d803bfe2b1
git-subtree-dir: vendor/ruvector git-subtree-split: b64c21726f2bb37286d9ee36a7869fef60cc6900
81 lines
2.5 KiB
Rust
81 lines
2.5 KiB
Rust
#![allow(clippy::needless_range_loop)]
|
|
#![allow(clippy::range_zip_with_len)]
|
|
|
|
use cpu_time::ProcessTime;
|
|
use rand::distr::Uniform;
|
|
use rand::prelude::*;
|
|
use std::time::{Duration, SystemTime};
|
|
|
|
use anndists::dist::*;
|
|
use hnsw_rs::prelude::*;
|
|
|
|
fn main() {
|
|
env_logger::Builder::from_default_env().init();
|
|
//
|
|
let nb_elem = 500000;
|
|
let dim = 25;
|
|
// generate nb_elem colmuns vectors of dimension dim
|
|
let mut rng = rand::rng();
|
|
let unif = rand::distr::StandardUniform;
|
|
let mut data = Vec::with_capacity(nb_elem);
|
|
for _ in 0..nb_elem {
|
|
let column = (0..dim).map(|_| rng.sample(unif)).collect::<Vec<f32>>();
|
|
data.push(column);
|
|
}
|
|
// give an id to each data
|
|
let data_with_id = data.iter().zip(0..data.len()).collect::<Vec<_>>();
|
|
|
|
let ef_c = 200;
|
|
let max_nb_connection = 15;
|
|
let nb_layer = 16.min((nb_elem as f32).ln().trunc() as usize);
|
|
let hns = Hnsw::<f32, DistL2>::new(max_nb_connection, nb_elem, nb_layer, ef_c, DistL2 {});
|
|
let mut start = ProcessTime::now();
|
|
let mut begin_t = SystemTime::now();
|
|
hns.parallel_insert(&data_with_id);
|
|
let mut cpu_time: Duration = start.elapsed();
|
|
println!(" hnsw data insertion cpu time {:?}", cpu_time);
|
|
println!(
|
|
" hnsw data insertion parallel, system time {:?} \n",
|
|
begin_t.elapsed().unwrap()
|
|
);
|
|
hns.dump_layer_info();
|
|
println!(
|
|
" parallel hnsw data nb point inserted {:?}",
|
|
hns.get_nb_point()
|
|
);
|
|
//
|
|
// serial insertion
|
|
//
|
|
let hns = Hnsw::<f32, DistL2>::new(max_nb_connection, nb_elem, nb_layer, ef_c, DistL2 {});
|
|
start = ProcessTime::now();
|
|
begin_t = SystemTime::now();
|
|
for _i in 0..data_with_id.len() {
|
|
hns.insert((data_with_id[_i].0.as_slice(), data_with_id[_i].1))
|
|
}
|
|
cpu_time = start.elapsed();
|
|
println!("\n\n serial hnsw data insertion {:?}", cpu_time);
|
|
println!(
|
|
" hnsw data insertion serial, system time {:?}",
|
|
begin_t.elapsed().unwrap()
|
|
);
|
|
hns.dump_layer_info();
|
|
println!(
|
|
" serial hnsw data nb point inserted {:?}",
|
|
hns.get_nb_point()
|
|
);
|
|
|
|
let ef_search = max_nb_connection * 2;
|
|
let knbn = 10;
|
|
//
|
|
for _iter in 0..100 {
|
|
let mut r_vec = Vec::<f32>::with_capacity(dim);
|
|
let mut rng = rand::rng();
|
|
let unif = Uniform::<f32>::new(0., 1.).unwrap();
|
|
for _ in 0..dim {
|
|
r_vec.push(rng.sample(unif));
|
|
}
|
|
//
|
|
let _neighbours = hns.search(&r_vec, knbn, ef_search);
|
|
}
|
|
}
|