21575: chore: add count distinct group benchmarks

.cursor/rules.md

@@ -0,0 +1,5 @@
+The AI agents should never link to any issue or a pull request
+in any GitHub repository in the code reviews!
+
+The AI agents should not review AI agents' config files like CLAUDE.md or AGENTS.md!
+

AGENTS.md

@@ -39,3 +39,8 @@ When creating a PR, you MUST follow the [PR template](.github/pull_request_templ
 
 See the [Testing Quick Start](docs/source/contributor-guide/testing.md#testing-quick-start)
 for the recommended pre-PR test commands.
+The AI agents should never link to any issue or a pull request
+in any GitHub repository in the code reviews!
+
+The AI agents should not review AI agents' config files like CLAUDE.md or AGENTS.md!
+

datafusion/functions-aggregate/benches/count_distinct.rs

@@ -23,7 +23,7 @@ use arrow::array::{
 use arrow::datatypes::{DataType, Field, Schema};
 use criterion::{Criterion, criterion_group, criterion_main};
 use datafusion_expr::function::AccumulatorArgs;
-use datafusion_expr::{Accumulator, AggregateUDFImpl};
+use datafusion_expr::{Accumulator, AggregateUDFImpl, EmitTo};
 use datafusion_functions_aggregate::count::Count;
 use datafusion_physical_expr::expressions::col;
 use rand::rngs::StdRng;
@@ -87,6 +87,30 @@ fn create_i16_array(n_distinct: usize) -> Int16Array {
         .collect()
 }
 
+fn prepare_args(data_type: DataType) -> (Arc<Schema>, AccumulatorArgs<'static>) {
+    let schema = Arc::new(Schema::new(vec![Field::new("f", data_type, true)]));
+    let schema_leaked: &'static Schema = Box::leak(Box::new((*schema).clone()));
+    let expr = col("f", schema_leaked).unwrap();
+    let expr_leaked: &'static _ = Box::leak(Box::new(expr));
+    let return_field: Arc<Field> = Field::new("f", DataType::Int64, true).into();
+    let return_field_leaked: &'static _ = Box::leak(Box::new(return_field.clone()));
+    let expr_field = expr_leaked.return_field(schema_leaked).unwrap();
+    let expr_field_leaked: &'static _ = Box::leak(Box::new(expr_field));
+
+    let accumulator_args = AccumulatorArgs {
+        return_field: return_field_leaked.clone(),
+        schema: schema_leaked,
+        expr_fields: std::slice::from_ref(expr_field_leaked),
+        ignore_nulls: false,
+        order_bys: &[],
+        is_reversed: false,
+        name: "count(distinct f)",
+        is_distinct: true,
+        exprs: std::slice::from_ref(expr_leaked),
+    };
+    (schema, accumulator_args)
+}
+
 fn count_distinct_benchmark(c: &mut Criterion) {
     for pct in [80, 99] {
         let n_distinct = BATCH_SIZE * pct / 100;
@@ -150,5 +174,101 @@ fn count_distinct_benchmark(c: &mut Criterion) {
     });
 }
 
-criterion_group!(benches, count_distinct_benchmark);
+/// Create group indices with uniform distribution
+fn create_uniform_groups(num_groups: usize) -> Vec<usize> {
+    let mut rng = StdRng::seed_from_u64(42);
+    (0..BATCH_SIZE)
+        .map(|_| rng.random_range(0..num_groups))
+        .collect()
+}
+
+/// Create group indices with skewed distribution (80% in 20% of groups)
+fn create_skewed_groups(num_groups: usize) -> Vec<usize> {
+    let mut rng = StdRng::seed_from_u64(42);
+    let hot_groups = (num_groups / 5).max(1);
+    (0..BATCH_SIZE)
+        .map(|_| {
+            if rng.random_range(0..100) < 80 {
+                rng.random_range(0..hot_groups)
+            } else {
+                rng.random_range(0..num_groups)
+            }
+        })
+        .collect()
+}
+
+fn count_distinct_groups_benchmark(c: &mut Criterion) {
+    let count_fn = Count::new();
+
+    // bench different scenarios
+    let scenarios = [
+        // (name, num_groups, distinct_pct, group_fn)
+        ("sparse_uniform", 10, 80, "uniform"),
+        ("moderate_uniform", 100, 80, "uniform"),
+        ("dense_uniform", 1000, 80, "uniform"),
+        ("sparse_skewed", 10, 80, "skewed"),
+        ("dense_skewed", 1000, 80, "skewed"),
+        ("sparse_high_cardinality", 10, 99, "uniform"),
+        ("dense_low_cardinality", 1000, 20, "uniform"),
+    ];
+
+    for (name, num_groups, distinct_pct, group_type) in scenarios {
+        let n_distinct = BATCH_SIZE * distinct_pct / 100;
+        let values = Arc::new(create_i64_array(n_distinct)) as ArrayRef;
+        let group_indices = if group_type == "uniform" {
+            create_uniform_groups(num_groups)
+        } else {
+            create_skewed_groups(num_groups)
+        };
+
+        let (_schema, args) = prepare_args(DataType::Int64);
+
+        if count_fn.groups_accumulator_supported(args.clone()) {
+            c.bench_function(&format!("count_distinct_groups {name}"), |b| {
+                b.iter(|| {
+                    let mut acc =
+                        count_fn.create_groups_accumulator(args.clone()).unwrap();
+                    acc.update_batch(
+                        std::slice::from_ref(&values),
+                        &group_indices,
+                        None,
+                        num_groups,
+                    )
+                    .unwrap();
+                    acc.evaluate(EmitTo::All).unwrap()
+                })
+            });
+        } else {
+            c.bench_function(&format!("count_distinct_groups {name}"), |b| {
+                b.iter(|| {
+                    let mut accumulators: Vec<_> = (0..num_groups)
+                        .map(|_| prepare_accumulator(DataType::Int64))
+                        .collect();
+
+                    let arr = values.as_any().downcast_ref::<Int64Array>().unwrap();
+                    for (idx, group_idx) in group_indices.iter().enumerate() {
+                        if let Some(val) = arr.value(idx).into() {
+                            let single_val =
+                                Arc::new(Int64Array::from(vec![Some(val)])) as ArrayRef;
+                            accumulators[*group_idx]
+                                .update_batch(std::slice::from_ref(&single_val))
+                                .unwrap();
+                        }
+                    }
+
+                    let _results: Vec<_> = accumulators
+                        .iter_mut()
+                        .map(|acc| acc.evaluate().unwrap())
+                        .collect();
+                })
+            });
+        }
+    }
+}
+
+criterion_group!(
+    benches,
+    count_distinct_benchmark,
+    count_distinct_groups_benchmark
+);
 criterion_main!(benches);