martin-g commented on code in PR #21575:
URL: https://github.com/apache/datafusion/pull/21575#discussion_r3093533497
##########
datafusion/functions-aggregate/benches/count_distinct.rs:
##########
@@ -150,5 +174,107 @@ 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();
+
+ 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()
Review Comment:
```suggestion
std::hint::black_box(acc.evaluate(EmitTo::All).unwrap())
```
blackbox the result to protect from dead code elimination
##########
datafusion/functions-aggregate/benches/count_distinct.rs:
##########
@@ -150,5 +174,107 @@ 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)
Review Comment:
```suggestion
rng.random_range(hot_groups..num_groups)
```
##########
datafusion/functions-aggregate/benches/count_distinct.rs:
##########
@@ -150,5 +174,107 @@ 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();
+
+ 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();
Review Comment:
```suggestion
let results: Vec<_> = accumulators
.iter_mut()
.map(|acc| acc.evaluate().unwrap())
.collect();
std::hint::black_box(results);
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
