prosolis
7179339bd2
src/player/load.i expands both codebooks to word-per-pixel form and packs the palette to GGGGGRRRRRBBBBBI out of the RAW container header, byte-exact against tools/bench/dlxload.py on both CPU cores. The palette half is gated on words read back out of the palette registers at $E82000, so "the words reached the hardware" is part of what passes. ROADMAP P1 is done; P2's encoder half (a reserved black entry, 23.4) is not, and is a re-encode rather than an edit. A scene change costs 18.96 ms of 68000 time, 22.8% of one 12 fps frame; boot costs 24.70 ms. The scratch tables describe the CRTC, not the scene, so pal_tables is a separate entry point built once at boot -- 5.29 ms off every scene change. The one that moves something: the scene header is 5,920 B that no rate table in this tree included, because it belongs to no frame record. In FINDINGS 51.3's currency it is divided by the surplus pipe - wire, so it is hypersensitive: 138 ms of extra refill climb at 488 KB/s and 1.099 s at 451.4 KB/s, for the same bytes. tools/analysis/22_scene_load.py prices it across explicit rates. Recorded as open: the two CPU cores agree to <3% on every stage but the table build, where they differ by 16.4%. px68k's C68K charges a flat 50 clocks for MULU/MULS (c68kmacro.h:1869) where the 68000 charges 38+2n, which explains 4,608 of the 8,703 clock gap. 4,095 clocks are unexplained. Nothing else in src/player/ multiplies, so no figure in FINDINGS 24-52 is affected. decode.s and stream.s are untouched; decode.bin is still 1,296 B at the same MD5. check.sh gains a stage that gates byte-exactness on both cores and deliberately does not gate the cycle counts -- MAME's clock is 1/55.46 s and a wall timing would make the green light host-sensitive. Claude-Session: https://claude.ai/code/session_01194oWYW8DQXK1SZ2DnChW6
55 lines
2.6 KiB
Bash
Executable File
55 lines
2.6 KiB
Bash
Executable File
#!/bin/bash
|
|
# One load-time transform run: the 68000 builds its own codebooks and palette
|
|
# out of the RAW container header, on both CPU cores (ROADMAP P1+P2, FINDINGS
|
|
# 53).
|
|
#
|
|
# tools/bench/load_run.sh [container]
|
|
#
|
|
# Both instruments run the same loadgate.bin over the same header bytes:
|
|
# * MAME, which is the only one of the two with real PALETTE REGISTERS -- the
|
|
# packed words are read back out of $E82000, not out of a RAM shadow, so
|
|
# "the words reached the hardware" is part of what passes.
|
|
# * px68k's C68K, which is exact to the cycle and counts BUS cycles, and is a
|
|
# second opinion on the cost from a separately written cycle table.
|
|
# Both outputs are compared byte-for-byte against tools/bench/dlxload.py, which
|
|
# stays the reference: this code replaces where those transforms RUN, not what
|
|
# they produce.
|
|
set -e
|
|
cd "$(dirname "$0")/../.."
|
|
DLX=${1:-tmp/rc_fr_singe_scsi_span.dlx}
|
|
PX68K=${PX68K:-$HOME/src/px68k}
|
|
ITER=${DLX_LOAD_ITER:-40}
|
|
|
|
tools/vasm/vasmm68k_mot -Fbin -o tmp/loadgate.bin src/player/loadgate.s > /dev/null
|
|
python3 tools/bench/prep_load.py "$DLX" > tmp/prep_load.log
|
|
cat tmp/prep_load.log
|
|
|
|
# stdbuf -oL: without it a long MAME run is unobservable until it exits, and a
|
|
# run that is merely finishing looks exactly like one that is wedged (34.1).
|
|
( cd tmp && DLX_LOAD_ITER=$ITER SDL_VIDEODRIVER=dummy stdbuf -oL timeout -k 5 180 \
|
|
mame x68000 -bios ipl10 -ramsize 2M -video soft -window -sound none \
|
|
-nothrottle -plugins -autoboot_script ../tools/bench/load.lua \
|
|
-seconds_to_run 30 > load_check.log 2>&1 )
|
|
# A run that never reached the dump must fail as that, not as a byte mismatch.
|
|
grep -q "^\[LOD\] done" tmp/load_check.log || {
|
|
echo "FAIL: the load rig did not finish -- no completion marker."
|
|
tail -6 tmp/load_check.log; exit 1; }
|
|
grep -a "^\[LOD\]" tmp/load_check.log | sed -n '/summary/,$p' | sed 's/\[LOD\] / /'
|
|
python3 tools/bench/verify_load.py "$DLX"
|
|
|
|
if [ -f "$PX68K/m68000/c68k.c" ]; then
|
|
make -s -C tools/bench/c68k PX68K="$PX68K" 2>/dev/null
|
|
for M in 4 1 2 7 3; do
|
|
tools/bench/c68k/c68k_bench --code tmp/loadgate.bin --loadraw tmp/load_data.bin \
|
|
--loadmode $M --loaditer 1 --cb1 8192 --cb4 2048 \
|
|
$([ $M = 3 ] && echo "--loaddump tmp/load_c68k.bin") 2>&1 >/dev/null \
|
|
| grep -av arena | sed 's/\[C68K\] / /'
|
|
done
|
|
# The second core's bytes are held to the same standard as the first's.
|
|
cmp -s tmp/load_c68k.bin tmp/load_out.bin || {
|
|
echo "FAIL: the two CPU cores produced DIFFERENT load-time output."; exit 1; }
|
|
echo " OK both CPU cores produced the same $(stat -c%s tmp/load_out.bin) B"
|
|
else
|
|
echo " SKIPPED: no px68k at $PX68K (set PX68K= to point at a checkout)"
|
|
fi
|