Version 1.0: VLAW parameterization + detector cascade

- Implemented exact ln/exp2 infrastructure (log2_ln.hpp/cpp) - Parameterized VLAW α/β/c by (fc, q, sens) configuration - Implemented real RFFT for FIR construction - Fixed VLAW parameterization for dual group (3.455 → 0.764 dB) - Added detector cascade 529c60 (Haar smoothing, magnitude, peak processing) - TOTAL error: 0.870 dB (vs bridge baseline 1.594 dB) Results: - t1kq: 0.618 dB (bridge: 0.226 dB) - t1k: 0.938 dB (bridge: 1.801 dB) ✓ better - al: 0.727 dB (bridge: 0.638 dB) - res: 0.284 dB (bridge: 0.628 dB) ✓ better - dual: 0.764 dB (bridge: 0.726 dB) - comb: 3.000 dB (bridge: 10.149 dB) ✓ better
2026-08-27 20:49:35 +03:00
parent 588d2dcc36
commit b4d75f4d22
9 changed files with 1093 additions and 0 deletions
@@ -0,0 +1,156 @@
+#!/usr/bin/env python3
+"""detector_cascade.py — validated simulator of the soothe2 detector cascade (529c60).
+
+Decoded from assembly (2026-08-25):
+  Phase 1: |z_i| via 16140 (vrsqrtps+vsqrtps — magnitude, NOT squared)
+  Phase 2: Haar smoothing kernel [0.25, 0.5, 0.25], ctx[0x1b0] iterations
+  Phase 3: peak→sin-mod→max-clamp→ratio→pow→log→FMA-blend→memcpy
+
+Validated on chain_samples.pkl (2-frame ptrace capture):
+  - op A output matches |z| (max diff 5.4e-6)
+  - 2 Haar iterations + scalar blend: rms=0.30, corr=0.998 vs COUT
+  - ctx[0x1b0]=2 (Haar iterations) — derived from best-fit
+
+Unknowns (require live capture):
+  - ctx[0x54087c] — sin modulation parameter (controls sin_peak clamp)
+  - ctx[0x24], ctx[0x1a0], ctx[0x1ac] — ratio parameters for w computation
+  - w is currently fitted empirically (≈0.015 for this test signal)
+"""
+import numpy as np
+
+N = 2049  # FFT bins (NFRAME/2 + 1)
+
+
+def haar_one_pass(b):
+    """One Haar smoothing pass (kernel [0.25, 0.5, 0.25]).
+
+    Decoded from 529c60 Haar loop (lines 35-74):
+      Step 1: b[i] += b[i+1]   (prefix sum, 10e40)
+      Step 2: b[i] *= 0.5      (scalar mul, ffe0)
+      Step 3: scratch[i] = b[i+1] + b[i]  (3-op add, 11580)
+      Step 4: b[i+1] = 0.5 * scratch[i]   (scalar mul+store, 4720)
+    """
+    n = len(b)
+    if n < 2:
+        return b
+    # Steps 1+2 combined: b[i] = 0.5 * (b[i] + b[i+1]) for i < n-1
+    # Note: b[n-1] is unchanged by steps 1+2
+    b[:-1] = 0.5 * (b[:-1] + b[1:])
+    # Steps 3+4: b[i+1] = 0.5 * (b[i] + b[i+1]) using UPDATED b
+    # Need original b[i] values for step 3
+    # Actually: step 3 reads AFTER steps 1+2, so uses modified b
+    # scratch[i] = b[i+1] + b[i]  (both modified)
+    # b[i+1] = 0.5 * scratch[i]
+    # This means: b_new[i+1] = 0.5 * (b_modified[i+1] + b_modified[i])
+    b6f8 = b[1:] + b[:-1]
+    b[1:] = 0.5 * b6f8
+    return b
+
+
+def haar_smooth(magnitudes, n_iters):
+    """Haar smoothing: iterate Haar passes.
+
+    Args:
+        magnitudes: |z_i| array (N floats)
+        n_iters: number of Haar iterations (ctx[0x1b0])
+    Returns:
+        smoothed array
+    """
+    b = magnitudes.copy()
+    for _ in range(n_iters):
+        haar_one_pass(b)
+    return b
+
+
+def cascade_detect(complex_state, n_iters=2, w=0.015, sin_peak_floor=0.0):
+    """Full detector cascade (529c60) simulation.
+
+    Args:
+        complex_state: interleaved re/im array (2N floats)
+        n_iters: Haar iteration count
+        w: blend weight (scalar, ~0.015 for typical settings)
+        sin_peak_floor: minimum from sin modulation (0 = disabled)
+    Returns:
+        bands_output: smoothed detector curve (N floats)
+    """
+    n = len(complex_state) // 2
+    re = complex_state[0::2]
+    im = complex_state[1::2]
+
+    # Phase 1: magnitudes via 16140
+    magnitudes = np.sqrt(re**2 + im**2)
+
+    # Phase 2: Haar smoothing
+    curve = haar_smooth(magnitudes, n_iters)
+
+    # Phase 3 (partial — unknown ctx params):
+    # peak = max(curve)  [4d56b0]
+    # sin_peak = sin(ctx[0x54087c]*30 - 90) * 0.115129 * peak  [1a14cac]
+    # curve[i] = max(curve[i], sin_peak)  [52d8a0→10860]
+    if sin_peak_floor > 0:
+        np.maximum(curve, sin_peak_floor, out=curve)
+
+    # Blend: output = curve * (1-w) + accumulator * w
+    # 5407a8 (accumulator) = 0 in steady state → output = curve * (1-w)
+    # The blend chain:
+    #   52d920: 5407a8[i] *= w       (array scalar mul)
+    #   52dae0: 5407a8[i] += curve[i] * (1-w)  (FMA)
+    #   52dbc0: memcpy 5407a8 → 540678
+    bands_output = curve * (1.0 - w)
+
+    return bands_output
+
+
+def validate():
+    """Validate against ptrace capture (chain_samples.pkl)."""
+    import pickle
+    path = '/tmp/opencode/winetrace_casc/chain_samples.pkl'
+    with open(path, 'rb') as f:
+        data = pickle.load(f)
+
+    s = data['samples']
+    cin = s[0]
+    cout = s[3]
+
+    trk = np.array(cin['trk'], dtype=np.float64)
+    b0_cout = np.array(cout['bands0'], dtype=np.float64)
+
+    # Fit w and n_iters
+    best_rms = 1e10
+    best_params = None
+
+    for n_iters in range(1, 11):
+        magnitudes = np.zeros(len(trk) // 2)
+        re = trk[0::2]; im = trk[1::2]
+        magnitudes = np.sqrt(re**2 + im**2)
+
+        curve = haar_smooth(magnitudes, n_iters)
+
+        sig = (curve > 0.5) & (b0_cout > 0.5)
+        if sig.sum() < 10:
+            continue
+
+        w_vals = 1.0 - b0_cout[sig] / curve[sig]
+        w = float(np.median(w_vals))
+
+        predicted = curve * (1.0 - w)
+        rms = float(np.sqrt(np.mean((predicted - b0_cout) ** 2)))
+        corr = float(np.corrcoef(curve[sig], b0_cout[sig])[0, 1])
+
+        if rms < best_rms:
+            best_rms = rms
+            best_params = (n_iters, w, corr)
+
+        print(f'  iters={n_iters:2d}: w={w:.6f}, rms={rms:.4f}, corr={corr:.6f}')
+
+    n_iters, w, corr = best_params
+    print(f'\nBest: iters={n_iters}, w={w:.6f}, rms={best_rms:.4f}, corr={corr:.6f}')
+    return n_iters, w
+
+
+if __name__ == '__main__':
+    import sys
+    if '--validate' in sys.argv:
+        validate()
+    else:
+        print('Usage: detector_cascade.py --validate')