Skip to content

Remove uneeded binary_op benchmarks #15632

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 1 commit into from
Apr 9, 2025
Merged

Remove uneeded binary_op benchmarks #15632

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
80 changes: 4 additions & 76 deletions datafusion/physical-expr/benches/binary_op.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,6 @@

use arrow::{
array::BooleanArray,
compute::{bool_and, bool_or},
datatypes::{DataType, Field, Schema},
};
use arrow::{array::StringArray, record_batch::RecordBatch};
Expand All @@ -28,7 +27,7 @@ use datafusion_physical_expr::{
planner::logical2physical,
PhysicalExpr,
};
use std::sync::{Arc, LazyLock};
use std::sync::Arc;

/// Generates BooleanArrays with different true/false distributions for benchmarking.
///
Expand Down Expand Up @@ -130,75 +129,6 @@ fn generate_boolean_cases<const TEST_ALL_FALSE: bool>(
cases
}

/// Benchmarks boolean operations `false_count/bool_or` and `true_count/bool_and` on [`BooleanArray`]
/// You can run this benchmark with:
/// ```sh
/// # test true_count/false_count
/// TEST_BOOL_COUNT=1 cargo bench --bench binary_op -- boolean_ops
/// # test bool_or/bool_and
/// cargo bench --bench binary_op -- boolean_ops
/// ```
fn benchmark_boolean_ops(c: &mut Criterion) {
let len = 1_000_000; // Use one million elements for clear performance differentiation
static TEST_BOOL_COUNT: LazyLock<bool> =
LazyLock::new(|| match std::env::var("TEST_BOOL_COUNT") {
Ok(_) => {
println!("TEST_BOOL_COUNT=ON");
true
}
Err(_) => {
println!("TEST_BOOL_COUNT=OFF");
false
}
});

// Determine the test function to be executed based on the ENV `TEST_BOOL_COUNT`
fn test_func<const TEST_ALL_FALSE: bool>(array: &BooleanArray) -> bool {
// Use false_count for all false and true_count for all true
if *TEST_BOOL_COUNT {
if TEST_ALL_FALSE {
array.false_count() == array.len()
} else {
array.true_count() == array.len()
}
}
// Use bool_or for all false and bool_and for all true
else if TEST_ALL_FALSE {
match bool_or(array) {
Some(v) => !v,
None => false,
}
} else {
bool_and(array).unwrap_or(false)
Copy link
Contributor Author

@alamb alamb Apr 8, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

these are benchmarks for arrow functions bool_and and false_count / true_count so I don't think we need them in DataFusion

}
}

// Test cases for false_count and bool_or
{
let test_cases = generate_boolean_cases::<true>(len);
for (scenario, array) in test_cases {
let arr_ref = Arc::new(array);

// Benchmark test_func across different scenarios
c.bench_function(&format!("boolean_ops/or/{}", scenario), |b| {
b.iter(|| test_func::<true>(black_box(&arr_ref)))
});
}
}
// Test cases for true_count and bool_and
{
let test_cases = generate_boolean_cases::<false>(len);
for (scenario, array) in test_cases {
let arr_ref = Arc::new(array);

// Benchmark test_func across different scenarios
c.bench_function(&format!("boolean_ops/and/{}", scenario), |b| {
b.iter(|| test_func::<false>(black_box(&arr_ref)))
});
}
}
}

/// Benchmarks AND/OR operator short-circuiting by evaluating complex regex conditions.
///
/// Creates 6 test scenarios per operator:
Expand Down Expand Up @@ -257,12 +187,14 @@ fn benchmark_binary_op_in_short_circuit(c: &mut Criterion) {
);

// Create physical binary expressions
// a AND ((b ~ regex) AND (c ~ regex))
let expr_and = BinaryExpr::new(
Arc::new(Column::new("a", 0)),
Operator::And,
logical2physical(&right_condition_and, &schema),
);

// a OR ((b ~ regex) OR (c ~ regex))
let expr_or = BinaryExpr::new(
Arc::new(Column::new("a", 0)),
Operator::Or,
Expand Down Expand Up @@ -364,10 +296,6 @@ fn create_record_batch<const TEST_ALL_FALSE: bool>(
Ok(rbs)
}

criterion_group!(
benches,
benchmark_boolean_ops,
benchmark_binary_op_in_short_circuit
);
criterion_group!(benches, benchmark_binary_op_in_short_circuit);

criterion_main!(benches);