>* = nullptr>
-auto make_normal_dist(T range_start, T range_end)
+auto make_normal_dist(T upper_bound)
 {
-  using uT            = typename std::make_unsigned<T>::type;
-  uT const range_size = range_end - range_start;
-  return std::binomial_distribution<uT>(range_size, 0.5);
+  using uT = typename std::make_unsigned<T>::type;
+  return std::binomial_distribution<uT>(upper_bound, 0.5);
 }
 
+/**
+ * @brief Generates a normal distribution between zero and upper_bound.
+ */
 template <typename T, std::enable_if_t<cudf::is_floating_point<T>()>* = nullptr>
-auto make_normal_dist(T range_start, T range_end)
+auto make_normal_dist(T upper_bound)
 {
-  T const mean   = range_start / 2 + range_end / 2;
-  T const stddev = range_end / 6 - range_start / 6;
+  T const mean   = upper_bound / 2;
+  T const stddev = upper_bound / 6;
   return std::normal_distribution<T>(mean, stddev);
 }
 
@@ -82,8 +87,8 @@ distribution_fn<T> make_distribution(distribution_id did, T lower_bound, T upper
 {
   switch (did) {
     case distribution_id::NORMAL:
-      return [lower_bound, dist = make_normal_dist(lower_bound, upper_bound)](
-               std::mt19937& engine) mutable -> T { return dist(engine) - lower_bound; };
+      return [lower_bound, dist = make_normal_dist(upper_bound - lower_bound)](
+               std::mt19937& engine) mutable -> T { return dist(engine) + lower_bound; };
     case distribution_id::UNIFORM:
       return [dist = make_uniform_dist(lower_bound, upper_bound)](
                std::mt19937& engine) mutable -> T { return dist(engine); };
@@ -104,8 +109,8 @@ distribution_fn<T> make_distribution(distribution_id dist_id, T lower_bound, T u
 {
   switch (dist_id) {
     case distribution_id::NORMAL:
-      return [dist = make_normal_dist(lower_bound, upper_bound)](
-               std::mt19937& engine) mutable -> T { return dist(engine); };
+      return [lower_bound, dist = make_normal_dist(upper_bound - lower_bound)](
+               std::mt19937& engine) mutable -> T { return dist(engine) + lower_bound; };
     case distribution_id::UNIFORM:
       return [dist = make_uniform_dist(lower_bound, upper_bound)](
                std::mt19937& engine) mutable -> T { return dist(engine); };

cpp/benchmarks/io/csv/csv_reader_benchmark.cpp

@@ -70,6 +70,7 @@ void BM_csv_read_varying_options(benchmark::State& state)
   auto const data_types =
     dtypes_for_column_selection(get_type_or_group({int32_t(type_group_id::INTEGRAL),
                                                    int32_t(type_group_id::FLOATING_POINT),
+                                                   int32_t(type_group_id::FIXED_POINT),
                                                    int32_t(type_group_id::TIMESTAMP),
                                                    int32_t(cudf::type_id::STRING)}),
                                 col_sel);
@@ -143,6 +144,7 @@ void BM_csv_read_varying_options(benchmark::State& state)
 
 RD_BENCHMARK_DEFINE_ALL_SOURCES(CSV_RD_BM_INPUTS_DEFINE, integral, type_group_id::INTEGRAL);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(CSV_RD_BM_INPUTS_DEFINE, floats, type_group_id::FLOATING_POINT);
+RD_BENCHMARK_DEFINE_ALL_SOURCES(CSV_RD_BM_INPUTS_DEFINE, decimal, type_group_id::FIXED_POINT);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(CSV_RD_BM_INPUTS_DEFINE, timestamps, type_group_id::TIMESTAMP);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(CSV_RD_BM_INPUTS_DEFINE, string, cudf::type_id::STRING);
 

cpp/benchmarks/io/csv/csv_writer_benchmark.cpp

@@ -63,6 +63,7 @@ void BM_csv_write_varying_options(benchmark::State& state)
 
   auto const data_types = get_type_or_group({int32_t(type_group_id::INTEGRAL),
                                              int32_t(type_group_id::FLOATING_POINT),
+                                             int32_t(type_group_id::FIXED_POINT),
                                              int32_t(type_group_id::TIMESTAMP),
                                              int32_t(cudf::type_id::STRING)});
 
@@ -96,6 +97,7 @@ void BM_csv_write_varying_options(benchmark::State& state)
 
 WR_BENCHMARK_DEFINE_ALL_SINKS(CSV_WR_BM_INOUTS_DEFINE, integral, type_group_id::INTEGRAL);
 WR_BENCHMARK_DEFINE_ALL_SINKS(CSV_WR_BM_INOUTS_DEFINE, floats, type_group_id::FLOATING_POINT);
+WR_BENCHMARK_DEFINE_ALL_SINKS(CSV_WR_BM_INOUTS_DEFINE, decimal, type_group_id::FIXED_POINT);
 WR_BENCHMARK_DEFINE_ALL_SINKS(CSV_WR_BM_INOUTS_DEFINE, timestamps, type_group_id::TIMESTAMP);
 WR_BENCHMARK_DEFINE_ALL_SINKS(CSV_WR_BM_INOUTS_DEFINE, string, cudf::type_id::STRING);
 

cpp/benchmarks/io/orc/orc_reader_benchmark.cpp

@@ -91,8 +91,10 @@ void BM_orc_read_varying_options(benchmark::State& state)
   auto const data_types =
     dtypes_for_column_selection(get_type_or_group({int32_t(type_group_id::INTEGRAL_SIGNED),
                                                    int32_t(type_group_id::FLOATING_POINT),
+                                                   int32_t(type_group_id::FIXED_POINT),
                                                    int32_t(type_group_id::TIMESTAMP),
-                                                   int32_t(cudf::type_id::STRING)}),
+                                                   int32_t(cudf::type_id::STRING),
+                                                   int32_t(cudf::type_id::LIST)}),
                                 col_sel);
   auto const tbl  = create_random_table(data_types, data_types.size(), table_size_bytes{data_size});
   auto const view = tbl->view();
@@ -158,6 +160,7 @@ void BM_orc_read_varying_options(benchmark::State& state)
 
 RD_BENCHMARK_DEFINE_ALL_SOURCES(ORC_RD_BM_INPUTS_DEFINE, integral, type_group_id::INTEGRAL_SIGNED);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(ORC_RD_BM_INPUTS_DEFINE, floats, type_group_id::FLOATING_POINT);
+RD_BENCHMARK_DEFINE_ALL_SOURCES(ORC_RD_BM_INPUTS_DEFINE, decimal, type_group_id::FIXED_POINT);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(ORC_RD_BM_INPUTS_DEFINE, timestamps, type_group_id::TIMESTAMP);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(ORC_RD_BM_INPUTS_DEFINE, string, cudf::type_id::STRING);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(ORC_RD_BM_INPUTS_DEFINE, list, cudf::type_id::LIST);

cpp/benchmarks/io/orc/orc_writer_benchmark.cpp

@@ -70,8 +70,10 @@ void BM_orc_write_varying_options(benchmark::State& state)
 
   auto const data_types = get_type_or_group({int32_t(type_group_id::INTEGRAL_SIGNED),
                                              int32_t(type_group_id::FLOATING_POINT),
+                                             int32_t(type_group_id::FIXED_POINT),
                                              int32_t(type_group_id::TIMESTAMP),
-                                             int32_t(cudf::type_id::STRING)});
+                                             int32_t(cudf::type_id::STRING),
+                                             int32_t(cudf::type_id::LIST)});
 
   auto const tbl  = create_random_table(data_types, data_types.size(), table_size_bytes{data_size});
   auto const view = tbl->view();
@@ -101,6 +103,7 @@ void BM_orc_write_varying_options(benchmark::State& state)
 
 WR_BENCHMARK_DEFINE_ALL_SINKS(ORC_WR_BM_INOUTS_DEFINE, integral, type_group_id::INTEGRAL_SIGNED);
 WR_BENCHMARK_DEFINE_ALL_SINKS(ORC_WR_BM_INOUTS_DEFINE, floats, type_group_id::FLOATING_POINT);
+WR_BENCHMARK_DEFINE_ALL_SINKS(ORC_WR_BM_INOUTS_DEFINE, decimal, type_group_id::FIXED_POINT);
 WR_BENCHMARK_DEFINE_ALL_SINKS(ORC_WR_BM_INOUTS_DEFINE, timestamps, type_group_id::TIMESTAMP);
 WR_BENCHMARK_DEFINE_ALL_SINKS(ORC_WR_BM_INOUTS_DEFINE, string, cudf::type_id::STRING);
 WR_BENCHMARK_DEFINE_ALL_SINKS(ORC_WR_BM_INOUTS_DEFINE, list, cudf::type_id::LIST);

cpp/benchmarks/io/parquet/parquet_reader_benchmark.cpp

@@ -92,8 +92,10 @@ void BM_parq_read_varying_options(benchmark::State& state)
   auto const data_types =
     dtypes_for_column_selection(get_type_or_group({int32_t(type_group_id::INTEGRAL),
                                                    int32_t(type_group_id::FLOATING_POINT),
+                                                   int32_t(type_group_id::FIXED_POINT),
                                                    int32_t(type_group_id::TIMESTAMP),
-                                                   int32_t(cudf::type_id::STRING)}),
+                                                   int32_t(cudf::type_id::STRING),
+                                                   int32_t(cudf::type_id::LIST)}),
                                 col_sel);
   auto const tbl  = create_random_table(data_types, data_types.size(), table_size_bytes{data_size});
   auto const view = tbl->view();
@@ -160,6 +162,7 @@ void BM_parq_read_varying_options(benchmark::State& state)
 
 RD_BENCHMARK_DEFINE_ALL_SOURCES(PARQ_RD_BM_INPUTS_DEFINE, integral, type_group_id::INTEGRAL);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(PARQ_RD_BM_INPUTS_DEFINE, floats, type_group_id::FLOATING_POINT);
+RD_BENCHMARK_DEFINE_ALL_SOURCES(PARQ_RD_BM_INPUTS_DEFINE, decimal, type_group_id::FIXED_POINT);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(PARQ_RD_BM_INPUTS_DEFINE, timestamps, type_group_id::TIMESTAMP);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(PARQ_RD_BM_INPUTS_DEFINE, string, cudf::type_id::STRING);
 RD_BENCHMARK_DEFINE_ALL_SOURCES(PARQ_RD_BM_INPUTS_DEFINE, list, cudf::type_id::LIST);

cpp/benchmarks/io/parquet/parquet_writer_benchmark.cpp

@@ -71,8 +71,10 @@ void BM_parq_write_varying_options(benchmark::State& state)
 
   auto const data_types = get_type_or_group({int32_t(type_group_id::INTEGRAL_SIGNED),
                                              int32_t(type_group_id::FLOATING_POINT),
+                                             int32_t(type_group_id::FIXED_POINT),
                                              int32_t(type_group_id::TIMESTAMP),
-                                             int32_t(cudf::type_id::STRING)});
+                                             int32_t(cudf::type_id::STRING),
+                                             int32_t(cudf::type_id::LIST)});
 
   auto const tbl  = create_random_table(data_types, data_types.size(), table_size_bytes{data_size});
   auto const view = tbl->view();
@@ -103,6 +105,7 @@ void BM_parq_write_varying_options(benchmark::State& state)
 
 WR_BENCHMARK_DEFINE_ALL_SINKS(PARQ_WR_BM_INOUTS_DEFINE, integral, type_group_id::INTEGRAL);
 WR_BENCHMARK_DEFINE_ALL_SINKS(PARQ_WR_BM_INOUTS_DEFINE, floats, type_group_id::FLOATING_POINT);
+WR_BENCHMARK_DEFINE_ALL_SINKS(PARQ_WR_BM_INOUTS_DEFINE, decimal, type_group_id::FIXED_POINT);
 WR_BENCHMARK_DEFINE_ALL_SINKS(PARQ_WR_BM_INOUTS_DEFINE, timestamps, type_group_id::TIMESTAMP);
 WR_BENCHMARK_DEFINE_ALL_SINKS(PARQ_WR_BM_INOUTS_DEFINE, string, cudf::type_id::STRING);
 WR_BENCHMARK_DEFINE_ALL_SINKS(PARQ_WR_BM_INOUTS_DEFINE, list, cudf::type_id::LIST);