Files
Arnaud Gourlay c196d2eb1a Benches: use SmallRng instead of ChaCha12-based generators (#9887)
* Benches: use SmallRng instead of ChaCha12-based generators

All benchmarks used StdRng or rand::rng() (ThreadRng), both backed by the
ChaCha12 block cipher in rand 0.10. Benchmarks do not need crypto-strength
randomness, and several draw random values inside the timed closure, so
cipher work was included in the measurement itself.

Switch every bench target to SmallRng (Xoshiro256++), and key the HNSW
graph cache and sparse index cache by RNG algorithm so stale caches built
from the old generator are not reused against newly generated vectors.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* Benches: replace free-function rand::random with local SmallRng

Addresses review: rand::random draws from the thread RNG (ChaCha12),
including inside the timed loop of the pq score benchmark.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-17 17:22:27 +02:00

67 lines
2.0 KiB
Rust

use std::sync::atomic::AtomicBool;
use common::counter::hardware_counter::HardwareCounterCell;
use criterion::{Criterion, criterion_group, criterion_main};
use quantization::encoded_storage::TestEncodedStorageBuilder;
use quantization::encoded_vectors::{DistanceType, EncodedVectors, VectorParameters};
use quantization::encoded_vectors_pq::{self, EncodedVectorsPQ};
use rand::RngExt;
use rand::rngs::SmallRng;
fn encode_bench(c: &mut Criterion) {
let mut group = c.benchmark_group("encode");
let vectors_count = 100_000;
let vector_dim = 1024;
let mut rng = rand::make_rng::<SmallRng>();
let mut list: Vec<f32> = Vec::new();
for _ in 0..vectors_count {
let vector: Vec<f32> = (0..vector_dim).map(|_| rng.random()).collect();
list.extend_from_slice(&vector);
}
let vector_parameters = VectorParameters {
dim: vector_dim,
deprecated_count: None,
distance_type: DistanceType::Dot,
invert: false,
};
let quantized_vector_size =
encoded_vectors_pq::get_quantized_vector_size(&vector_parameters, 2);
let pq_encoded = EncodedVectorsPQ::encode(
(0..vectors_count).map(|i| &list[i * vector_dim..(i + 1) * vector_dim]),
TestEncodedStorageBuilder::new(None, quantized_vector_size),
&vector_parameters,
vectors_count,
2,
2,
None,
&AtomicBool::new(false),
)
.unwrap();
let query: Vec<f32> = (0..vector_dim).map(|_| rng.random()).collect();
let encoded_query = pq_encoded.encode_query(&query);
let mut total = 0.0;
let hardware_counter = HardwareCounterCell::new();
group.bench_function("score random access pq", |b| {
b.iter(|| {
let random_idx = rng.random_range(0..vectors_count as u32);
total += pq_encoded.score_point(&encoded_query, random_idx, &hardware_counter);
});
});
println!("total: {total}");
}
criterion_group! {
name = benches;
config = Criterion::default().sample_size(10);
targets = encode_bench
}
criterion_main!(benches);