// A browser-side validation + benchmark of the GPU decision layer.
// Open this through the demo server (e.g. `npx vite` then /gpu-check.html)
// or paste it into the demo console — it needs a WebGPU device, which node
// does not have.
//
// It runs the SAME compiled strain programs on the CPU (the reference) and
// on the GPU (the experiment) over identical senses, and reports the worst
// disagreement plus the timing of both paths.

import { buildSong } from '../src/song/song.js';
import { ensureFlat, runProgram, SENSE_COUNT, GRAD_COUNT, ACTION_COUNT, REGS } from '../src/song/strains.js';
import { GpuDecisionLayer } from '../src/sim/gpu.js';
import { analyse } from '../src/audio/analyse.js';
import { decodeWav, mono } from '../src/audio/wav.js';

export async function gpuCheck(song) {
    const report = { available: GpuDecisionLayer.available };
    if (!report.available) {
        report.note = 'no WebGPU device — the CPU path remains the simulation';
        return report;
    }
    const gpu = new GpuDecisionLayer();
    report.ready = await gpu.init();
    if (!report.ready) { report.note = 'device request failed'; return report; }

    const world = { fc: 4096, FC: 64, m: song.strains.length, strains: song.strains };
    for (const strain of song.strains) ensureFlat(strain);
    gpu.uploadPrograms(world);

    // synthetic but plausible senses: random-ish, deterministic
    const fc = world.fc, m = world.m;
    const senses = new Float32Array(m * fc * SENSE_COUNT);
    const grads = new Float32Array(m * fc * GRAD_COUNT);
    let seed = 12345;
    const rnd = () => (seed = (seed * 1103515245 + 12345) & 0x7fffffff) / 0x7fffffff;
    for (let i = 0; i < senses.length; i++) senses[i] = rnd();
    for (let i = 0; i < grads.length; i++) grads[i] = Math.sign(rnd() - 0.5);

    // CPU reference
    const cpuAct = new Float32Array(m * fc * ACTION_COUNT);
    const t0 = performance.now();
    for (let s = 0; s < m; s++) {
        const strain = song.strains[s];
        const flat = ensureFlat(strain);
        const mem = new Float32Array(REGS);
        for (let b = 0; b < fc; b++) {
            const ss = senses.slice(s * fc * SENSE_COUNT + b * SENSE_COUNT,
                s * fc * SENSE_COUNT + (b + 1) * SENSE_COUNT);
            const gg = grads.slice(s * fc * GRAD_COUNT + b * GRAD_COUNT,
                s * fc * GRAD_COUNT + (b + 1) * GRAD_COUNT);
            const act = new Float32Array(ACTION_COUNT);
            runProgram(mem, 0, ss, gg, act, flat._flatI, flat._flatF, flat._flatN);
            for (let a = 0; a < ACTION_COUNT; a++) {
                cpuAct[(s * fc + b) * ACTION_COUNT + a] = act[a];
            }
        }
    }
    report.cpuMs = performance.now() - t0;

    // GPU run (the registers start zero; the CPU reference used zeroed mem too)
    const t1 = performance.now();
    const gpuAct = await gpu.decide(world, senses, grads);
    report.gpuMs = performance.now() - t1;

    let worst = 0;
    let worstAt = -1;
    for (let i = 0; i < cpuAct.length; i++) {
        const d = Math.abs(cpuAct[i] - gpuAct[i]);
        if (d > worst) { worst = d; worstAt = i; }
    }
    report.worstDelta = worst;
    report.worstAt = worstAt;
    report.verdict = worst < 1e-4 ? 'MATCH (bit-close)' : `DIVERGES (worst ${worst.toFixed(6)})`;
    return report;
}