Skip to content

use criterion.rs for word benchmarks #113

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
Jan 30, 2023
Merged

use criterion.rs for word benchmarks #113

Show file tree
Hide file tree
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
55 changes: 26 additions & 29 deletions benches/unicode_words.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,55 +1,52 @@
#[macro_use]
extern crate bencher;
extern crate unicode_segmentation;
use criterion::{black_box, criterion_group, criterion_main, Criterion};

use bencher::Bencher;
use std::fs;
use unicode_segmentation::UnicodeSegmentation;

fn unicode_words(bench: &mut Bencher, path: &str) {
fn unicode_words(c: &mut Criterion, lang: &str, path: &str) {
let text = fs::read_to_string(path).unwrap();
bench.iter(|| {
for w in text.unicode_words() {
bencher::black_box(w);
}
c.bench_function(&format!("unicode_words_{}", lang), |bench| {
bench.iter(|| {
for w in text.unicode_words() {
black_box(w);
}
})
});

bench.bytes = text.len() as u64;
}

fn unicode_words_arabic(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/arabic.txt");
fn unicode_words_arabic(c: &mut Criterion) {
unicode_words(c, "arabic", "benches/texts/arabic.txt");
}

fn unicode_words_english(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/english.txt");
fn unicode_words_english(c: &mut Criterion) {
unicode_words(c, "english", "benches/texts/english.txt");
}

fn unicode_words_hindi(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/hindi.txt");
fn unicode_words_hindi(c: &mut Criterion) {
unicode_words(c, "hindi", "benches/texts/hindi.txt");
}

fn unicode_words_japanese(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/japanese.txt");
fn unicode_words_japanese(c: &mut Criterion) {
unicode_words(c, "japanese", "benches/texts/japanese.txt");
}

fn unicode_words_korean(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/korean.txt");
fn unicode_words_korean(c: &mut Criterion) {
unicode_words(c, "korean", "benches/texts/korean.txt");
}

fn unicode_words_mandarin(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/mandarin.txt");
fn unicode_words_mandarin(c: &mut Criterion) {
unicode_words(c, "mandarin", "benches/texts/mandarin.txt");
}

fn unicode_words_russian(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/russian.txt");
fn unicode_words_russian(c: &mut Criterion) {
unicode_words(c, "russian", "benches/texts/russian.txt");
}

fn unicode_words_source_code(bench: &mut Bencher) {
unicode_words(bench, "benches/texts/source_code.txt");
fn unicode_words_source_code(c: &mut Criterion) {
unicode_words(c, "source_code", "benches/texts/source_code.txt");
}

benchmark_group!(
criterion_group!(
benches,
unicode_words_arabic,
unicode_words_english,
Expand All @@ -61,4 +58,4 @@ benchmark_group!(
unicode_words_source_code,
);

benchmark_main!(benches);
criterion_main!(benches);
55 changes: 26 additions & 29 deletions benches/word_bounds.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,55 +1,52 @@
#[macro_use]
extern crate bencher;
extern crate unicode_segmentation;
use criterion::{black_box, criterion_group, criterion_main, Criterion};

use bencher::Bencher;
use std::fs;
use unicode_segmentation::UnicodeSegmentation;

fn word_bounds(bench: &mut Bencher, path: &str) {
fn word_bounds(c: &mut Criterion, lang: &str, path: &str) {
let text = fs::read_to_string(path).unwrap();
bench.iter(|| {
for w in text.split_word_bounds() {
bencher::black_box(w);
}
c.bench_function(&format!("word_bounds_{}", lang), |bench| {
bench.iter(|| {
for w in text.split_word_bounds() {
black_box(w);
}
});
});

bench.bytes = text.len() as u64;
}

fn word_bounds_arabic(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/arabic.txt");
fn word_bounds_arabic(c: &mut Criterion) {
word_bounds(c, "arabic", "benches/texts/arabic.txt");
}

fn word_bounds_english(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/english.txt");
fn word_bounds_english(c: &mut Criterion) {
word_bounds(c, "english", "benches/texts/english.txt");
}

fn word_bounds_hindi(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/hindi.txt");
fn word_bounds_hindi(c: &mut Criterion) {
word_bounds(c, "hindi", "benches/texts/hindi.txt");
}

fn word_bounds_japanese(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/japanese.txt");
fn word_bounds_japanese(c: &mut Criterion) {
word_bounds(c, "japanese", "benches/texts/japanese.txt");
}

fn word_bounds_korean(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/korean.txt");
fn word_bounds_korean(c: &mut Criterion) {
word_bounds(c, "korean", "benches/texts/korean.txt");
}

fn word_bounds_mandarin(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/mandarin.txt");
fn word_bounds_mandarin(c: &mut Criterion) {
word_bounds(c, "mandarin", "benches/texts/mandarin.txt");
}

fn word_bounds_russian(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/russian.txt");
fn word_bounds_russian(c: &mut Criterion) {
word_bounds(c, "russian", "benches/texts/russian.txt");
}

fn word_bounds_source_code(bench: &mut Bencher) {
word_bounds(bench, "benches/texts/source_code.txt");
fn word_bounds_source_code(c: &mut Criterion) {
word_bounds(c, "source_code", "benches/texts/source_code.txt");
}

benchmark_group!(
criterion_group!(
benches,
word_bounds_arabic,
word_bounds_english,
Expand All @@ -61,4 +58,4 @@ benchmark_group!(
word_bounds_source_code,
);

benchmark_main!(benches);
criterion_main!(benches);