Align the container to the disc, and find the decoder-free packed player fits
Two sessions, unrecorded until now, committed together because their edits share files and cannot be split cleanly after the fact. Session 28 (FINDINGS 60): the container is DLX5 -- every record sector-aligned, 120/120 starting on a boundary where 3/120 did, +0.48% on the wire and zero clocks -- and the ring's release rounds to RECALN so no pad is stranded. Two encoder levers measured and refused: `--spans all` buys +0.19 dB for +67% of the wire, and joint span/lam selection emits byte-identical containers because `lam` never leaves its floor on any of 120 frames. Session 29 (FINDINGS 61): the packed full-frame blit is 27.3% of a 12 fps frame, a channel fills GVRAM in buffer mode off the disc with the CPU halted, and it walks the 1,024 B line stride itself through array chaining. At the 9 clk/B dual-address floor the codec is 110.4% of a frame and a decoder-free packed literal player is 55.2%, at +4.89 dB -- 2.75 dB past a ceiling the codec's scene-wide palette cannot cross. Encoder work is parked; the codec is kept and not built on. check.sh is ALL GREEN before and after, plus one new stage that gates the ORDER of the measured paint costs rather than their values. Claude-Session: https://claude.ai/code/session_01194oWYW8DQXK1SZ2DnChW6
This commit is contained in:
prosolis
+41
-7
@@ -66,6 +66,7 @@ import argparse, struct, sys, os
|
||||
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
||||
import numpy as np
|
||||
import vq as VQ, vq_hybrid as H, ratectl as RC, spans as SP
|
||||
from dlx import SECTOR
|
||||
|
||||
# Measured on the emulated 68000, FINDINGS 24. Instruction cycles against
|
||||
# zero-wait-state memory, so these are floors, not hardware predictions.
|
||||
@@ -134,8 +135,12 @@ def build_records(m, enc, span_mode):
|
||||
return out
|
||||
|
||||
|
||||
def write_container(path, m, frames, fps, k1, k4, span_mode):
|
||||
"""Write the whole container. Returns (total bytes, video bytes, pad)."""
|
||||
def write_container(path, m, frames, fps, k1, k4, span_mode, sector=True):
|
||||
"""Write the whole container. Returns (total bytes, video bytes, pad).
|
||||
|
||||
`sector` selects DLX5's 512-byte record alignment over DLX4's 4-byte one.
|
||||
"""
|
||||
align = SECTOR if sector else 4
|
||||
palette = m["pal"][:256]
|
||||
if len(palette) < 256:
|
||||
palette = np.vstack([palette, np.zeros((256 - len(palette), 3), np.uint8)])
|
||||
@@ -144,6 +149,9 @@ def write_container(path, m, frames, fps, k1, k4, span_mode):
|
||||
cb4_b = m["cb4"].astype(np.uint8).tobytes()
|
||||
|
||||
off_pal = 36 if span_mode else 32
|
||||
if not span_mode:
|
||||
sector = False # DLX2 has no index and no sector rule
|
||||
align = 4
|
||||
off_cb1 = off_pal + len(pal_b)
|
||||
off_cb4 = off_cb1 + len(cb1_b)
|
||||
# DLX4: the record index sits with the palette and the codebooks, ahead of
|
||||
@@ -154,7 +162,7 @@ def write_container(path, m, frames, fps, k1, k4, span_mode):
|
||||
qlens = []
|
||||
for i, rec in enumerate(frames):
|
||||
n = 4 + len(rec)
|
||||
n += -n % 4
|
||||
n += -n % align
|
||||
q = n // 4
|
||||
assert q <= 0xFFFF, (f"frame {i} is {n} B: a u16 longword count "
|
||||
f"caps a record at 262,140 B")
|
||||
@@ -169,9 +177,15 @@ def write_container(path, m, frames, fps, k1, k4, span_mode):
|
||||
# a 68000, not a slow read. It vectors into the IPL and looks exactly like
|
||||
# an infinite loop (FINDINGS 28.3). tools/bench/prep_dlx.py has been
|
||||
# realigning at load time; the container now carries it.
|
||||
tbl_pad = -off_frm % 4
|
||||
# DLX5 aligns the frame stream itself as well as the records inside it, so
|
||||
# the whole container can be laid on a volume at a sector boundary and every
|
||||
# record lands on one. Aligning the records to each other and not the run
|
||||
# they sit in would leave 117 of 120 of them off-sector again the moment the
|
||||
# scene header changed length by a byte.
|
||||
tbl_pad = -off_frm % align
|
||||
off_frm += tbl_pad
|
||||
hdr = ((b"DLX4" if span_mode else b"DLX2")
|
||||
magic = (b"DLX5" if sector else b"DLX4") if span_mode else b"DLX2"
|
||||
hdr = (magic
|
||||
+ struct.pack(">HHHHHH", m["W"], m["H"], fps, len(frames), k1, k4)
|
||||
+ struct.pack(">IIII", off_pal, off_cb1, off_cb4, off_frm))
|
||||
if span_mode:
|
||||
@@ -190,7 +204,7 @@ def write_container(path, m, frames, fps, k1, k4, span_mode):
|
||||
# record is padded too, and the file ends where the index says it
|
||||
# does rather than up to 3 bytes short of it.
|
||||
if span_mode or i + 1 < len(frames):
|
||||
n = -(4 + len(rec)) % 4
|
||||
n = -(4 + len(rec)) % align
|
||||
fh.write(b"\0" * n); frm_pad += n
|
||||
total = os.path.getsize(path)
|
||||
return total, sum(len(r) + 4 for r in frames) + frm_pad, frm_pad
|
||||
@@ -252,6 +266,13 @@ def main():
|
||||
"Default OFF: measured, it is worth one frame of 120 "
|
||||
"at --spans need and a 2%% regression at --spans all "
|
||||
"(FINDINGS 44)")
|
||||
ap.add_argument("--joint-spans", action="store_true",
|
||||
help="re-run the lam search with the bytes the span pass "
|
||||
"freed, then re-span (E3, FINDINGS 39.3 item 5). The "
|
||||
"span pass removes the block payload of every block "
|
||||
"it covers, so without this the frame lands under its "
|
||||
"allowance and the blocks that were NOT spanned were "
|
||||
"priced as if those bytes were still needed.")
|
||||
ap.add_argument("--no-cpu-fit", action="store_true",
|
||||
help="drop the per-frame 68000 decode ceiling (session 7 "
|
||||
"behaviour: 31%% of frames on hard content do not fit)")
|
||||
@@ -259,6 +280,13 @@ def main():
|
||||
help="how full the player's buffer is assumed to be at "
|
||||
"scene start, as a fraction of the bucket (0 = cold "
|
||||
"buffer after a seek, the conservative assumption)")
|
||||
ap.add_argument("--no-reserve-black", action="store_true",
|
||||
help="let the scene palette spend all 256 entries on the "
|
||||
"picture. The default RESERVES index 0 as true black "
|
||||
"(FINDINGS 23.4), because GVRAM cleared to zero shows "
|
||||
"entry 0 and the 256x192 picture sits in a 256x256 "
|
||||
"mode -- so a free palette letterboxes the frame in "
|
||||
"whatever colour mediancut happened to put first.")
|
||||
ap.add_argument("--preview")
|
||||
a = ap.parse_args()
|
||||
|
||||
@@ -279,6 +307,7 @@ def main():
|
||||
if a.disk_clk_byte is not None:
|
||||
RC.DISK_CLK_BYTE = a.disk_clk_byte
|
||||
RC.JOINT_DECIDE = a.joint_decide
|
||||
RC.JOINT_SPANS = a.joint_spans
|
||||
RC.JOINT_BUCKET = a.joint_bucket
|
||||
cyc_budget = None if a.no_cpu_fit else RC.FRAME_CYCLES
|
||||
span_mode = None if (a.spans == "off" or not rc) else a.spans
|
||||
@@ -301,8 +330,13 @@ def main():
|
||||
else:
|
||||
print(f" target {prof['kbps']} KB/s, FIXED lam={lam} (no rate control)")
|
||||
print(f" k1={k1} k4={k4}, {_IDX_BYTES}-byte indices")
|
||||
print(f" palette: " + ("255 picture colours, index 0 RESERVED as true "
|
||||
"black for the letterbox (23.4)" if not a.no_reserve_black
|
||||
else "all 256 entries to the picture (--no-reserve-black); index 0 "
|
||||
"is whatever mediancut put there, and the letterbox with it"))
|
||||
|
||||
m = H.build(a.frames_dir, k1=k1, k4=k4, iters=a.iters)
|
||||
m = H.build(a.frames_dir, k1=k1, k4=k4, iters=a.iters,
|
||||
reserve_black=not a.no_reserve_black)
|
||||
if rc:
|
||||
enc = RC.encode_rate_controlled(m, prof["kbps"], fps=a.fps,
|
||||
bucket_frames=a.bucket_frames,
|
||||
|
||||
Reference in New Issue
Block a user