1//! Benchmark the overhead that the synchronization of `OnceCell::get` causes.
2//! We do some other operations that write to memory to get an imprecise but somewhat realistic
3//! measurement.
4
5use once_cell::sync::OnceCell;
6use std::sync::atomic::{AtomicUsize, Ordering};
7
8const N_THREADS: usize = 16;
9const N_ROUNDS: usize = 1_000_000;
10
11static CELL: OnceCell<usize> = OnceCell::new();
12static OTHER: AtomicUsize = AtomicUsize::new(0);
13
14fn main() {
15    let start = std::time::Instant::now();
16    let threads =
17        (0..N_THREADS).map(|i| std::thread::spawn(move || thread_main(i))).collect::<Vec<_>>();
18    for thread in threads {
19        thread.join().unwrap();
20    }
21    println!("{:?}", start.elapsed());
22    println!("{:?}", OTHER.load(Ordering::Relaxed));
23}
24
25#[inline(never)]
26fn thread_main(i: usize) {
27    // The operations we do here don't really matter, as long as we do multiple writes, and
28    // everything is messy enough to prevent the compiler from optimizing the loop away.
29    let mut data = [i; 128];
30    let mut accum = 0usize;
31    for _ in 0..N_ROUNDS {
32        let _value = CELL.get_or_init(|| i + 1);
33        let k = OTHER.fetch_add(data[accum & 0x7F] as usize, Ordering::Relaxed);
34        for j in data.iter_mut() {
35            *j = (*j).wrapping_add(accum);
36            accum = accum.wrapping_add(k);
37        }
38    }
39}
40