//! A fabric member priced on this process's own counters
//! (`marginal_energy::measure_member_process`, what `fabric_calibrate` and
//! `mpp_energy` fall back to where the IOReport CPU rail is frozen), against an
//! oracle sharing no code with the meter: this process's own CPU energy count,
//! read around the same span with a bare `proc_pid_rusage`.
//!
//! One test in its own binary, so no other test's thread runs in this process
//! during the span (the span, and the oracle, read every thread of it).

#![cfg(feature = "fabric-meter")]

use jouleclaw_energy::span::ProcessSpanMeter;
use jouleclaw_loader_gguf::marginal_energy::{measure_member_process, MemberRuns, NotMeasured};

/// This process's own CPU energy count, nJ: `proc_pid_rusage(getpid(),
/// RUSAGE_INFO_V6)`'s `ri_energy_nj`, read with a bare buffer of the struct's 464
/// bytes at its SDK offset, 336. Written out here, sharing no code with the meter
/// it checks.
#[cfg(target_os = "macos")]
fn own_energy_nj() -> u64 {
    unsafe extern "C" {
        fn proc_pid_rusage(pid: i32, flavor: i32, buffer: *mut std::ffi::c_void) -> i32;
    }
    let mut buf = [0u64; 58];
    // SAFETY: `buf` is 464 writable bytes, the size of `rusage_info_v6`.
    let rc = unsafe { proc_pid_rusage(std::process::id() as i32, 6, buf.as_mut_ptr().cast()) };
    assert_eq!(rc, 0, "proc_pid_rusage on this process");
    buf[336 / 8]
}

#[cfg(not(target_os = "macos"))]
fn own_energy_nj() -> u64 {
    0
}

/// A CPU member (the NEON BF16 matmul) priced on this process: where both of this
/// process's counters are live, the figure is given, its GPU part an exact zero, and
/// its CPU part agrees with the oracle, read inside the span at the first operation's
/// start and the last one's end — so the span holds the oracle's window and differs
/// from it only by the meter's last and first reads around it — and the per-GFLOP
/// figure is that energy over the work. Where they are not, the member is refused,
/// never priced on the host meter. Twice, three seconds each, however loaded the host.
#[test]
fn a_cpu_member_is_priced_on_this_process_as_its_own_count_says() {
    use std::cell::Cell;
    let meter = ProcessSpanMeter::new(jouleclaw_backend_apple::gpu_liveness_load);
    let (m, n, k) = (16usize, 512usize, 512usize);
    let gflop = 2.0 * (m * n * k) as f64 / 1e9;
    let a: Vec<f32> = (0..m * k).map(|i| ((i % 101) as f32 / 50.0) - 1.0).collect();
    let w: Vec<u8> = (0..n * k)
        .flat_map(|i| jouleclaw_loader_gguf::matmul_bf16::f32_to_bf16_rne(((i % 97) as f32 / 48.0 - 1.0) * 0.1).to_le_bytes())
        .collect();
    let mut out = vec![0f32; m * n];
    for round in 1..=2 {
        let (first, last) = (Cell::new(None), Cell::new(0u64));
        let figure = measure_member_process(&meter, MemberRuns::Cpu, gflop, 3.0, || {
            if first.get().is_none() {
                first.set(Some(own_energy_nj()));
            }
            jouleclaw_loader_gguf::matmul_bf16::matmul_bf16_neon(&a, &w, &[], m, n, k, &mut out);
            last.set(own_energy_nj());
        });
        let oracle_uj = (last.get() - first.get().expect("the work ran")) / 1_000;
        eprintln!("CPU member round {round}: oracle {oracle_uj} µJ; metered={} {figure:?}", meter.is_metered());
        if meter.is_metered() {
            let f = figure.expect("a CPU member on live counters is priced");
            assert_eq!(f.gpu_uj, 0, "the NEON matmul spent GPU energy: {f:?}");
            assert_eq!(f.provenance, jouleclaw_energy::Provenance::HwShunt);
            assert!(oracle_uj > 100_000, "setup: the work read {oracle_uj} µJ");
            let ratio = f.cpu_uj as f64 / oracle_uj as f64;
            assert!((0.9..=1.1).contains(&ratio), "the span read {} µJ of {oracle_uj} µJ", f.cpu_uj);
            let total = f.uj_per_gflop * f.ops as f64 * gflop;
            assert!((total - f.cpu_uj as f64).abs() <= 1.0, "{total} µJ priced of {} µJ read", f.cpu_uj);
            // CI's macOS energy job greps for this line: the oracle ran on live counters.
            eprintln!("process calibration: CPU member round {round} read {} µJ of {oracle_uj} µJ", f.cpu_uj);
        } else {
            let why = figure.expect_err("no live counters, yet a figure");
            assert!(
                matches!(why, NotMeasured::NotWhole(_) | NotMeasured::NotOwnCounters(_) | NotMeasured::SpanFailed(_)),
                "{why}"
            );
        }
    }
}