theirix commented on code in PR #21487:
URL: https://github.com/apache/datafusion/pull/21487#discussion_r3066659295
##########
datafusion/functions-aggregate/benches/first_last.rs:
##########
@@ -72,92 +74,129 @@ fn prepare_groups_accumulator(is_first: bool) -> Box<dyn
GroupsAccumulator> {
}
}
-fn prepare_accumulator(is_first: bool) -> Box<dyn Accumulator> {
- let schema = Arc::new(Schema::new(vec![
- Field::new("value", DataType::Int64, true),
- Field::new("ord", DataType::Int64, true),
- ]));
-
- let order_expr = col("ord", &schema).unwrap();
- let sort_expr = PhysicalSortExpr {
- expr: order_expr,
- options: SortOptions::default(),
- };
-
- let value_field: Arc<Field> = Field::new("value", DataType::Int64,
true).into();
- let accumulator_args = AccumulatorArgs {
- return_field: Arc::clone(&value_field),
- schema: &schema,
- expr_fields: &[value_field],
- ignore_nulls: false,
- order_bys: std::slice::from_ref(&sort_expr),
- is_reversed: false,
- name: if is_first {
- "FIRST_VALUE(value ORDER BY ord)"
- } else {
- "LAST_VALUE(value ORDER BY ord)"
- },
- is_distinct: false,
- exprs: &[col("value", &schema).unwrap()],
- };
-
+fn create_trivial_accumulator(
+ is_first: bool,
+ ignore_nulls: bool,
+) -> Box<dyn Accumulator> {
if is_first {
- FirstValue::new().accumulator(accumulator_args).unwrap()
+ Box::new(
+ TrivialFirstValueAccumulator::try_new(&DataType::Int64,
ignore_nulls)
+ .unwrap(),
+ )
} else {
- LastValue::new().accumulator(accumulator_args).unwrap()
+ Box::new(
+ TrivialLastValueAccumulator::try_new(&DataType::Int64,
ignore_nulls).unwrap(),
+ )
}
}
#[expect(clippy::needless_pass_by_value)]
-fn convert_to_state_bench(
+#[expect(clippy::too_many_arguments)]
+fn evaluate_bench(
c: &mut Criterion,
is_first: bool,
+ emit_to: EmitTo,
name: &str,
values: ArrayRef,
+ ord: ArrayRef,
opt_filter: Option<&BooleanArray>,
+ num_groups: usize,
) {
+ let n = values.len();
+ let group_indices: Vec<usize> = (0..n).map(|i| i % num_groups).collect();
+
c.bench_function(name, |b| {
- b.iter(|| {
- let accumulator = prepare_groups_accumulator(is_first);
- black_box(
- accumulator
- .convert_to_state(std::slice::from_ref(&values),
opt_filter)
- .unwrap(),
- )
+ b.iter_custom(|iters| {
+ // Every `evaluate` call mutates the accumulator, so prebuild
`iters` accumulators
+ let mut accumulators: Vec<Box<dyn GroupsAccumulator>> = (0..iters)
Review Comment:
It's for scaling runs. One run of evaluate / update_bench / merge_bench is
diminishingly fast, so multiple accumulators are created just to run a
benchmark function on them. We cannot just run 1000 iterations for
`evaluate/...` since it mutates the state.
However, for update_bench / merge_bench we can merge multiple batches for
one bench run - I'll try this
--
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]
