Skip to content

Add benchmark for casting to RunEndEncoded (REE) #8710

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
merged 3 commits into from
Oct 27, 2025
+41 −0
Merged

Add benchmark for casting to RunEndEncoded (REE) #8710

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ea19521
Add benchmark for casting to RunEndEncoded (REE)
vegarsti Oct 26, 2025
adcfde3
Move benchmarks into existing cast_kernels benchmarks
alamb Oct 27, 2025
6a3d6b0
Merge remote-tracking branch 'apache/main' into cast-ree-bench
alamb Oct 27, 2025
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
1 change: 1 addition & 0 deletions arrow-cast/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,3 +75,4 @@ harness = false
[[bench]]
name = "parse_decimal"
harness = false

40 changes: 40 additions & 0 deletions arrow/benches/cast_kernels.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -359,6 +359,46 @@ fn add_benchmark(c: &mut Criterion) {
c.bench_function("cast binary view to string view", |b| {
b.iter(|| cast_array(&binary_view_array, DataType::Utf8View))
});

c.bench_function("cast string single run to ree<int32>", |b| {
let source_array = StringArray::from(vec!["a"; 8192]);
let array_ref = Arc::new(source_array) as ArrayRef;
let target_type = DataType::RunEndEncoded(
Arc::new(Field::new("run_ends", DataType::Int32, false)),
Arc::new(Field::new("values", DataType::Utf8, true)),
);
b.iter(|| cast(&array_ref, &target_type).unwrap());
});

c.bench_function("cast runs of 10 string to ree<int32>", |b| {
let source_array: Int32Array = (0..8192).map(|i| i / 10).collect();
let array_ref = Arc::new(source_array) as ArrayRef;
let target_type = DataType::RunEndEncoded(
Arc::new(Field::new("run_ends", DataType::Int32, false)),
Arc::new(Field::new("values", DataType::Int32, true)),
);
b.iter(|| cast(&array_ref, &target_type).unwrap());
});

c.bench_function("cast runs of 1000 int32s to ree<int32>", |b| {
let source_array: Int32Array = (0..8192).map(|i| i / 1000).collect();
let array_ref = Arc::new(source_array) as ArrayRef;
let target_type = DataType::RunEndEncoded(
Arc::new(Field::new("run_ends", DataType::Int32, false)),
Arc::new(Field::new("values", DataType::Int32, true)),
);
b.iter(|| cast(&array_ref, &target_type).unwrap());
});

c.bench_function("cast no runs of int32s to ree<int32>", |b| {
let source_array: Int32Array = (0..8192).collect();
let array_ref = Arc::new(source_array) as ArrayRef;
let target_type = DataType::RunEndEncoded(
Arc::new(Field::new("run_ends", DataType::Int32, false)),
Arc::new(Field::new("values", DataType::Int32, true)),
);
b.iter(|| cast(&array_ref, &target_type).unwrap());
});
}

criterion_group!(benches, add_benchmark);
Expand Down
Loading