Skip to content
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

Filter DecimalArray as PrimitiveArray ~5x Faster (#2637) #2870

Merged
merged 3 commits into from
Oct 15, 2022
Merged

Filter DecimalArray as PrimitiveArray ~5x Faster (#2637) #2870

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
ba5b771
Filter DecimalArray as PrimitiveArray (#2637)
tustvold Oct 14, 2022
5010ade
Add decimal filter benches
tustvold Oct 15, 2022
4f1bbfc
Format
tustvold Oct 15, 2022
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
24 changes: 24 additions & 0 deletions arrow/benches/filter_kernels.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ use arrow::array::*;
use arrow::compute::filter;
use arrow::datatypes::{Field, Float32Type, Int32Type, Schema, UInt8Type};

use arrow_array::types::Decimal128Type;
use criterion::{criterion_group, criterion_main, Criterion};

fn bench_filter(data_array: &dyn Array, filter_array: &BooleanArray) {
Expand Down Expand Up @@ -143,6 +144,29 @@ fn add_benchmark(c: &mut Criterion) {
b.iter(|| bench_built_filter(&sparse_filter, &data_array))
});

let data_array = create_primitive_array::<Decimal128Type>(size, 0.0);
c.bench_function("filter decimal128 (kept 1/2)", |b| {
b.iter(|| bench_filter(&data_array, &filter_array))
});
c.bench_function("filter decimal128 high selectivity (kept 1023/1024)", |b| {
b.iter(|| bench_filter(&data_array, &dense_filter_array))
});
c.bench_function("filter decimal128 low selectivity (kept 1/1024)", |b| {
b.iter(|| bench_filter(&data_array, &sparse_filter_array))
});

c.bench_function("filter context decimal128 (kept 1/2)", |b| {
b.iter(|| bench_built_filter(&filter, &data_array))
});
c.bench_function(
"filter context decimal128 high selectivity (kept 1023/1024)",
|b| b.iter(|| bench_built_filter(&dense_filter, &data_array)),
);
c.bench_function(
"filter context decimal128 low selectivity (kept 1/1024)",
|b| b.iter(|| bench_built_filter(&sparse_filter, &data_array)),
);

let data_array = create_string_array::<i32>(size, 0.5);
c.bench_function("filter context string (kept 1/2)", |b| {
b.iter(|| bench_built_filter(&filter, &data_array))
Expand Down
10 changes: 10 additions & 0 deletions arrow/src/compute/kernels/filter.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -338,6 +338,16 @@ fn filter_array(values: &dyn Array, predicate: &FilterPredicate) -> Result<Array
// actually filter
_ => downcast_primitive_array! {
values => Ok(Arc::new(filter_primitive(values, predicate))),
DataType::Decimal128(p, s) => {
let values = values.as_any().downcast_ref::<Decimal128Array>().unwrap();
let filtered = filter_primitive(values, predicate);
Ok(Arc::new(filtered.with_precision_and_scale(*p, *s).unwrap()))
}
DataType::Decimal256(p, s) => {
let values = values.as_any().downcast_ref::<Decimal256Array>().unwrap();
let filtered = filter_primitive(values, predicate);
Ok(Arc::new(filtered.with_precision_and_scale(*p, *s).unwrap()))
}
DataType::Boolean => {
let values = values.as_any().downcast_ref::<BooleanArray>().unwrap();
Ok(Arc::new(filter_boolean(values, predicate)))
Expand Down