Skip to content

bench(arrow): cover Boolean, Dictionary, and REE coalescing #11722

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
etseidl merged 2 commits into from
Oct 21, 2026
Merged

bench(arrow): cover Boolean, Dictionary, and REE coalescing #11722

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b240a14
bench(arrow): cover Boolean, Dictionary, and REE coalescing
Rich-T-kid Oct 19, 2026
48d5ff9
Merge branch 'main' into rich-T-kid/coalescer-specialized-benchmarks
Rich-T-kid Oct 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 86 additions & 0 deletions arrow/benches/coalesce_kernels.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
//! Benchmarks for the `coalesce` kernels in Arrow.
use arrow::util::bench_util::*;
use arrow::util::data_gen::create_random_array;
use std::sync::Arc;

use arrow::array::*;
Expand Down Expand Up @@ -105,6 +106,29 @@ fn add_all_filter_benchmarks(c: &mut Criterion) {
// TODO model other dictionary types here (FixedSizeBinary for example)
]));

let single_dictionary_schema = SchemaRef::new(Schema::new(vec![Field::new(
"value",
DataType::Dictionary(Box::new(DataType::Int32), Box::new(DataType::Utf8)),
true,
)]));

let single_run_end_schema = SchemaRef::new(Schema::new(vec![Field::new(
"value",
DataType::RunEndEncoded(
Arc::new(Field::new(
Field::REE_RUN_ENDS_FIELD_DEFAULT_NAME,
DataType::Int32,
false,
)),
Arc::new(Field::new(
Field::REE_VALUES_FIELD_DEFAULT_NAME,
DataType::Int32,
true,
)),
),
true,
)]));

let single_fsb16_schema = SchemaRef::new(Schema::new(vec![Field::new(
"value",
DataType::FixedSizeBinary(16),
Expand Down Expand Up @@ -320,6 +344,18 @@ fn add_all_filter_benchmarks(c: &mut Criterion) {
}
.build();

FilterBenchmarkBuilder {
c,
name: "single_dict",
batch_size,
num_output_batches: 25,
null_density,
selectivity,
max_string_len: 30,
schema: &single_dictionary_schema,
}
.build();

FilterBenchmarkBuilder {
c,
name: "single_fsb16",
Expand Down Expand Up @@ -356,6 +392,18 @@ fn add_all_filter_benchmarks(c: &mut Criterion) {
}
.build();

FilterBenchmarkBuilder {
c,
name: "single_ree",
batch_size,
num_output_batches: 25,
null_density,
selectivity,
max_string_len: 0,
schema: &single_run_end_schema,
}
.build();

FilterBenchmarkBuilder {
c,
name: "single_fsl4",
Expand Down Expand Up @@ -470,6 +518,29 @@ fn add_all_gather_benchmarks(c: &mut Criterion, operation: GatherOperation) {
Field::new("float_val2", DataType::Float64, true),
]));

let single_dictionary_schema = SchemaRef::new(Schema::new(vec![Field::new(
"value",
DataType::Dictionary(Box::new(DataType::Int32), Box::new(DataType::Utf8)),
true,
)]));

let single_run_end_schema = SchemaRef::new(Schema::new(vec![Field::new(
"value",
DataType::RunEndEncoded(
Arc::new(Field::new(
Field::REE_RUN_ENDS_FIELD_DEFAULT_NAME,
DataType::Int32,
false,
)),
Arc::new(Field::new(
Field::REE_VALUES_FIELD_DEFAULT_NAME,
DataType::Int32,
true,
)),
),
true,
)]));

let single_fsb16_schema = SchemaRef::new(Schema::new(vec![Field::new(
"value",
DataType::FixedSizeBinary(16),
Expand Down Expand Up @@ -568,6 +639,12 @@ fn add_all_gather_benchmarks(c: &mut Criterion, operation: GatherOperation) {
max_string_len: 30,
schema: &mixed_dict_schema,
},
GatherBenchmarkScenario {
name: "single_dict",
num_output_batches: 25,
max_string_len: 30,
schema: &single_dictionary_schema,
},
GatherBenchmarkScenario {
name: "single_fsb16",
num_output_batches: 50,
Expand All @@ -586,6 +663,12 @@ fn add_all_gather_benchmarks(c: &mut Criterion, operation: GatherOperation) {
max_string_len: 0,
schema: &single_boolean_schema,
},
GatherBenchmarkScenario {
name: "single_ree",
num_output_batches: 25,
max_string_len: 0,
schema: &single_run_end_schema,
},
GatherBenchmarkScenario {
name: "single_fsl4",
num_output_batches: 50,
Expand Down Expand Up @@ -1385,6 +1468,9 @@ impl DataStreamBuilder {
10,
seed,
)),
DataType::RunEndEncoded(_, _) => {
create_random_array(field, self.batch_size, self.null_density, 0.5).unwrap()
}
_ => panic!("Unsupported data type: {field:?}"),
}
}
Expand Down
Loading