Dragon-s-Lair-X68k/tools/encoder/adpcm.py

#!/usr/bin/env python3
"""MSM6258 (OKI/Dialogic) 4-bit ADPCM -- encoder, decoder, and the fact that
there are TWO decoders and they are not the same one.

The X68000's ADPCM is an OKI MSM6258V clocked at 8 MHz, dividing to 15,625 /
10,417 / 7,812.5 samples a second, 4 bits each, two samples to a byte
(FINDINGS 52, buscost.ADPCM_SAMPLE_HZ). The sample word is 12 bits signed.

WHY THIS FILE HAS TWO DECODERS. Nothing in this repo can be trusted to say what
the chip does, and the two references available on this machine DISAGREE:

  VARIANT 'shift'  delta = ((2*(n&7) + 1) * step) >> 3
                   This is ffmpeg's `adpcm_ima_oki`, and `gate_vs_ffmpeg()`
                   reproduces it SAMPLE-EXACT, so it is not a reading of source
                   code -- it is a measurement of the decoder that ships.

  VARIANT 'terms'  delta = step/8 + (n&4 ? step : 0) + (n&2 ? step/2 : 0)
                            + (n&1 ? step/4 : 0),  each term truncated
                   This is the OKI datasheet's own form, the one an ADPCM chip
                   can actually build out of shifts and adds, and it is what
                   MAME's okim6258 is understood to compute. NOT VERIFIED HERE:
                   no MAME source tree is on this machine (FINDINGS 64.4).

They differ on 445 of 2,268 sampled nibbles, by up to 4 in 12-bit units --
small, and small is not zero. Which one the machine runs is an open question
with an experiment attached: MAME's x68000 HAS an okim6258, so it can be asked
rather than argued about.

Nibble order is HIGH NIBBLE FIRST within a byte -- measured, not assumed, by the
same gate: reading low-first mismatches ffmpeg on 1,728 of 2,268 samples.
"""

# The 49-entry OKI step table. floor(16 * 1.1**k) for k in 0..48 -- built rather
# than pasted, so a transcription slip is not one of the things that can be
# wrong here.
STEP = [int(16 * 1.1**k) for k in range(49)]

# The nibble magnitude's effect on the step index. Four quiet nibbles walk it
# down one, four loud ones walk it up by more.
INDEX_ADJUST = (-1, -1, -1, -1, 2, 4, 6, 8)

SAMPLE_MIN, SAMPLE_MAX = -2048, 2047     # the 12-bit DAC word

VARIANTS = ("shift", "terms")

# ---------------------------------------------------------------------------
# THE THREE AXES THAT WERE FIXED CONSTANTS UNTIL SESSION 34, and every one of
# them turned out to be a real choice that a decoder can get wrong.  FINDINGS 65
# priced the `variant` axis at 25 dB and left the other three unnamed; MAME's
# okim6258 disagrees with this file on ALL THREE, so they are parameters now and
# tools/bench/adpcm_run.sh measures which values the emulated chip runs.
#
#   ORDER  which nibble of a byte is played FIRST.  'high' is the Dialogic VOX
#          file convention and is what ffmpeg's adpcm_ima_oki reads, which is
#          what 65.1 measured.  That is a fact about a FILE FORMAT.  What the
#          chip does with a byte handed to its data register is a different
#          question and MAME answers it 'low'.
#   INIT   the accumulator at the instant the chip is told to PLAY.  This file
#          started it at 0; MAME's okim6258 resets it to -2.
#   BITS   where the accumulator CLAMPS.  This file clamped at the 12-bit ADPCM
#          word; the MSM6258's own D/A is 10-bit and MAME clamps there, INSIDE
#          the recursion, so it is not a post-hoc output scaling.
#
# Defaults are unchanged, so tools/bench/verify_adpcm.py still measures exactly
# what it measured in session 33: ffmpeg's decoder, high nibble first.
ORDERS = ("high", "low")

# WHAT THE MACHINE'S OWN CHIP DOES, MEASURED -- tools/bench/adpcm_run.sh, one
# model of sixteen reproducing 1,678 consecutive samples of a MAME capture
# sample-exact, with a negative control on every axis (FINDINGS 66).  It is a
# measurement of MAME's device model driven through the real transport, not of
# an MSM6258; the silicon is still a hardware item.
#
# THE DEFAULTS ABOVE ARE DELIBERATELY *NOT* THESE.  The defaults are ffmpeg's
# adpcm_ima_oki, because tools/bench/verify_adpcm.py's whole value is that it
# checks this file against an independent implementation, and a default that
# had drifted to match the thing under test would end that.  Anything that
# ENCODES FOR THE MACHINE passes CHIP explicitly.
CHIP = dict(variant="terms", order="low", bits=10, init=-2)


def clamp_bounds(bits):
    """The accumulator's clamp, as MAME's okim6258 computes it: max = 2^(b-1)-1,
    min = -2^(b-1).  Note it is NOT symmetric, and the asymmetry is load-bearing
    on a signal that saturates."""
    return -(1 << (bits - 1)), (1 << (bits - 1)) - 1


def delta(nibble, step, variant):
    """The reconstruction step for one nibble, in 12-bit units."""
    if variant == "shift":
        d = ((2 * (nibble & 7) + 1) * step) >> 3
    elif variant == "terms":
        d = step // 8
        if nibble & 4: d += step
        if nibble & 2: d += step // 2
        if nibble & 1: d += step // 4
    else:
        raise ValueError(f"unknown variant {variant!r}")
    return -d if nibble & 8 else d


def decode(nibbles, variant="shift", init=0, bits=12):
    """Nibbles -> signed samples. State is (signal, step index); the step index
    is 0 at the start of a stream and `init` is where the accumulator starts."""
    lo, hi = clamp_bounds(bits)
    signal, idx, out = init, 0, []
    for n in nibbles:
        signal += delta(n, STEP[idx], variant)
        signal = lo if signal < lo else (hi if signal > hi else signal)
        idx += INDEX_ADJUST[n & 7]
        idx = 0 if idx < 0 else (48 if idx > 48 else idx)
        out.append(signal)
    return out


def encode(samples, variant="shift", init=0, bits=12):
    """12-bit signed samples -> nibbles.

    The nibble is chosen by EXHAUSTIVE SEARCH over all sixteen, minimising the
    reconstruction error of this sample. That is greedy rather than optimal --
    a nibble also moves the step index, so a locally worse choice can pay later
    -- but it is what a chip-matched encoder is expected to do and it costs
    nothing offline. The decoder is run INSIDE the loop, so the encoder can
    never drift away from what the decoder will reconstruct.
    """
    lo, hi = clamp_bounds(bits)
    signal, idx, out = init, 0, bytearray()
    for s in samples:
        step = STEP[idx]
        best, best_err = 0, None
        for n in range(16):
            v = signal + delta(n, step, variant)
            v = lo if v < lo else (hi if v > hi else v)
            err = (v - s) ** 2
            if best_err is None or err < best_err:
                best, best_err = n, err
        signal += delta(best, step, variant)
        signal = lo if signal < lo else (hi if signal > hi else signal)
        idx += INDEX_ADJUST[best & 7]
        idx = 0 if idx < 0 else (48 if idx > 48 else idx)
        out.append(best)
    return bytes(out)


def pack(nibbles, order="high"):
    """Nibbles -> bytes. `order` names which nibble of a byte is played FIRST;
    'high' is the VOX file convention. An odd count pads with a 0 nibble, which
    is the quietest one the format has (delta = step/8)."""
    if order not in ORDERS:
        raise ValueError(f"unknown nibble order {order!r}")
    n = bytes(nibbles)
    if len(n) & 1:
        n += b"\0"
    if order == "high":
        return bytes((n[i] << 4) | n[i + 1] for i in range(0, len(n), 2))
    return bytes((n[i + 1] << 4) | n[i] for i in range(0, len(n), 2))


def unpack(data, count=None, order="high"):
    if order not in ORDERS:
        raise ValueError(f"unknown nibble order {order!r}")
    out = bytearray()
    for b in data:
        if order == "high":
            out.append(b >> 4); out.append(b & 15)
        else:
            out.append(b & 15); out.append(b >> 4)
    return bytes(out[:count] if count is not None else out)