Struct Pool 

pub struct Pool { /* private fields */ }

Persistent thread pool: shared job slot, epoch dispatch, caller participation.

Implementations

impl Pool

pub fn new(n_workers: usize) -> Self

Examples found in repository

examples/pool_lat.rs (line 15)

fn main() {
    for nt in [2usize, 4, 6, 8, 10] {
        let pool = Pool::new(nt);
        let noop: &(dyn Fn(usize, usize) + Sync) = &|_w, _n| {};
        // Warm: first dispatch spawns/parks the workers.
        for _ in 0..100 {
            pool.run(noop);
        }
        let iters = 20_000;
        let t0 = Instant::now();
        for _ in 0..iters {
            pool.run(noop);
        }
        let el = t0.elapsed().as_secs_f64();
        let per = el / iters as f64 * 1e6;
        println!(
            "threads={nt:2}  {per:7.2} us/dispatch  -> {:6.2} ms/token at 200 matvecs",
            per * 200.0 / 1e3
        );
    }
}

examples/matvec_bw.rs (line 60)

fn main() {
    let mut args = std::env::args().skip(1);
    let path = args
        .next()
        .expect("usage: matvec_bw <model.cmf> [sweep|one <tensor>]");
    let mode = args.next().unwrap_or_else(|| "sweep".to_string());
    let model = Arc::new(cortiq_core::CmfModel::open(&path).expect("open model"));

    // Real LM activations carry a few heavy channels (>8·rms); measured
    // mean on this model is ~3.7. NOUT models that distribution.
    let nout: usize = std::env::var("NOUT")
        .ok()
        .and_then(|v| v.parse().ok())
        .unwrap_or(4);
    let mk_x = |cols: usize| -> Vec<f32> {
        let mut x: Vec<f32> = (0..cols).map(|i| ((i % 17) as f32 - 8.0) / 8.0).collect();
        for k in 0..nout {
            x[k * 37 % cols] = 40.0;
        }
        x
    };

    if mode == "one" {
        let name = args
            .next()
            .unwrap_or_else(|| "model.embed_tokens.weight".to_string());
        let entry = model.tensor(&name).expect("tensor not found");
        let (rows, cols) = (entry.shape[0], entry.shape[1]);
        let nbytes = entry.nbytes as f64;
        println!(
            "tensor {name}: {rows}x{cols} {:?} = {:.1} MB, NOUT={nout}",
            entry.dtype,
            nbytes / 1e6
        );
        let t = QTensor::from_model(&model, &name).expect("wrap");
        let x = mk_x(cols);
        let mut out = vec![0f32; rows];
        t.matvec(&x, &mut out, None);
        for nt in [1usize, 2, 4, 6, 8, 10] {
            let pool = if nt == 1 { None } else { Some(Pool::new(nt)) };
            let iters = 8;
            t.matvec(&x, &mut out, pool.as_ref());
            let t0 = Instant::now();
            for _ in 0..iters {
                t.matvec(&x, &mut out, pool.as_ref());
            }
            let el = t0.elapsed().as_secs_f64();
            println!(
                "threads={nt:2}  {:6.2} ms/matvec  {:6.1} GB/s (sink {:.3})",
                el / iters as f64 * 1e3,
                nbytes * iters as f64 / el / 1e9,
                out[0]
            );
        }
        return;
    }

    // sweep: every 2-D q8_2f tensor once = one decode's worth of weights.
    let names: Vec<String> = model
        .tensors
        .iter()
        .filter(|t| t.dtype == TensorDtype::Q8_2f && t.shape.len() == 2)
        .map(|t| t.name.clone())
        .collect();
    let total_bytes: f64 = model
        .tensors
        .iter()
        .filter(|t| t.dtype == TensorDtype::Q8_2f && t.shape.len() == 2)
        .map(|t| t.nbytes as f64)
        .sum();
    println!(
        "sweep: {} q8_2f tensors, {:.2} GB total (= weights streamed per decode token), NOUT={nout}",
        names.len(),
        total_bytes / 1e9
    );

    let tensors: Vec<(QTensor, Vec<f32>, Vec<f32>)> = names
        .iter()
        .map(|n| {
            let e = model.tensor(n).unwrap();
            let (rows, cols) = (e.shape[0], e.shape[1]);
            (
                QTensor::from_model(&model, n).expect("wrap"),
                mk_x(cols),
                vec![0f32; rows],
            )
        })
        .collect();
    let mut tensors = tensors;

    // Whole-model residency pass BEFORE any timing: the first touch of a
    // 4.2 GB mmap faults ~260k pages, which would otherwise be charged to
    // whichever thread count happens to run first. REVERSE=1 flips the
    // order as a check that no first-touch cost is left in the table.
    for _ in 0..2 {
        for (t, x, out) in tensors.iter_mut() {
            t.matvec(x, out, None);
        }
    }
    let mut counts = vec![1usize, 2, 4, 6, 8, 10];
    if std::env::var("REVERSE").is_ok() {
        counts.reverse();
    }
    for nt in counts {
        let pool = if nt == 1 { None } else { Some(Pool::new(nt)) };
        // one warm pass, then two measured
        for (t, x, out) in tensors.iter_mut() {
            t.matvec(x, out, pool.as_ref());
        }
        let iters = 2;
        let t0 = Instant::now();
        for _ in 0..iters {
            for (t, x, out) in tensors.iter_mut() {
                t.matvec(x, out, pool.as_ref());
            }
        }
        let el = t0.elapsed().as_secs_f64();
        let per_tok = el / iters as f64;
        println!(
            "threads={nt:2}  {:7.1} ms/sweep  {:6.1} GB/s  -> weight-path-only ceiling {:5.1} tok/s",
            per_tok * 1e3,
            total_bytes * iters as f64 / el / 1e9,
            1.0 / per_tok
        );
    }
}

pub fn with_spin(n_workers: usize, spin_budget: usize) -> Self

Explicit spin budget (tests pin it without touching the env).

pub fn effective_threads() -> usize

The thread count from_env would use RIGHT NOW: forced (C ABI)

CMF_THREADS > big-core topology > available_parallelism−1. ≤1 means the model runs serial (no pool). Introspection (execution_mode, status endpoints) must report THIS, not available_parallelism.

pub fn from_env() -> Option<Arc<Self>>

Pool sized from CMF_THREADS (see module docs). None = serial. Without the env, heterogeneous ARM defaults to its BIG cores.

pub fn n_workers(&self) -> usize

Spawned worker threads (the caller joins each job on top).

pub fn run_rows(&self, rows: usize, f: &(dyn Fn(usize, usize) + Sync))

Run f(row_start, row_end) over 0..rows, self-balancing.

One dispatch, but workers pull row-ranges from a shared cursor instead of each taking a fixed 1/n slice. On a heterogeneous CPU (Apple Silicon: 4 P-cores + 6 E-cores here) a static split makes every matvec end at the SLOWEST core’s pace while the fast ones idle at the barrier; pulling by grain lets a P-core take several chunks for each one an E-core takes, so skew collapses to a single grain. Row ranges stay disjoint and each row’s dot is computed exactly as in the serial path → bit-identical output.

pub fn run_many(&self, parts: &[(usize, &(dyn Fn(usize, usize) + Sync))])

Multi-matrix job: one dispatch serves SEVERAL row spaces (roadmap §3 P0 — «одна внешняя публикация job на слой»). Parts are laid out back-to-back in a virtual row space and pulled by grain from one shared cursor, so QKV or gate+up cost a single barrier instead of one each. Each part’s f(start, end) sees its OWN row indices — per-row math and outputs are bit-identical to separate run_rows calls.

pub fn run(&self, f: &(dyn Fn(usize, usize) + Sync))

Run f(worker_idx, n_participants) on every worker AND the calling thread (worker_idx = n_workers() for the caller); returns when all participants have finished.

Examples found in repository

examples/pool_lat.rs (line 19)

fn main() {
    for nt in [2usize, 4, 6, 8, 10] {
        let pool = Pool::new(nt);
        let noop: &(dyn Fn(usize, usize) + Sync) = &|_w, _n| {};
        // Warm: first dispatch spawns/parks the workers.
        for _ in 0..100 {
            pool.run(noop);
        }
        let iters = 20_000;
        let t0 = Instant::now();
        for _ in 0..iters {
            pool.run(noop);
        }
        let el = t0.elapsed().as_secs_f64();
        let per = el / iters as f64 * 1e6;
        println!(
            "threads={nt:2}  {per:7.2} us/dispatch  -> {:6.2} ms/token at 200 matvecs",
            per * 200.0 / 1e3
        );
    }
}

Trait Implementations

impl Drop for Pool

fn drop(&mut self)

Executes the destructor for this type.

fn pin_drop(self: Pin<&mut Self>)

🔬This is a nightly-only experimental API. (pin_ergonomics)

Execute the destructor for this type, but different to Drop::drop, it requires self to be pinned.