"""Diagnostic: is the CPU/GPU 18% divergence float32-vs-float64 in the plane
eval, and does the authentic int-truncation (golden model stores int(Ax+By+C))
reconcile them? Renders frame 11's prims three ways and compares.

  A = float64 planes, no truncation   (== current render_faithful / CPU ref)
  B = float64 planes, int-truncated    (authentic: int(Ax+By+C) fields)
  C = float32 planes, int-truncated    (authentic + GPU precision)

If B ~= C, int-truncation removes the float32/64 sensitivity -> the fix.
"""
import sys, os, struct
HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, HERE); sys.path.insert(0, os.path.dirname(HERE))
sys.path.insert(0, r'C:\VWE\TeslaRel410\dpl3-revive\patha')
import emu860, emu_main, emu860c
import numpy as np
from driver import boot, CpuShim
from vrboard import A
from texstore import build_texstore
from dpl_sampler import mode_to_texflags, wrap_index, composite
ANAME = {int(a): a.name for a in A}
emu860.Mem.log = lambda self, *a, **k: None
SRC = r'C:/VWE/TeslaRel410/emulator/render-bridge/captures/netdeath-20260708.fifodump'
PROG_LO, PROG_HI = 0x08158000, 0x08170000
W, H = 832, 512
EDGE = {0x42, 0x0d, 0x2c}
TARGET = 11

data = open(SRC, 'rb').read()
recs = []; off = 0
while True:
    i = data.find(b'VPXM', off)
    if i < 0:
        break
    ln = struct.unpack_from('<I', data, i + 4)[0]
    body = data[i + 8:i + 8 + ln]; off = i + 8 + ln
    if len(body) >= 4 and struct.unpack_from('<I', body, 0)[0] < 0x100:
        recs.append((struct.unpack_from('<I', body, 0)[0], body[4:]))
store = build_texstore(recs)
texlist = list(store.items())
r = boot(fw='vrend410', queue=recs)
shim = CpuShim()
RECV = emu_main.MAPS['vrend410']['receive']
yy64, xx64 = np.mgrid[0:H, 0:W].astype(np.float64)
yy32, xx32 = xx64.astype(np.float32), yy64.astype(np.float32)


def f32(w):
    return struct.unpack('<f', struct.pack('<I', w & 0xffffffff))[0]


def capture_polys():
    prog = {a: emu860c.r32(a) for a in range(PROG_LO, PROG_HI, 4) if emu860c.r32(a)}
    rd = lambda a: prog.get(a, 0)
    setups = [a for a in sorted(prog) if rd(a) == 0x100]
    polys = []
    for a in setups:
        p = a + 4; edges = []
        while ((rd(p) >> 8) & 0xff) in EDGE and len(edges) < 6:
            edges.append((f32(rd(p+4)), f32(rd(p+8)), f32(rd(p+12)))); p += 16
        if len(edges) < 3:
            continue
        zp = tzp = up = vp = None; tid = None; q = p
        for _ in range(70):
            w = rd(q); op = (w >> 8) & 0xff; ad = w & 0xff
            if op == 0x21 and zp is None: zp = (f32(rd(q+4)), f32(rd(q+8)), f32(rd(q+12)))
            if op == 0x43 and ad == 32 and tzp is None: tzp = (f32(rd(q+4)), f32(rd(q+8)), f32(rd(q+12)))
            if op == 0x43 and ad == 58 and up is None: up = (f32(rd(q+4)), f32(rd(q+8)), f32(rd(q+12)))
            if op == 0x43 and ad == 78 and vp is None: vp = (f32(rd(q+4)), f32(rd(q+8)), f32(rd(q+12)))
            if op == 0xf7 and ad in (141, 142) and tid is None: tid = (rd(q+4) >> 2) & 0x3f
            q += 4
        if zp is None:
            continue
        polys.append((edges, zp, tzp, up, vp, tid))
    return polys


def render(polys, xx, yy, trunc):
    zbuf = np.full((H, W), -1e30)
    img = np.zeros((H, W, 3), np.uint8)
    for edges, zp, tzp, up, vp, tid in polys:
        ep = np.ones((H, W), bool); en = np.ones((H, W), bool)
        for Ae, Be, Ce in edges:
            v = Ae*xx + Be*yy + Ce; ep &= v >= 0; en &= v < 0
        inside = ep | en
        if not inside.any():
            continue
        z = zp[0]*xx + zp[1]*yy + zp[2]
        if trunc:
            z = np.trunc(z)
        inside &= z > zbuf
        if not inside.any():
            continue
        if up and vp and tzp:
            h, (tu, tv, mode, arr) = texlist[(tid or 0) % len(texlist)]
            wu, wv, cm = mode_to_texflags(mode)
            tzv = tzp[0]*xx + tzp[1]*yy + tzp[2]
            uu = up[0]*xx + up[1]*yy + up[2]
            vv = vp[0]*xx + vp[1]*yy + vp[2]
            if trunc:
                tzv = np.trunc(tzv); uu = np.trunc(uu); vv = np.trunc(vv)
            tzv = np.where(np.abs(tzv) < 1.0, np.sign(tzv) + (tzv == 0), tzv)
            uc = (uu.astype(np.float64)/tzv*2048).astype(np.int64)
            vc = (vv.astype(np.float64)/tzv*2048).astype(np.int64)
            ui = wrap_index((uc*tu) >> 8, tu, wu); vi = wrap_index((vc*tv) >> 8, tv, wv)
            dm = composite(img, inside, arr[vi, ui], cm)
        else:
            img[inside] = (60, 60, 70); dm = inside
        zbuf[dm] = np.asarray(z, np.float64)[dm]
    return img


frames = 0; prev = False
while r.qi < len(r.queue):
    reason, _ = emu860c.run(500_000_000)
    if reason == 3:
        continue
    if reason != 0:
        break
    pc = emu860c.getstate()['pc']
    h = r.hooks.get(pc)
    if h is None:
        break
    if pc == RECV:
        if prev:
            if frames == TARGET:
                polys = capture_polys()
                print("frame %d: %d polys" % (frames, len(polys)), flush=True)
                A_ = render(polys, xx64, yy64, False)
                B_ = render(polys, xx64, yy64, True)
                C_ = render(polys, xx32, yy32, True)
                def cmp(p, q, na, nb):
                    d = np.abs(p.astype(int) - q.astype(int)).sum(2)
                    print("  %s vs %s: differ>24 %.2f%%  mean|d| %.2f"
                          % (na, nb, 100*(d > 24).mean(), d.mean()), flush=True)
                cmp(A_, B_, "float64-raw(A)", "float64-trunc(B)")
                cmp(B_, C_, "float64-trunc(B)", "float32-trunc(C)")
                cmp(A_, C_, "float64-raw(A)", "float32-trunc(C)")
                break
            frames += 1
            prev = False
        if r.qi < len(r.queue) and ANAME.get(r.queue[r.qi][0]) == 'draw_scene':
            prev = True
    if h(shim) == 'done':
        break