アンシャッフルソートを使用する

アンシャッフルソート (unshuffle sort) は、入力を両端キュー(パイル)へ載せ、載せられなければ新しいパイルを増やし、最後にパイルをマージして昇順にする。

整列済みの山札を切って混ぜ直した状態を「元に戻す」イメージから名付けられた。整列済みに近い入力や、すでに単調な部分列が多いデータで効率が出やすい。

  1. 分布フェーズ: 入力を左から走査し、各値 x について既存のパイル(両端にだけ追加できる整列済み両端キュー)を左から試す。先頭要素 h に対し x <= h なら先頭へ、末尾要素 t に対し x >= t なら末尾へ載せる。どのパイルにも載せられなければ右端に新しいパイルを増やす。
  2. マージフェーズ: 分布でできた複数のパイルを理想マージと呼ばれる逐次マージで 1 本の昇順列へ統合する。各パイル内部は先頭から末尾へ非減少に保たれる。
procedure unshuffle_distribute(elements)
  piles = sequence of piles, initially empty deques
  for each x in elements then
    placed = false
    for each pile p in piles left to right then
      if x <= front(p) then
        push_front x onto p
        placed = true
        break
      else if x >= back(p) then
        push_back x onto p
        placed = true
        break
    if not placed then
      piles.append(deque containing only x)

procedure unshuffle_merge(piles)
  result = contents of piles[0]
  for i from 1 to length(piles) - 1 then
    result = merge_sorted(result, contents of piles[i])
  return result

要素の交換や中間挿入を避け、リンクの付け替えで済むため、もともとは単方向連結リスト向けに設計された。配列上では各パイルを両端キューとして模倣する実装が一般的である。

整列済みや逆順に近い入力では O(n) に近づく。大小が交互の並びでは最悪計算量 O(n²) となる。

理想マージにより逐次二分マージを最適化するが、各パイルが内部で昇順であるため、デモでは各パイル先頭の最小を繰り返し取る k 入力のマージでも同じ結果が得られる。

類似アルゴリズムとの相違点

ペイシェンスソートもパイルへ載せるが、両端キューに先頭・末尾へ載せられる点と、理想マージによる統合が異なる。載せる条件も山の一番上だけに厳密に大きい値、というルールが違う。

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 0.000011 0.000063 4 4
512 0.000021 0.000084 8 9
1024 0.000045 0.000132 17 17
2048 0.000102 0.000304 33 35
4096 0.000254 0.000497 67 67
8192 0.000740 0.009651 131 134
16384 0.002417 0.006928 262 262
32768 0.006924 0.010129 518 524
65536 0.020339 0.066586 1036 1036
131072 0.057926 0.081842 2060 2072
262144 0.166731 0.855630 4120 4120
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::{
    alloc::{GlobalAlloc, Layout, System},
    env,
    process::Command,
    sync::atomic::{AtomicUsize, Ordering},
    time::{Duration, Instant},
};

/// Counts live heap bytes and the high-water mark so auxiliary sort buffers
/// (swap Vecs, etc.) are measured as explicit heap growth during the sort.
struct TrackingAllocator;

static LIVE_BYTES: AtomicUsize = AtomicUsize::new(0);
static PEAK_BYTES: AtomicUsize = AtomicUsize::new(0);

fn record_alloc(size: usize) {
    let live = LIVE_BYTES.fetch_add(size, Ordering::Relaxed) + size;
    PEAK_BYTES.fetch_max(live, Ordering::Relaxed);
}

unsafe impl GlobalAlloc for TrackingAllocator {
    unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
        let ptr = System.alloc(layout);
        if !ptr.is_null() {
            record_alloc(layout.size());
        }
        ptr
    }

    unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
        LIVE_BYTES.fetch_sub(layout.size(), Ordering::Relaxed);
        System.dealloc(ptr, layout);
    }

    unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
        let ptr = System.alloc_zeroed(layout);
        if !ptr.is_null() {
            record_alloc(layout.size());
        }
        ptr
    }

    unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
        let new_ptr = System.realloc(ptr, layout, new_size);
        if !new_ptr.is_null() {
            LIVE_BYTES.fetch_sub(layout.size(), Ordering::Relaxed);
            record_alloc(new_size);
        }
        new_ptr
    }
}

#[global_allocator]
static GLOBAL: TrackingAllocator = TrackingAllocator;
const MIN_POWER: u32 = 8;
const MAX_POWER: u32 = 18;
const RUNS: usize = 8192;


fn merge_two_sorted(left: &[usize], right: &[usize]) -> Vec<usize> {
    let mut out = Vec::with_capacity(left.len() + right.len());
    let mut i = 0;
    let mut j = 0;
    while i < left.len() && j < right.len() {
        if left[i] <= right[j] {
            out.push(left[i]);
            i += 1;
        } else {
            out.push(right[j]);
            j += 1;
        }
    }
    out.extend_from_slice(&left[i..]);
    out.extend_from_slice(&right[j..]);
    out
}

fn unshuffle_sort(a: &mut [usize]) {
    let mut piles: Vec<Vec<usize>> = Vec::new();

    for &x in a.iter() {
        let mut placed = false;
        for pile in piles.iter_mut() {
            let front = pile[0];
            let back = *pile.last().unwrap();
            if x <= front {
                pile.insert(0, x);
                placed = true;
                break;
            } else if x >= back {
                pile.push(x);
                placed = true;
                break;
            }
        }
        if !placed {
            piles.push(vec![x]);
        }
    }

    if piles.is_empty() {
        return;
    }

    let mut merged = piles[0].clone();
    for pile in piles.into_iter().skip(1) {
        merged = merge_two_sorted(&merged, &pile);
    }

    a.copy_from_slice(&merged);
}


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

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

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

/// Peak heap growth during `benchmark_sort`, in KiB (explicit buffers such as swap).
fn run_once(size: usize, seed: usize) -> (u128, usize) {
    let mut array = input_array(size, seed as u64);

    let base_bytes = LIVE_BYTES.load(Ordering::Relaxed);
    PEAK_BYTES.store(base_bytes, Ordering::Relaxed);

    let start = Instant::now();

    benchmark_sort(&mut array);

    let elapsed = start.elapsed();
    let peak_bytes = PEAK_BYTES.load(Ordering::Relaxed);
    let aux_kb = peak_bytes.saturating_sub(base_bytes) / 1024;

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

    (micros(elapsed), aux_kb)
}

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 == "--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 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 aux_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;
            }

            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