ROADMAP P3 said "needs MFP timer or VBL" and neither can do it. The MFP's timer clock is 16 MHz/4, its prescalers stop at 200 and its data register is 8 bits, so the slowest tick any single timer can make is 78.125 Hz -- 6.5x faster than a frame -- and 4e6/12 is not an integer, so no setting reaches 12 Hz at all. The raster has no whole divide near 12 either: 4 refreshes is 13.86 fps and 5 is 11.09. tools/analysis/23_frame_clock.py walks all 7x256 timer settings rather than asserting it. src/player/clock.i takes the V-DISP falling edge on MFP GPIP4 -- the start of vertical blanking, which is when a player would present -- and adds fps*VTOTAL per edge to a 16-bit accumulator, emitting a tick at 31,500 and keeping the remainder. The long-run rate is fps*VTOTAL/VTOTAL = 12.000000 fps exactly, and both constants are read out of the CRTC at init, so the clock is derived from the registers that generate the raster it counts. Measured over 3,000 refreshes: 3,000 interrupts, 649 ticks where 649.1429 were due. It costs 181.35 clocks per V-DISP, 838 per frame, 0.1006% of the budget -- timed by the 68000 itself, because the host's granularity is 17.64 ms and the interrupt is microseconds. The loop's own cost was calibrated rather than looked up and landed on 38.000002 clocks, which both licenses the subtraction and confirms buscost.py's model; the 181.35 then decomposes exactly, leaving 43.99 clocks for the interrupt exception -- the textbook 44, measured. THE ONE THAT MOVES SOMETHING: 12 fps on a 55.4577 Hz raster is 4.6215 refreshes, so a frame is shown for 4 refreshes (72.13 ms) or 5 (90.16 ms), 37.9% of them short. The 833,333-clock budget every figure in this project is priced against is the MEAN slot, and the short one is 13.4% under it. The cadence was already in the tree unnamed: stream.lua's tick is sampled at frame boundaries, so its gaps were always 4 or 5, and every host-paced result in FINDINGS 49/51 carried it. P3 moved who produces it onto the machine and made it visible. It is not a dropped frame -- the pace gate lets an overrun eat the next frame's idle -- and on the gate container it costs 4 frames of 120 their idle against 1 for the nominal model, most of that the frame-0 transient at 111% of budget. stream.s counts it now, and the rig matches an offline model of the divider exactly. Also struck: MAME's raster runs 2.22% fast. refresh_mode() builds the frame period from scr.max_x*scr.max_y with scr.max_x = m_htotal - 8, one character cell short and an inclusive bound used as a count, so it runs at 56.6901 Hz where the registers say 55.4577 -- agreeing to six digits with the arithmetic. Every "1/55.46 s granularity" note in this tree was wrong and is 1/56.69 s, corrected in six files with the derivation put once in crtc_mode.lua. No conclusion changes and no 68000 cycle figure moves; the CPU clock is unrelated to the screen. But anything paced by the raster runs fast under MAME, so the rig reports both rates and prices the interrupt against the hardware's. decode.s and frame.i are unchanged; decode.bin is still 1,296 B at the same MD5. The pace gate's wait loop is byte-for-byte the one FINDINGS 51 measured and the free-running path executes none of the new code. check.sh gains two stages: the clock's own measurement, and 120 frames decoded pixel-exact with nothing outside the machine deciding when a frame may start. Claude-Session: https://claude.ai/code/session_01194oWYW8DQXK1SZ2DnChW6
178 lines
7.3 KiB
Lua
178 lines
7.3 KiB
Lua
-- Time and verify src/player/decode.s on the emulated 68000.
|
|
--
|
|
-- Two questions, one run:
|
|
-- 1. CORRECTNESS. Decode the whole window frame by frame and snapshot the
|
|
-- last frame. tools/bench/verify_decode.py checks it against the Python
|
|
-- reference decoder (tools/encoder/dlx.py) pixel-for-pixel. Every SKIP
|
|
-- block in every frame is a claim about the previous frame still being on
|
|
-- screen, so a sequential run is the only honest test -- decoding one
|
|
-- frame in isolation would prove nothing about the temporal recursion.
|
|
-- 2. COST. Time individual frames chosen across the non-SKIP distribution,
|
|
-- not its mean (FINDINGS 25.6), plus one full 120-frame pass.
|
|
--
|
|
-- MEASUREMENT SCOPE, unchanged from blit.lua: MAME's gvram_w/gvram_r carry no
|
|
-- timing at all, so these are pure 68000 instruction cycles against
|
|
-- zero-wait-state memory -- a LOWER BOUND on real hardware, not a prediction.
|
|
-- Interrupts are masked (SR=$2700) so the IPL cannot steal cycles.
|
|
--
|
|
-- Codebook expansion and palette packing are done host-side by prep_dlx.py:
|
|
-- they are load-time costs, not per-frame ones, and including them would
|
|
-- flatter or damn the inner loop for no reason.
|
|
|
|
M = manager.machine
|
|
SP = M.devices[":maincpu"].spaces["program"]
|
|
|
|
local function findfile(n)
|
|
for _,p in ipairs{"../tools/bench/"..n, "tools/bench/"..n, n} do
|
|
local f = io.open(p,"rb"); if f then f:close(); return p end
|
|
end
|
|
error(n.." not found")
|
|
end
|
|
local MODE = loadfile(findfile("crtc_mode.lua"))()
|
|
local META = loadfile("decode_meta.lua")()
|
|
|
|
local FLAG, ITER, NFR, FPTR = 0x18000, 0x18008, 0x1800C, 0x18010
|
|
local CB1, CB4, STREAM = 0x20000, 0x22000, 0x30000
|
|
local GVRAM, GPAL = 0xC00000, 0xE82000
|
|
local CPUHZ = 10000000 -- x68k.cpp:1133, 40_MHz_XTAL/4
|
|
local FRAME12 = CPUHZ / META.fps
|
|
|
|
local code do local f=io.open("decode.bin","rb"); code=f:read("a"); f:close() end
|
|
local data do local f=io.open("decode_data.bin","rb"); data=f:read("a"); f:close() end
|
|
|
|
local YOFF = (MODE.height - META.H) // 2
|
|
local function T() local t=M.time; return t.seconds + t.attoseconds/1e18 end
|
|
local function P(s) print("[DEC] "..s) end
|
|
|
|
-- Bulk-load a slice of the blob as big-endian longwords. 1 MB one byte at a
|
|
-- time is 1M Lua->C calls; longwords cut that by four.
|
|
local function push(addr, s, from, len)
|
|
local i, n = from, len
|
|
while n >= 4 do
|
|
SP:write_u32(addr, (string.unpack(">I4", s, i)))
|
|
addr, i, n = addr+4, i+4, n-4
|
|
end
|
|
while n > 0 do
|
|
SP:write_u8(addr, string.byte(s,i)); addr, i, n = addr+1, i+1, n-1
|
|
end
|
|
end
|
|
|
|
local function setup()
|
|
MODE.apply(SP)
|
|
local o = 1
|
|
push(CB1, data, o, META.cb1_len); o = o + META.cb1_len
|
|
push(CB4, data, o, META.cb4_len); o = o + META.cb4_len
|
|
local palo = o; o = o + META.pal_len
|
|
push(STREAM, data, o, META.stream_len)
|
|
for c = 0, 255 do
|
|
SP:write_u16(GPAL + c*2, (string.unpack(">I2", data, palo + c*2)))
|
|
end
|
|
-- Active area starts at index 0, exactly as the reference decoder's canvas
|
|
-- does; the letterbox gets the palette's darkest entry because the encoder
|
|
-- does not yet reserve a black one (docs/STATUS.md, encoder gaps).
|
|
for y = 0, MODE.height-1 do
|
|
local base, v = GVRAM + y*1024, 0
|
|
if y < YOFF or y >= YOFF+META.H then v = META.dark end
|
|
for x = 0, MODE.width-1 do SP:write_u16(base + x*2, v) end
|
|
end
|
|
for i = 1, #code do SP:write_u8(0x10000+i-1, string.byte(code,i)) end
|
|
P(string.format("loaded decode.bin=%d B, codebooks %d+%d B, stream %d B, %d frames",
|
|
#code, META.cb1_len, META.cb4_len, META.stream_len, META.nframes))
|
|
end
|
|
|
|
local function launch(off, nfr, iter)
|
|
SP:write_u32(FLAG, 0)
|
|
SP:write_u32(ITER, iter)
|
|
SP:write_u32(NFR, nfr)
|
|
SP:write_u32(FPTR, STREAM + off)
|
|
local cpu = M.devices[":maincpu"]
|
|
cpu.state["SR"].value = 0x2700 -- supervisor, ALL interrupts masked
|
|
cpu.state["SP"].value = 0x8000
|
|
cpu.state["PC"].value = 0x10000
|
|
end
|
|
|
|
-- The plan: one sequential correctness pass, then the cost anchors, then a
|
|
-- full pass timed. Iteration counts target ~4 emulated seconds each so the
|
|
-- 1/56.69 s timing granularity (crtc_mode.lua) costs under 0.5%.
|
|
-- DLX_VERIFY_ONLY=1 drops the cost anchors and runs only the correctness pass,
|
|
-- so tools/bench/check.sh can gate the decoder without paying for ~2 minutes of
|
|
-- timing runs that would make the green light sensitive to host load anyway.
|
|
local VERIFY_ONLY = os.getenv("DLX_VERIFY_ONLY") == "1"
|
|
|
|
local PLAN = { {name="sequential decode of all "..META.nframes.." frames (correctness)",
|
|
off=0, nfr=META.nframes, iter=1, snap=true} }
|
|
for _,an in ipairs(VERIFY_ONLY and {} or META.anchors) do
|
|
local est = math.max(0.06, an.frac/100) * 1.30 * FRAME12
|
|
PLAN[#PLAN+1] = {name="frame @ "..an.name, off=an.off, nfr=1,
|
|
iter=math.max(20, math.floor(4*CPUHZ/est)), frac=an.frac}
|
|
end
|
|
if not VERIFY_ONLY then
|
|
PLAN[#PLAN+1] = {name="full "..META.nframes.."-frame pass (mean over the window)",
|
|
off=0, nfr=META.nframes, iter=1, seq=true}
|
|
end
|
|
|
|
local step, st, t0 = 0, "boot", nil
|
|
local results = {}
|
|
|
|
local function report(p, dt)
|
|
local per = p.nfr * p.iter
|
|
local cyc = dt * CPUHZ / per
|
|
local pct = 100 * cyc / FRAME12
|
|
if p.snap then return end -- correctness pass, iter=1, too coarse
|
|
results[#results+1] = {p=p, cyc=cyc, pct=pct}
|
|
P(string.format("%s", p.name))
|
|
P(string.format(" %d frames in %.4f s -> %.0f cycles/frame = %.1f%% of a %dfps frame",
|
|
per, dt, cyc, pct, META.fps))
|
|
end
|
|
|
|
SUB = emu.add_machine_frame_notifier(function()
|
|
local ok, err = pcall(function()
|
|
local t = T()
|
|
if st == "boot" then
|
|
if t < 3.0 then return end
|
|
setup(); step = 1; launch(PLAN[1].off, PLAN[1].nfr, PLAN[1].iter)
|
|
st, t0 = "running", nil; return
|
|
end
|
|
if st == "running" then
|
|
local fl = SP:read_u32(FLAG)
|
|
if fl == 1 and not t0 then t0 = t; return end
|
|
if fl == 0xEE then
|
|
P("BITSTREAM DESYNC -- decoder consumed the wrong number of payload bytes")
|
|
M:exit(); return
|
|
end
|
|
if fl == 0xFF then
|
|
report(PLAN[step], t - (t0 or t))
|
|
if PLAN[step].snap then st = "snap"; return end
|
|
step = step + 1
|
|
if PLAN[step] then
|
|
launch(PLAN[step].off, PLAN[step].nfr, PLAN[step].iter)
|
|
st, t0 = "running", nil
|
|
else st = "finish" end
|
|
return
|
|
end
|
|
if t > 400 then P("TIMEOUT flag="..string.format("%08X",fl)); M:exit() end
|
|
return
|
|
end
|
|
if st == "snap" then
|
|
M.video:snapshot()
|
|
P("snapshot taken after the sequential pass -- last frame, 68000-decoded")
|
|
step = step + 1
|
|
-- DLX_VERIFY_ONLY leaves nothing after the correctness pass, and this
|
|
-- used to walk off the end of PLAN and raise a Lua error AFTER the
|
|
-- snapshot was already on disk -- harmless to check.sh, and exactly the
|
|
-- kind of thing that gets mistaken for a decoder failure later.
|
|
if not PLAN[step] then st = "finish"; return end
|
|
launch(PLAN[step].off, PLAN[step].nfr, PLAN[step].iter)
|
|
st, t0 = "running", nil; return
|
|
end
|
|
if st == "finish" then
|
|
P("---- summary (instruction cycles only; real GVRAM adds wait states) ----")
|
|
for _,r in ipairs(results) do
|
|
P(string.format(" %-46s %8.0f cyc %5.1f%% of a frame", r.p.name, r.cyc, r.pct))
|
|
end
|
|
M:exit()
|
|
end
|
|
end)
|
|
if not ok then print("[DEC] LUA ERROR: "..tostring(err)); M:exit() end
|
|
end)
|