イントロソートを使用する

イントロソート (introspective sort) は、クイックソートを主役にし、再帰が深くなりすぎた区間をヒープソートに切り替え、十分に短い部分配列は挿入ソートで仕上げる。

クイックソート単体は入力次第でピボット選びが偏り、再帰深度が O(n) に達して最悪計算量 O(n²) になり得る。

そこでイントロソートは許容する再帰の深さに上限(多くの実装で 2·⌊log₂ n⌋ 前後)を設け、それを超えそうな区間だけヒープソートにフォールバックする。比較ソートとしての下界 Ω(n log n) に張り付いたまま、最悪ケースを回避できる。

  1. クイックソート: 通常どおり分割と再帰を行う。
  2. 深さの監視: 再帰の残り許容深度が 0 になった区間は、クイックソートを続けずヒープソートで処理する。
  3. 小区間の挿入: 要素数が閾値以下の部分配列は挿入ソートで済ませる(再帰オーバーヘッドとマージコストを抑える)。
procedure introsort(A, lo, hi, depth_limit)
  if hi - lo <= INSERTION_THRESHOLD then
    insertion_sort(A, lo, hi)
    return
  if depth_limit = 0 then
    heapsort(A, lo, hi)
    return
  p = partition(A, lo, hi)
  introsort(A, lo, p - 1, depth_limit - 1)
  introsort(A, p + 1, hi, depth_limit - 1)

procedure sort(A)
  introsort(A, 0, length(A) - 1, max(2 * floor(log2(length(A))), 1))

この切り替えにより最悪計算量は O(n log n) に保たれるが、ピボット型の分割や挿入ソートの交換が相対順序を変えうるため、一般に不安定である。

類似アルゴリズムとの相違点

ロムート分割型クイックソートに深さ監視とヒープソートへの切り替え、挿入ソートによる小区間仕上げを加えたものである。

クイックソート単体の最悪計算量 O(n²) を避けつつ、平均性能を維持しようとする設計である。

計算時間量および空間計算量を計測する

Size Average time Maximum time Average memory Maximum memory
256 0.000005 0.000103 57 64
512 0.000011 0.000056 58 64
1024 0.000023 0.000092 61 68
2048 0.000050 0.000234 58 64
4096 0.000108 0.000173 62 68
8192 0.000235 0.000417 70 76
16384 0.000508 0.000648 62 68
32768 0.001091 0.002530 62 68
65536 0.002335 0.003743 66 72
131072 0.004966 0.010070 62 68
262144 0.010490 0.021564 78 84
計測に使用したコードを表示する

set -euo pipefail

WORKDIR="$(mktemp -d)"
trap 'rm -rf "$WORKDIR"' EXIT

cat > "$WORKDIR/Dockerfile" <<'EOF'
FROM rust:1.95.0

WORKDIR /app

RUN mkdir -p src

RUN cat > Cargo.toml <<'CARGO'
[package]
name = "rust-benchmark"
version = "0.1.0"
edition = "2021"

[profile.release]
lto = true
codegen-units = 1
panic = "abort"
CARGO

RUN cat > src/main.rs <<'RUST'
use std::{
    env,
    process::Command,
    time::{Duration, Instant},
};
const MIN_POWER: u32 = 8;
const MAX_POWER: u32 = 18;
const RUNS: usize = 8192;
fn insertion_sort(a: &mut [usize]) {
    for i in 1..a.len() {
        let mut j = i;
        while j > 0 && a[j - 1] > a[j] {
            a.swap(j - 1, j);
            j -= 1;
        }
    }
}

fn partition_at(a: &mut [usize], lo: usize, hi: usize, pivot_idx: usize) -> usize {
    a.swap(pivot_idx, hi);
    let pivot = a[hi];
    let mut i = lo;
    for j in lo..hi {
        if a[j] < pivot {
            a.swap(i, j);
            i += 1;
        }
    }
    a.swap(i, hi);
    i
}

fn partition(a: &mut [usize], lo: usize, hi: usize) -> usize {
    partition_at(a, lo, hi, lo + (hi - lo) / 2)
}

fn sift_down(a: &mut [usize], mut root: usize, end: usize) {
    loop {
        let child = root * 2 + 1;
        if child > end {
            break;
        }
        let mut swap_idx = child;
        if child < end && a[child] < a[child + 1] {
            swap_idx = child + 1;
        }
        if a[root] >= a[swap_idx] {
            break;
        }
        a.swap(root, swap_idx);
        root = swap_idx;
    }
}

fn heap_sort(a: &mut [usize]) {
    if a.len() <= 1 {
        return;
    }
    for start in (0..a.len() / 2).rev() {
        sift_down(a, start, a.len() - 1);
    }
    for end in (1..a.len()).rev() {
        a.swap(0, end);
        sift_down(a, 0, end - 1);
    }
}



fn intro_sort_range(a: &mut [usize], lo: usize, hi: usize, depth: usize) {
    if hi <= lo {
        return;
    }
    if hi - lo < 16 {
        insertion_sort(&mut a[lo..=hi]);
        return;
    }
    if depth == 0 {
        heap_sort(&mut a[lo..=hi]);
        return;
    }
    let p = partition(a, lo, hi);
    if p > 0 {
        intro_sort_range(a, lo, p - 1, depth - 1);
    }
    intro_sort_range(a, p + 1, hi, depth - 1);
}

fn intro_sort(a: &mut [usize]) {
    if let Some(hi) = a.len().checked_sub(1) {
        let depth = usize::BITS as usize - a.len().leading_zeros() as usize;
        intro_sort_range(a, 0, hi, depth * 2);
    }
}


fn benchmark_sort(array: &mut [usize]) {

    intro_sort(array);

}

fn is_non_decreasing(a: &[usize]) -> bool {
    a.windows(2).all(|w| w[0] <= w[1])
}

fn same_multiset(a: &[usize], b: &[usize]) -> bool {
    if a.len() != b.len() {
        return false;
    }

    let mut left = a.to_vec();
    let mut right = b.to_vec();
    left.sort_unstable();
    right.sort_unstable();
    left == right
}

fn check_correctness_case(label: &str, mut input: Vec<usize>) {
    let original = input.clone();

    benchmark_sort(&mut input);

    if !is_non_decreasing(&input) {
        panic!("correctness case {}: output is not sorted", label);
    }

    if !same_multiset(&input, &original) {
        panic!("correctness case {}: elements were lost or added", label);
    }
}

fn few_unique_values(size: usize, unique: usize, seed: u64) -> Vec<usize> {
    let mut state = seed;

    (0..size)
        .map(|_| {
            state ^= state << 13;
            state ^= state >> 7;
            state ^= state << 17;
            (state as usize % unique) + 1
        })
        .collect()
}

fn run_correctness_checks() {
    check_correctness_case("empty", vec![]);
    check_correctness_case("single", vec![42]);
    check_correctness_case("duplicates", vec![3, 1, 3, 2, 1, 2]);
    check_correctness_case("sorted", vec![1, 2, 3, 4, 5]);
    check_correctness_case("reverse", vec![5, 4, 3, 2, 1]);
    check_correctness_case("all_equal", vec![7, 7, 7, 7]);
    check_correctness_case("skewed_range", vec![1_000_000, 2, 1_000_001, 1, 999_999]);
    // Static-buffer Grail skips the in-buffer build when key collection is sparse
    // (ideal_buffer = false). Exercising that path catches regressions in buffer gating.
    check_correctness_case(
        "few_keys_len16",
        vec![2, 2, 2, 2, 2, 2, 2, 2, 4, 3, 1, 2, 3, 4, 1, 4],
    );
    // Seed 0 is a fixed point of the xorshift below, so it would degenerate into
    // yet another all-equal case instead of a 4-value mix. Start at 1.
    for seed in 1..=32 {
        check_correctness_case(
            &format!("few_keys_len32_seed_{seed}"),
            few_unique_values(32, 4, seed),
        );
    }
}


fn shuffled(size: usize, seed: u64) -> Vec<usize> {
    let mut v: Vec<usize> = (1..=size).collect();

    let mut state = seed;

    for i in (1..size).rev() {
        state ^= state << 13;
        state ^= state >> 7;
        state ^= state << 17;

        let j = (state as usize) % (i + 1);

        v.swap(i, j);
    }

    v
}

fn memory_usage_kb() -> usize {
    // VmHWM (peak RSS, KiB). Reported memory subtracts a per-size baseline that only
    // holds the input array, so the table reflects auxiliary space during sorting.
    let contents = std::fs::read_to_string("/proc/self/status")
        .unwrap_or_default();

    for line in contents.lines() {
        if let Some(rest) = line.strip_prefix("VmHWM:") {
            let kb = rest
                .split_whitespace()
                .next()
                .unwrap_or("0")
                .parse::<usize>()
                .unwrap_or(0);

            return kb;
        }
    }

    0
}

fn micros(d: Duration) -> u128 {
    d.as_micros()
}

fn input_array(size: usize, seed: u64) -> Vec<usize> {
    shuffled(size, seed)
}

fn run_baseline(size: usize) -> usize {
    let _hold = input_array(size, 1);
    memory_usage_kb()
}

fn run_once(size: usize, seed: usize) -> (u128, usize) {
    let mut array = input_array(size, seed as u64);

    let start = Instant::now();

    benchmark_sort(&mut array);

    let elapsed = start.elapsed();
    let mem = memory_usage_kb();

    let expected: Vec<usize> = (1..=size).collect();
    if array != expected {
        panic!(
            "sort failed with seed {} for size {}",
            seed,
            size
        );
    }

    (micros(elapsed), mem)
}

fn run_baseline_child(args: &[String]) {
    let size = args[2].parse::<usize>().expect("invalid size");
    let mem = run_baseline(size);
    println!("{}", mem);
}

fn run_child(args: &[String]) {
    let size = args[2].parse::<usize>().expect("invalid size");
    let seed = args[3].parse::<usize>().expect("invalid seed");
    let (elapsed_us, mem) = run_once(size, seed);
    println!("{} {}", elapsed_us, mem);
}

fn main() {
    let args: Vec<String> = env::args().collect();
    if args.get(1).is_some_and(|arg| arg == "--baseline-once") {
        run_baseline_child(&args);
        return;
    }
    if args.get(1).is_some_and(|arg| arg == "--run-once") {
        run_child(&args);
        return;
    }

    run_correctness_checks();

    println!(
        "| {:>10} | {:>15} | {:>15} | {:>15} | {:>15} |",
        "Size",
        "Average time",
        "Maximum time",
        "Average memory",
        "Maximum memory"
    );

    println!(
        "|{:-<11}:|{:-<16}:|{:-<16}:|{:-<16}:|{:-<16}:|",
        "",
        "",
        "",
        "",
        ""
    );

    for power in MIN_POWER..=MAX_POWER {
        let size = 1usize << power;

        let baseline_output = Command::new(env::current_exe().expect("failed to find current executable"))
            .arg("--baseline-once")
            .arg(size.to_string())
            .output()
            .expect("failed to run benchmark baseline process");

        if !baseline_output.status.success() {
            panic!(
                "benchmark baseline process failed: {}",
                String::from_utf8_lossy(&baseline_output.stderr)
            );
        }

        let baseline_stdout = String::from_utf8(baseline_output.stdout)
            .expect("baseline process returned non-UTF-8 output");
        let baseline_mem = baseline_stdout
            .split_whitespace()
            .next()
            .expect("missing baseline memory usage")
            .parse::<usize>()
            .expect("invalid baseline memory usage");

        let mut total_time: u128 = 0;
        let mut max_time: u128 = 0;

        let mut total_mem: usize = 0;
        let mut max_mem: usize = 0;

        for seed in 1..=RUNS {
            let output = Command::new(env::current_exe().expect("failed to find current executable"))
                .arg("--run-once")
                .arg(size.to_string())
                .arg(seed.to_string())
                .output()
                .expect("failed to run benchmark child process");

            if !output.status.success() {
                panic!(
                    "benchmark child process failed: {}",
                    String::from_utf8_lossy(&output.stderr)
                );
            }

            let stdout = String::from_utf8(output.stdout)
                .expect("child process returned non-UTF-8 output");
            let mut fields = stdout.split_whitespace();
            let elapsed_us = fields
                .next()
                .expect("missing elapsed time")
                .parse::<u128>()
                .expect("invalid elapsed time");
            let mem = fields
                .next()
                .expect("missing memory usage")
                .parse::<usize>()
                .expect("invalid memory usage");

            total_time += elapsed_us;

            if elapsed_us > max_time {
                max_time = elapsed_us;
            }

            let aux_mem = mem.saturating_sub(baseline_mem);

            total_mem += aux_mem;

            if aux_mem > max_mem {
                max_mem = aux_mem;
            }
        }

        let avg_time = total_time / RUNS as u128;
        let avg_mem = total_mem / RUNS;

        println!(
            "| {:>10} | {:>15} | {:>15} | {:>15} | {:>15} |",
            size,
            format!("{}.{:06}", avg_time / 1_000_000, avg_time % 1_000_000),
            format!("{}.{:06}", max_time / 1_000_000, max_time % 1_000_000),
            avg_mem,
            max_mem
        );
    }
}
RUST

RUN cargo build --release

CMD ["./target/release/rust-benchmark"]
EOF

docker build -t rust-benchmark "$WORKDIR"
docker run --rm --init rust-benchmark