Skip to content

perf: optimize nanvl in datafusion-functions #23458

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
Dandandan merged 3 commits into from
Jul 11, 2026
Merged

perf: optimize nanvl in datafusion-functions #23458

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
63c88a5
perf: optimize nanvl in datafusion-functions
andygrove Jul 10, 2026
c99084e
test: add partially-null nanvl benchmarks and unit tests
andygrove Jul 10, 2026
d261479
Apply suggestion from @Dandandan
Dandandan Jul 11, 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
74 changes: 74 additions & 0 deletions datafusion/functions/benches/nanvl.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,80 @@ fn criterion_benchmark(c: &mut Criterion) {
bench.iter(|| black_box(nanvl_fn.invoke_with_args(args.clone()).unwrap()))
});
}

// Partially-null array benchmarks exercise the null-aware match arms that
// the fully-populated benchmarks above never reach: only-x-null,
// only-y-null, and both-null.
let bench_pair =
|c: &mut Criterion, name: &str, x: ArrayRef, y: ArrayRef, size: usize| {
c.bench_function(name, |bench| {
let args = ScalarFunctionArgs {
args: vec![
ColumnarValue::Array(Arc::clone(&x)),
ColumnarValue::Array(Arc::clone(&y)),
],
arg_fields: vec![
Field::new("a", DataType::Float64, true).into(),
Field::new("b", DataType::Float64, true).into(),
],
number_rows: size,
return_field: Field::new("f", DataType::Float64, true).into(),
config_options: Arc::clone(&config_options),
};
bench.iter(|| black_box(nanvl_fn.invoke_with_args(args.clone()).unwrap()))
});
};

for size in [1024, 4096, 8192] {
// `x` mixes non-NaN, NaN, and null so every code path is taken.
let x_nulls: ArrayRef = Arc::new(Float64Array::from(
(0..size)
.map(|i| match i % 3 {
0 => Some(1.0),
1 => Some(f64::NAN),
_ => None,
})
.collect::<Vec<_>>(),
));
// `x` without nulls, alternating non-NaN and NaN.
let x_full: ArrayRef = Arc::new(Float64Array::from(
(0..size)
.map(|i| if i % 2 == 0 { 1.0 } else { f64::NAN })
.collect::<Vec<_>>(),
));
// `y` with roughly a quarter nulls.
let y_nulls: ArrayRef = Arc::new(Float64Array::from(
(0..size)
.map(|i| if i % 4 == 3 { None } else { Some(2.0) })
.collect::<Vec<_>>(),
));
let y_full: ArrayRef = Arc::new(Float64Array::from(vec![2.0; size]));

// (Some, None): only `x` has nulls.
bench_pair(
c,
&format!("nanvl/array_f64_x_nulls/{size}"),
Arc::clone(&x_nulls),
Arc::clone(&y_full),
size,
);
// (None, Some): only `y` has nulls.
bench_pair(
c,
&format!("nanvl/array_f64_y_nulls/{size}"),
Arc::clone(&x_full),
Arc::clone(&y_nulls),
size,
);
// (Some, Some): both inputs have nulls.
bench_pair(
c,
&format!("nanvl/array_f64_both_nulls/{size}"),
Arc::clone(&x_nulls),
Arc::clone(&y_nulls),
size,
);
}
}

criterion_group!(benches, criterion_benchmark);
Expand Down
203 changes: 164 additions & 39 deletions datafusion/functions/src/math/nanvl.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,16 +17,20 @@

use std::sync::Arc;

use arrow::array::{ArrayRef, AsArray, Float16Array, Float32Array, Float64Array};
use arrow::array::builder::NullBufferBuilder;
use arrow::array::{Array, ArrayRef, AsArray, PrimitiveArray};
use arrow::datatypes::DataType::{Float16, Float32, Float64};
use arrow::datatypes::{DataType, Float16Type, Float32Type, Float64Type};
use arrow::datatypes::{
ArrowPrimitiveType, DataType, Float16Type, Float32Type, Float64Type,
};
use datafusion_common::types::{NativeType, logical_float64};
use datafusion_common::{Result, ScalarValue, exec_err, utils::take_function_args};
use datafusion_expr::{
Coercion, ColumnarValue, Documentation, ScalarFunctionArgs, ScalarUDFImpl, Signature,
TypeSignature, TypeSignatureClass, Volatility,
};
use datafusion_macros::user_doc;
use num_traits::Float;

#[user_doc(
doc_section(label = "Math Functions"),
Expand Down Expand Up @@ -148,46 +152,80 @@ fn scalar_is_nan(scalar: &ScalarValue) -> bool {
/// - otherwise -> output is x (which may itself be NULL)
fn nanvl(args: &[ArrayRef]) -> Result<ArrayRef> {
match args[0].data_type() {
Float64 => {
let x = args[0].as_primitive::<Float64Type>();
let y = args[1].as_primitive::<Float64Type>();
let result: Float64Array = x
.iter()
.zip(y.iter())
.map(|(x_value, y_value)| match x_value {
Some(x_value) if x_value.is_nan() => y_value,
_ => x_value,
})
.collect();
Ok(Arc::new(result) as ArrayRef)
}
Float32 => {
let x = args[0].as_primitive::<Float32Type>();
let y = args[1].as_primitive::<Float32Type>();
let result: Float32Array = x
Float64 => Ok(Arc::new(nanvl_impl::<Float64Type>(
args[0].as_primitive(),
args[1].as_primitive(),
))),
Float32 => Ok(Arc::new(nanvl_impl::<Float32Type>(
args[0].as_primitive(),
args[1].as_primitive(),
))),
Float16 => Ok(Arc::new(nanvl_impl::<Float16Type>(
args[0].as_primitive(),
args[1].as_primitive(),
))),
other => exec_err!("Unsupported data type {other:?} for function nanvl"),
}
}

/// Element-wise `nanvl`: selects `y[i]` where `x[i]` is `NaN`, otherwise `x[i]`
/// (a null `x` selects `x`, i.e. propagates null).
///
/// This produces output identical to collecting an iterator of `Option`s but
/// splits out a null-free fast path that iterates the raw value slices,
/// skipping per-element validity checks and `Option` handling. The null-aware
/// path builds its null buffer lazily via [`NullBufferBuilder`].
fn nanvl_impl<T>(x: &PrimitiveArray<T>, y: &PrimitiveArray<T>) -> PrimitiveArray<T>
where
T: ArrowPrimitiveType,
T::Native: Float,
{
let xv = x.values();
let yv = y.values();

match (x.nulls(), y.nulls()) {
// No nulls in either input means no nulls in the output, so we can
// iterate values directly and avoid the null bookkeeping entirely.
(None, None) => {
let values: Vec<T::Native> = xv
.iter()
.zip(y.iter())
.map(|(x_value, y_value)| match x_value {
Some(x_value) if x_value.is_nan() => y_value,
_ => x_value,
})
.zip(yv.iter())
.map(
|(&x_value, &y_value)| {
if x_value.is_nan() { y_value } else { x_value }
},
)
.collect();
Ok(Arc::new(result) as ArrayRef)
PrimitiveArray::<T>::new(values.into(), None)
}
Float16 => {
let x = args[0].as_primitive::<Float16Type>();
let y = args[1].as_primitive::<Float16Type>();
let result: Float16Array = x
.iter()
.zip(y.iter())
.map(|(x_value, y_value)| match x_value {
Some(x_value) if x_value.is_nan() => y_value,
_ => x_value,
})
.collect();
Ok(Arc::new(result) as ArrayRef)
_ => {
let len = x.len();
let mut nulls = NullBufferBuilder::new(len);
let mut values = Vec::with_capacity(len);
for i in 0..len {
// `y` is only consulted when `x` is a (non-null) NaN, matching
// the original short-circuiting match.

@Jefffrey Jefffrey Jul 11, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same here, no need to mention original short-circuiting match considering the code will be gone

if x.is_valid(i) {
let x_value = xv[i];
if x_value.is_nan() {
if y.is_valid(i) {
values.push(yv[i]);
nulls.append_non_null();
} else {
values.push(T::Native::default());
nulls.append_null();
}
} else {
values.push(x_value);
nulls.append_non_null();
}
} else {
values.push(T::Native::default());
nulls.append_null();
}
}
PrimitiveArray::<T>::new(values.into(), nulls.finish())
}
other => exec_err!("Unsupported data type {other:?} for function nanvl"),
}
}

Expand All @@ -197,7 +235,7 @@ mod test {

use crate::math::nanvl::nanvl;

use arrow::array::{ArrayRef, Float32Array, Float64Array};
use arrow::array::{Array, ArrayRef, Float32Array, Float64Array};
use datafusion_common::cast::{as_float32_array, as_float64_array};

#[test]
Expand Down Expand Up @@ -235,4 +273,91 @@ mod test {
assert_eq!(floats.value(2), 3.0);
assert!(floats.value(3).is_nan());
}

#[test]
fn test_nanvl_f64_with_nulls() {
// Covers the null-aware path and null propagation:
// - x null -> null (regardless of y)
// - x NaN, y non-null -> y
// - x NaN, y null -> null
// - x non-NaN -> x
let args: Vec<ArrayRef> = vec![
Arc::new(Float64Array::from(vec![
None,
Some(f64::NAN),
Some(f64::NAN),
Some(2.5),
])), // x
Arc::new(Float64Array::from(vec![
Some(9.0),
Some(6.0),
None,
Some(7.0),
])), // y
];

let result = nanvl(&args).expect("failed to initialize function nanvl");
let floats =
as_float64_array(&result).expect("failed to initialize function nanvl");

assert_eq!(floats.len(), 4);
assert!(floats.is_null(0));
assert_eq!(floats.value(1), 6.0);
assert!(floats.is_null(2));
assert_eq!(floats.value(3), 2.5);
}

#[test]
fn test_nanvl_f64_only_y_nulls() {
// `x` has no nulls, `y` does:
// - x non-NaN -> x
// - x NaN, y non-null -> y
// - x NaN, y null -> null (propagated from y)
let args: Vec<ArrayRef> = vec![
Arc::new(Float64Array::from(vec![1.0, f64::NAN, f64::NAN, 4.0])), // x
Arc::new(Float64Array::from(vec![
Some(5.0),
Some(6.0),
None,
Some(8.0),
])), // y
];

let result = nanvl(&args).expect("failed to initialize function nanvl");
let floats =
as_float64_array(&result).expect("failed to initialize function nanvl");

assert_eq!(floats.len(), 4);
assert_eq!(floats.value(0), 1.0);
assert_eq!(floats.value(1), 6.0);
assert!(floats.is_null(2));
assert_eq!(floats.value(3), 4.0);
}

#[test]
fn test_nanvl_f64_only_x_nulls() {
// `x` has nulls, `y` does not:
// - x null -> null (propagated from x)
// - x NaN -> y
// - x non-NaN -> x
let args: Vec<ArrayRef> = vec![
Arc::new(Float64Array::from(vec![
None,
Some(f64::NAN),
Some(3.0),
None,
])), // x
Arc::new(Float64Array::from(vec![5.0, 6.0, 7.0, 8.0])), // y
];

let result = nanvl(&args).expect("failed to initialize function nanvl");
let floats =
as_float64_array(&result).expect("failed to initialize function nanvl");

assert_eq!(floats.len(), 4);
assert!(floats.is_null(0));
assert_eq!(floats.value(1), 6.0);
assert_eq!(floats.value(2), 3.0);
assert!(floats.is_null(3));
}
}
Loading