groups_acc_more_robust_checks

Author: coderfender

datafusion/functions-aggregate/benches/count_distinct.rs

@@ -18,7 +18,7 @@
 use std::sync::Arc;
 
 use arrow::array::{
-    ArrayRef, Int8Array, Int16Array, Int64Array, UInt8Array, UInt16Array,
+    Array, ArrayRef, Int8Array, Int16Array, Int64Array, UInt8Array, UInt16Array,
 };
 use arrow::datatypes::{DataType, Field, Schema};
 use criterion::{Criterion, criterion_group, criterion_main};
@@ -87,13 +87,6 @@ fn create_i16_array(n_distinct: usize) -> Int16Array {
         .collect()
 }
 
-fn create_group_indices(num_groups: usize) -> Vec<usize> {
-    let mut rng = StdRng::seed_from_u64(42);
-    (0..BATCH_SIZE)
-        .map(|_| rng.random_range(0..num_groups))
-        .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()));
@@ -181,62 +174,100 @@ fn count_distinct_benchmark(c: &mut Criterion) {
     });
 }
 
+/// 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();
 
-    for num_groups in [10, 100, 1000] {
-        let n_distinct = BATCH_SIZE * 80 / 100;
-        let values = Arc::new(create_i64_array(n_distinct)) as ArrayRef;
-        let group_indices = create_group_indices(num_groups);
-
-        let (_schema, args) = prepare_args(DataType::Int64);
-
-        if count_fn.groups_accumulator_supported(args.clone()) {
-            c.bench_function(
-                &format!("count_distinct_groups i64 {num_groups} groups"),
-                |b| {
-                    b.iter(|| {
-                        let (_schema, args) = prepare_args(DataType::Int64);
-                        let mut acc = count_fn.create_groups_accumulator(args).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 i64 {num_groups} groups"),
-                |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 group_counts = [100, 1000, 10000];
+    let cardinalities = [("low", 20), ("mid", 80), ("high", 99)];
+    let distributions = ["uniform", "skewed"];
+
+    for num_groups in group_counts {
+        for (card_name, distinct_pct) in cardinalities {
+            for dist in distributions {
+                let name = format!("g{num_groups}_{card_name}_{dist}");
+                let n_distinct = BATCH_SIZE * distinct_pct / 100;
+                let values = Arc::new(create_i64_array(n_distinct)) as ArrayRef;
+                let group_indices = if dist == "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 {
+                    let arr = values.as_any().downcast_ref::<Int64Array>().unwrap();
+                    let mut group_rows: Vec<Vec<i64>> = vec![Vec::new(); num_groups];
+                    for (idx, &group_idx) in group_indices.iter().enumerate() {
+                        if arr.is_valid(idx) {
+                            group_rows[group_idx].push(arr.value(idx));
                         }
+                    }
+                    let group_arrays: Vec<ArrayRef> = group_rows
+                        .iter()
+                        .map(|rows| Arc::new(Int64Array::from(rows.clone())) as ArrayRef)
+                        .collect();
+
+                    c.bench_function(&format!("count_distinct_groups {name}"), |b| {
+                        b.iter(|| {
+                            let mut accumulators: Vec<_> = (0..num_groups)
+                                .map(|_| prepare_accumulator(DataType::Int64))
+                                .collect();
+
+                            for (group_idx, batch) in group_arrays.iter().enumerate() {
+                                if !batch.is_empty() {
+                                    accumulators[group_idx]
+                                        .update_batch(std::slice::from_ref(batch))
+                                        .unwrap();
+                                }
+                            }
 
-                        let _results: Vec<_> = accumulators
-                            .iter_mut()
-                            .map(|acc| acc.evaluate().unwrap())
-                            .collect();
-                    })
-                },
-            );
+                            let _results: Vec<_> = accumulators
+                                .iter_mut()
+                                .map(|acc| acc.evaluate().unwrap())
+                                .collect();
+                        })
+                    });
+                }
+            }
         }
     }
 }