chore: bench additional math function

native/spark-expr/Cargo.toml

@@ -239,10 +239,18 @@ harness = false
 name = "abs"
 harness = false
 
+[[bench]]
+name = "modulo"
+harness = false
+
 [[bench]]
 name = "levenshtein"
 harness = false
 
+[[bench]]
+name = "negative"
+harness = false
+
 [[bench]]
 name = "split"
 harness = false

native/spark-expr/benches/modulo.rs

@@ -0,0 +1,51 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
+use datafusion::physical_plan::ColumnarValue;
+use datafusion_comet_spark_expr::spark_modulo;
+use std::hint::black_box;
+use std::sync::Arc;
+
+#[path = "common/mod.rs"]
+mod common;
+use common::{i64_array, NULL_RATIOS, ROW_COUNTS};
+
+fn criterion_benchmark(c: &mut Criterion) {
+    let mut group = c.benchmark_group("spark_modulo");
+    for rows in ROW_COUNTS {
+        // Divisor fully populated and non-zero so the benchmark measures the modulo, not the
+        // divide-by-zero null path.
+        let divisor = i64_array(rows, 0.0, |i| (i as i64 % 7) + 1);
+        for (null_ratio, tag) in NULL_RATIOS {
+            let dividend = i64_array(rows, null_ratio, |i| i as i64 % 1000);
+            let args = vec![
+                ColumnarValue::Array(dividend),
+                ColumnarValue::Array(Arc::clone(&divisor)),
+            ];
+            group.bench_with_input(
+                BenchmarkId::from_parameter(format!("{rows}/{tag}")),
+                &args,
+                |b, args| b.iter(|| black_box(spark_modulo(black_box(args), false).unwrap())),
+            );
+        }
+    }
+    group.finish();
+}
+
+criterion_group!(benches, criterion_benchmark);
+criterion_main!(benches);

native/spark-expr/benches/negative.rs

@@ -0,0 +1,53 @@
+// Licensed to the Apache Software Foundation (ASF) under one
+// or more contributor license agreements.  See the NOTICE file
+// distributed with this work for additional information
+// regarding copyright ownership.  The ASF licenses this file
+// to you under the Apache License, Version 2.0 (the
+// "License"); you may not use this file except in compliance
+// with the License.  You may obtain a copy of the License at
+//
+//   http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing,
+// software distributed under the License is distributed on an
+// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+// KIND, either express or implied.  See the License for the
+// specific language governing permissions and limitations
+// under the License.
+
+use arrow::array::RecordBatch;
+use arrow::datatypes::{DataType, Field, Schema};
+use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
+use datafusion::physical_expr::expressions::Column;
+use datafusion_comet_spark_expr::create_negate_expr;
+use std::hint::black_box;
+use std::sync::Arc;
+
+#[path = "common/mod.rs"]
+mod common;
+use common::{i64_array, NULL_RATIOS, ROW_COUNTS};
+
+fn criterion_benchmark(c: &mut Criterion) {
+    let schema = Arc::new(Schema::new(vec![Field::new("a", DataType::Int64, true)]));
+    let expr = create_negate_expr(Arc::new(Column::new("a", 0)), false).unwrap();
+
+    let mut group = c.benchmark_group("negative");
+    for rows in ROW_COUNTS {
+        for (null_ratio, tag) in NULL_RATIOS {
+            let batch = RecordBatch::try_new(
+                Arc::clone(&schema),
+                vec![i64_array(rows, null_ratio, |i| i as i64 % 1000)],
+            )
+            .unwrap();
+            group.bench_with_input(
+                BenchmarkId::from_parameter(format!("{rows}/{tag}")),
+                &batch,
+                |b, batch| b.iter(|| black_box(expr.evaluate(black_box(batch)).unwrap())),
+            );
+        }
+    }
+    group.finish();
+}
+
+criterion_group!(benches, criterion_benchmark);
+criterion_main!(benches);

native/spark-expr/src/lib.rs

@@ -86,9 +86,9 @@ pub use json_funcs::{FromJson, ToJson};
 pub use math_funcs::{
     abs, checked_add, checked_div, checked_mul, checked_sub, create_modulo_expr,
     create_negate_expr, spark_ceil, spark_decimal_div, spark_decimal_integral_div, spark_floor,
-    spark_log, spark_make_decimal, spark_pow, spark_round, spark_unhex, spark_unscaled_value,
-    CheckOverflow, DecimalRescaleCheckOverflow, NegativeExpr, NormalizeNaNAndZero,
-    WideDecimalBinaryExpr, WideDecimalOp,
+    spark_log, spark_make_decimal, spark_modulo, spark_pow, spark_round, spark_unhex,
+    spark_unscaled_value, CheckOverflow, DecimalRescaleCheckOverflow, NegativeExpr,
+    NormalizeNaNAndZero, WideDecimalBinaryExpr, WideDecimalOp,
 };
 pub use query_context::{create_query_context_map, QueryContext, QueryContextMap};
 pub use string_funcs::*;

native/spark-expr/src/math_funcs/mod.rs

@@ -38,7 +38,7 @@ pub use div::spark_decimal_integral_div;
 pub use floor::spark_floor;
 pub use internal::*;
 pub use log::spark_log;
-pub use modulo_expr::create_modulo_expr;
+pub use modulo_expr::{create_modulo_expr, spark_modulo};
 pub use negative::{create_negate_expr, NegativeExpr};
 pub use pow::spark_pow;
 pub use round::spark_round;