USER DECISION: drop the `sasi` profile. Not on bandwidth -- on capacity. A SASI volume is 40 MB, and the 22.8 min of unique scene footage on the source Blu-ray (streams 00000-00201, measured, not recalled) is 146 MiB at the LOWEST rate this codec makes -- more than the machine's whole 4-unit SASI space. `scsi` is the only profile now. FINDINGS 32. Then the user asked whether we were drawing the wrong conclusions about PIO vs DMA, and we were, more broadly than the question implied. Every CPU figure in FINDINGS 24-34 is scored against the full 833,333 cycles/frame with nothing subtracted for moving the bitstream off disk. Debiting the HD63450 cycle-steal at the long-standing 8 clk/word ESTIMATE, "1 frame of 120 misses" becomes 84 of 120, median 112.4%. PIO at the span rate is 99.8% of the machine. Spans buy cycles by spending bandwidth and the bandwidth returns as steal, so 31.6's "fits completely" becomes a worst frame of 114.3%. 10 fps absorbs it: median 93.7%, 1/120. FINDINGS 35. `11_cpu_budget.py` takes --io dma|pio|none, defaults to dma, and warns if asked for none. Also landed: - item 1 done: the cost model checked against the 68000 on a cost-aware container, -3.07% to +0.01%, whole-window mean -1.22%. FINDINGS 34. - item 4 done: the container carries its own 4-byte record alignment (DLX2). 94/120 record starts were on odd addresses -- an address error, not a slow read -- now 0/120 for 16 B/s. Re-encoding reproduces 31.1 exactly. FINDINGS 33. - a `scsi` window does not fit the 2 MB machine the rig emulates (2.84 MB of stream past a 0x200000 ceiling). The gate now verifies 80 of 120 frames and SAYS so, and fails loudly when the pass does not complete, instead of reporting a phantom 49,005-pixel diff. FINDINGS 36. Three near-misses this session had one shape: an unobservable run nearly produced a false finding. stdbuf -oL on any MAME job that prints progress -- a file is block-buffered too, and a run that is merely finishing looks exactly like one that is wedged. check.sh ALL GREEN. Claude-Session: https://claude.ai/code/session_01194oWYW8DQXK1SZ2DnChW6
128 lines
5.3 KiB
Python
128 lines
5.3 KiB
Python
#!/usr/bin/env python3
|
|
"""Reference DLX1 reader/decoder -- the ground truth the 68000 player is checked against.
|
|
|
|
This is deliberately a *decoder*, not a re-run of the encoder: it parses the
|
|
container byte-for-byte the way `src/player/` must, so that any disagreement
|
|
between it and the 68000 is a decoder bug rather than two encoders differing.
|
|
`tools/analysis/09_ratectl_drift.py` already gates the encoder against its own
|
|
reconstruction; this gates the container against the player.
|
|
|
|
Everything is big-endian (see the `encode.py` docstring). Block raster order,
|
|
2-bit modes packed MSB-first: 00=SKIP 01=V1 10=V4 11=RAW.
|
|
|
|
V4 sub-block order is (sub_y, sub_x) row-major -- TL, TR, BL, BR -- matching
|
|
`vq_hybrid.paint`'s reshape(-1,2,2,2,2).transpose(0,1,3,2,4).
|
|
"""
|
|
import struct
|
|
import numpy as np
|
|
|
|
MODE_SKIP, MODE_V1, MODE_V4, MODE_RAW = 0, 1, 2, 3
|
|
|
|
|
|
class DLX:
|
|
def __init__(self, path):
|
|
self.raw = open(path, "rb").read()
|
|
b = self.raw
|
|
# DLX2 pads every frame record up to a 4-byte boundary; DLX1 lays them
|
|
# end to end. On a 68000 that is not a slow read but an ADDRESS ERROR
|
|
# (FINDINGS 28.3), so the padding is part of the format, not a loader
|
|
# convenience -- but DLX1 containers stay readable, because every
|
|
# measurement in FINDINGS 28-31 was taken on one.
|
|
if b[:4] not in (b"DLX1", b"DLX2"):
|
|
raise ValueError(f"{path}: not a DLX container")
|
|
self.version = int(b[3:4])
|
|
self.aligned = self.version >= 2
|
|
(self.W, self.H, self.fps, self.nframes,
|
|
self.k1, self.k4) = struct.unpack(">HHHHHH", b[4:16])
|
|
off_pal, off_cb1, off_cb4, off_frm = struct.unpack(">IIII", b[16:32])
|
|
|
|
self.pal = np.frombuffer(b, np.uint8, 256 * 3, off_pal).reshape(256, 3)
|
|
self.cb1 = np.frombuffer(b, np.uint8, self.k1 * 16,
|
|
off_cb1).reshape(self.k1, 4, 4)
|
|
self.cb4 = np.frombuffer(b, np.uint8, self.k4 * 4,
|
|
off_cb4).reshape(self.k4, 2, 2)
|
|
|
|
self.idx_bytes = 1 if max(self.k1, self.k4) <= 256 else 2
|
|
self.nbx, self.nby = self.W // 4, self.H // 4
|
|
self.nb = self.nbx * self.nby
|
|
self.mode_bytes = (self.nb * 2 + 7) // 8
|
|
|
|
# frame directory: (offset of the mode header, payload length)
|
|
if self.aligned and off_frm % 4:
|
|
raise ValueError(f"{path}: DLX2 frame stream starts at {off_frm}, "
|
|
f"which is not 4-byte aligned")
|
|
self.frames = []
|
|
p = off_frm
|
|
for _ in range(self.nframes):
|
|
(n,) = struct.unpack(">I", b[p:p + 4])
|
|
self.frames.append((p + 4, n))
|
|
p += 4 + n
|
|
if self.aligned:
|
|
p += -p % 4 # skip the pad to the next record
|
|
# The writer does not pad after the LAST record -- nothing follows it --
|
|
# so `p` may have advanced past the end by up to 3 bytes there.
|
|
slack = len(b) - p
|
|
if not (slack == 0 or (self.aligned and -3 <= slack < 0)):
|
|
raise ValueError(f"{path}: {slack} trailing bytes after "
|
|
f"{self.nframes} frames")
|
|
|
|
def modes(self, f):
|
|
o, _ = self.frames[f]
|
|
h = np.frombuffer(self.raw, np.uint8, self.mode_bytes, o)
|
|
m = np.stack([(h >> 6) & 3, (h >> 4) & 3, (h >> 2) & 3, h & 3], axis=1)
|
|
return m.reshape(-1)[:self.nb].copy()
|
|
|
|
def blocks(self, f):
|
|
"""Decoded 4x4 palette-index blocks for the non-SKIP blocks of frame f.
|
|
|
|
Returns (mode, dict{block index -> (4,4) uint8}). SKIP blocks are
|
|
absent by construction -- the player must leave those pixels alone,
|
|
and a decoder that materialises them is hiding the very bug this
|
|
module exists to catch.
|
|
"""
|
|
mode = self.modes(f)
|
|
o, n = self.frames[f]
|
|
p, end = o + self.mode_bytes, o + n
|
|
ib, out = self.idx_bytes, {}
|
|
b = self.raw
|
|
for i, mo in enumerate(mode):
|
|
if mo == MODE_SKIP:
|
|
continue
|
|
if mo == MODE_V1:
|
|
v = b[p] if ib == 1 else (b[p] << 8) | b[p + 1]
|
|
p += ib
|
|
out[i] = self.cb1[v]
|
|
elif mo == MODE_V4:
|
|
sub = []
|
|
for _ in range(4):
|
|
v = b[p] if ib == 1 else (b[p] << 8) | b[p + 1]
|
|
p += ib
|
|
sub.append(self.cb4[v])
|
|
blk = np.empty((4, 4), np.uint8)
|
|
blk[0:2, 0:2], blk[0:2, 2:4] = sub[0], sub[1]
|
|
blk[2:4, 0:2], blk[2:4, 2:4] = sub[2], sub[3]
|
|
out[i] = blk
|
|
else:
|
|
out[i] = np.frombuffer(b, np.uint8, 16, p).reshape(4, 4)
|
|
p += 16
|
|
if p != end:
|
|
raise ValueError(f"frame {f}: payload consumed {p - o} of {n} bytes")
|
|
return mode, out
|
|
|
|
def paint(self, canvas, f):
|
|
"""Apply frame f in place to a (H,W) index canvas. SKIP = untouched."""
|
|
mode, blks = self.blocks(f)
|
|
for i, blk in blks.items():
|
|
by, bx = divmod(i, self.nbx)
|
|
canvas[by * 4:by * 4 + 4, bx * 4:bx * 4 + 4] = blk
|
|
return mode
|
|
|
|
def decode_all(self):
|
|
"""The true reconstruction sequence: what any correct player displays."""
|
|
c = np.zeros((self.H, self.W), np.uint8)
|
|
out = []
|
|
for f in range(self.nframes):
|
|
self.paint(c, f)
|
|
out.append(c.copy())
|
|
return out
|