1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
// 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 std::hint::black_box;
use std::sync::Arc;
use arrow::array::{ArrayRef, Int64Array};
use arrow::datatypes::{DataType, Field};
use arrow::util::bench_util::{
create_string_array_with_len, create_string_view_array_with_len,
};
use criterion::{BenchmarkId, Criterion, criterion_group, criterion_main};
use datafusion_common::config::ConfigOptions;
use datafusion_expr::{ColumnarValue, ScalarFunctionArgs};
use datafusion_functions::unicode::{left, right};
fn create_args(
size: usize,
str_len: usize,
use_negative: bool,
is_string_view: bool,
) -> Vec<ColumnarValue> {
let string_arg = if is_string_view {
ColumnarValue::Array(Arc::new(create_string_view_array_with_len(
size, 0.1, str_len, true,
)))
} else {
ColumnarValue::Array(Arc::new(create_string_array_with_len::<i32>(
size, 0.1, str_len,
)))
};
// For negative n, we want to trigger the double-iteration code path
let n_values: Vec<i64> = if use_negative {
(0..size).map(|i| -((i % 10 + 1) as i64)).collect()
} else {
(0..size).map(|i| (i % 10 + 1) as i64).collect()
};
let n_array = Arc::new(Int64Array::from(n_values));
vec![
string_arg,
ColumnarValue::Array(Arc::clone(&n_array) as ArrayRef),
]
}
fn criterion_benchmark(c: &mut Criterion) {
let left_function = left();
let right_function = right();
for function in [left_function, right_function] {
for is_string_view in [false, true] {
for is_negative in [false, true] {
for size in [1024, 4096] {
let function_name = function.name();
let mut group =
c.benchmark_group(format!("{function_name} size={size}"));
let bench_name = format!(
"{} {} n",
if is_string_view {
"string_view_array"
} else {
"string_array"
},
if is_negative { "negative" } else { "positive" },
);
let return_type = if is_string_view {
DataType::Utf8View
} else {
DataType::Utf8
};
let args = create_args(size, 32, is_negative, is_string_view);
group.bench_function(BenchmarkId::new(bench_name, size), |b| {
let arg_fields = args
.iter()
.enumerate()
.map(|(idx, arg)| {
Field::new(format!("arg_{idx}"), arg.data_type(), true)
.into()
})
.collect::<Vec<_>>();
let config_options = Arc::new(ConfigOptions::default());
b.iter(|| {
black_box(
function
.invoke_with_args(ScalarFunctionArgs {
args: args.clone(),
arg_fields: arg_fields.clone(),
number_rows: size,
return_field: Field::new(
"f",
return_type.clone(),
true,
)
.into(),
config_options: Arc::clone(&config_options),
})
.expect("should work"),
)
})
});
group.finish();
}
}
}
}
}
criterion_group!(benches, criterion_benchmark);
criterion_main!(benches);