Commit Graph

761 Commits

Author SHA1 Message Date
chrg6
ad58dfcddb Keep the fallback blit's scratch images for the sizes in use, and let the tonemap pass's views go with their image.
The scratch images of the fallback blit, one per size and format, were kept for the process, the first eight ever
asked for. Their sizes follow the scene's resolution, which DLSS modes, the dynamic resolution and a window or
picture size change move, at up to 32 MiB each at 2160 lines; a ninth size got no scratch and its blit was left out.
A new size now takes the place of the one used longest ago, which goes once the GPU is past the submission being
recorded, and never one the submission being recorded uses. The cache is under a lock, since replay workers record
blits side by side.

The tonemap pass's views were kept by image handle for the process, a game image's view naming a destroyed image that
a new image could get the handle of, and no view at all past sixteen. A view now goes with its image: at a scratch
image's replacement, and with a game image through the replay's image-gone hook.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 00:41:47 -05:00
chrg6
4882623ce7 Look the pool up again when its new mirror joins the mirror list, and count the table hand-over under the pool lock.
A mirror is made on the replay thread after a look at the pool index; a pool finalized on another thread in between
had no mirror to forget, and the new mirror then joined the list for a record already retired: freed twice, or
never. The index is searched again under the exclusive lock where the mirror joins the list, and a pool that is gone
has its new buffer deferred past the submission being recorded instead. The count of mirrors waiting for their table
hand-over is raised under the same lock that the finalize and the prologue take it down under.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 00:40:43 -05:00
chrg6
6e3dcf67d6 Finalize a memory pool that the game initializes again without finalizing it.
The back end's record of the old pool was left behind with nothing naming it: its import, a VRAM mirror that stayed
on the mirror list and in its byte count until some later mirror evicted it, a physical pool's device-local memory
for good, its device address table record and its GPU address range. Initialize now runs Finalize's work first when
the object still holds a live pool, as texture initialize already does, and the back end lets the memory go once the
GPU is past the submissions that may use it. The log counts it (the first four, then at each doubling), since how
often the game does this is not known.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 00:40:02 -05:00
chrg6
bc28416fc0 Destroy a fast-linked pipeline once its optimised build has replaced it and the GPU is done with it.
With the graphics pipeline library a draw's first pipeline is linked from stage libraries, and the optimised build
replaces it when ready. The fast link was kept until the process ended, so each pipeline a run drew held the driver
memory of two: one play session replaced 907 fast links while the video memory outside the allocator, where the
driver keeps compiled pipelines, grew by 491 MiB, and a 68,400-frame session grew it from 1,672 to 2,485 MiB.

The replaced fast link is now destroyed on the completion thread once the GPU is past the submission being recorded
and one after it. The draws read the pipeline from the cache entry each time they record and keep no handle past
their submission, so none can name the old one later. The gpl log line counts the fast links given back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 00:39:28 -05:00
chrg6
4f80dbcbc2 Bring the 0.10.0 line's low-end replay default into the pull request intake. 2026-11-12 23:04:56 -05:00
chrg6
d64a9b689c Move the sprint button's stance host off the water ripples' patch page slot, and fix how presses and timings reach it.
The stance site called page +0xf50, which the 0.10.0 line gives the water ripples above 60 fps: the second
registration ends every 1.1.1 start with "registered twice", the sprint button off included. It calls +0xf30 now, and
the comments say which slots the other sets hold. The set's switch is NX2NAVI_SPRINT_BUTTON_PATCH, not a name another
open request uses for a set of its own.

The stand-still timings count 60 Hz frames (frame_step_frames), so a toggled sprint no longer ends on a short stop at
high frame rates. A press is decided at its start for its whole length: kept from the game and the sprint's when it
begins in gameplay (B: while Link moves), else the game's alone, so a held B is not handed to the game half way and a
B that closes the pause menu starts no sprint. A sprint switched off with the button setting does not come back by
itself, Link's state is read only where the memory is readable, and the row, nx2navi.ini.example and the controls
page say that B is the jump under the game's Swap Jump Controls and name the button without assuming the layout.
tests\sprint_check.py covers the press latch, the menu press, 240 fps and the switch-off.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:57:56 -05:00
kendo
aab082ff51 Say that the sprint button's B puts the weapon away when Link is not moving, not that it attacks. 2026-11-12 22:55:14 -05:00
kendo
54fa3bc0c7 Offer only L3 and the game's B button as sprint buttons, and name B as the Nintendo layout's bottom button. 2026-11-12 22:55:14 -05:00
kendo
0a4fe144c9 Run the sprint patch set only while a sprint button is chosen, and never switch it on over a start that kept it off. 2026-11-12 22:54:58 -05:00
kendo
6faf4bd7f5 Add a sprint button: a setting that makes Link sprint without rolling first, as a toggle or while held. 2026-11-12 22:54:58 -05:00
chrg6
f3856c8dca Ask for a reused compute request before its shader module is made, and report the reuse with the prebuild.
A compute warm request the same as one built before still made its shader module, with the SPIR-V fixes, pool rebind
and marks, before the reuse table answered; the table is now asked first, all of its key being known by then. The
table is cleared under its lock, the count of reused requests is in the prebuild's and the preparation's report
instead of a line at every autosave, and NX2NAVI_COMPUTE_WARM_REUSE is a known setting, so nx2navi.ini can set it
without an "unknown key" line.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:54:02 -05:00
automata.
9e23aec717 Reuse equivalent shader translation and compute preparation work 2026-11-12 22:53:00 -05:00
chrg6
6590f68f6e Check the driver's cache of stage libraries at normal priority, into the driver's cache only, and go on with a warm from where it stopped.
Taken from pull request 760 and redone on the line's check: the sample was built at below-normal priority as the
guest started beside the boot's background builds, and on an RTX 5080 (0.9.2) it read a warm cache as cold, a median
of 136 ms, after which 42,231 libraries were built again in 873 s although the driver had them. The sample is now built
at normal priority and into the driver's cache only, as the warm's workers build (a library our own pipeline cache
holds read fast whatever the driver had), and a sample that says cold is taken again 10 s later, except while the start
waits for the whole warm after a driver change, where cold is the expected answer. The thread goes back to below
normal afterwards only when the game runs beside it.

Two parts of the pull request are not taken. The third fastest of twelve called a cache warm when three libraries
were in it, which is the partly evicted cache the warm is for; the cache counts as warm when three quarters of the
sample are fast. A resumed warm was sampled and stamped done when it looked fast, which a warm cut off past a quarter
of the list would pass with the rest never built; it is not sampled, and goes on from the variant the earlier run
reached, which shader-warm.txt now keeps every 8,000 variants, instead of from the first variant again: the cause of
the warm at every start the pull request saw with sessions shorter than a warm.

Co-Authored-By: Leyukaka <45659323+Leyukaka@users.noreply.github.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:52:54 -05:00
chrg6
de3f10fe82 Keep the pipeline cache limit at 1024 MB at least, and fold the play file only with room left for the fold's save.
The RAM-based default gave 509 MB on a 16 GB machine, below the about 550 MB a full cache of the pipeline list reaches
on an NVIDIA card: with the limit kept on the write side the files would stop there and every pipeline past it would
compile again at every start, on the most common RAM size. The default is now RAM / 32 between 1024 and 4096 MB.

A fold was taken when the merged cache fitted the limit at the boot, but pipeline-cache.bin is written at the first
autosave, after the boot's builds have added to it. Past the limit that save was refused while the play file was
written over with the new run's pipelines, and what had been folded from it in memory was then in neither file. The
fold now needs a play file's worth of room (pipeline_cache_play_mb) under the limit, and the play file is not written
while a fold is not yet in pipeline-cache.bin.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:51:08 -05:00
Leyukaka
fe5bff8328 Keep the pipeline cache files under their limit when writing them, and set the limit from the RAM.
The limit was only checked when a file was read, all or nothing, so a run could write a file the next start then
dropped whole. On an RTX 5080 (0.9.2) pipeline-cache-play.bin reached 524.9 MB in one session and the next start began
empty; pipeline-cache.bin grows 14-28 MB at each fold and crosses 512 MB within a few sessions. Now a fold is made only
when its result fits, and a cache past the limit is not saved again, so the file keeps its last save under the limit.
Unset, the limit is the RAM / 32 between 512 and 4096 MB (512 on 16 GB as before, 2048 on 64 GB), which on that PC
took boot hits from 14 to 84 % and left no pipeline to background builds.

Taken into the 0.10.0 line with its conflicts resolved: the line had raised the limit to 1024 MB and says why in
the comment above cache_data_read, in nx2navi.ini.example and in AUDIT.md; those texts keep that reason and give the
RAM-based default, whose floor the next commit raises to match.
2026-11-12 22:50:53 -05:00
chrg6
de02ced989 Leave asynchronous replay off in the low-end GPU mode.
It can show a dark or flickering frame now and then, so the mode no longer turns it on with its other defaults. Its row under the mode's switch still turns it on for a player who wants it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:50:13 -05:00
chrg6
70c9935789 Give the movie timestamp sites a switch of their own, say what changes in a decoder stall, and keep the movie cap's reasons.
The two sites that count a movie's event frames from the shown picture's timestamp were part of the real-time step's
set, so the only way back to the old count also turned the step off. They are set omovie now, NX2NAVI_MOVIE_PTS
(movie_pts in nx2navi.ini), on by default.

The comment says what the new count changes at the default movie cap: nothing while the decoder keeps up; in a stall
the cues wait with the picture instead of going on with the soundtrack, and step by 2 or more when a picture is
dropped. The counter's reader, main+0x3b3ec10, hands it out as a float frame through a virtual call; its callers were
not traced, so whether a cue on a dropped picture's tick can be missed is said to be unknown, which is what the
switch is for.

The movie cap's comment keeps the measurements it rests on, the narration 2.4 times early and the fade at 65 s of 154
at 144 fps, with one sentence on the new sites. The new test is described in prose with what it does not cover,
instead of a row in the lifter's table.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:49:19 -05:00
automata.
feeb504bf4 Drive movie event timelines from the selected video picture timestamp 2026-11-12 22:48:34 -05:00
chrg6
2571e180c8 Check the texture pool's set against the device's descriptor limits, and name the slot a carried translation reads.
The larger pool asks for 655,360 sampled images in one set where 524,288 were asked before. The start now logs the
device's limits for one set and one stage next to that count, warns when the count is over them, and a refused
layout ends the start with the limits named instead of a bare failure.

The log line for a slot registered past the pool names both slots a shader reads instead: the pool's last entry, and
the last of the old length for a translation carried over from the translator before. The comments say what they say
without an issue number.

The translator's identity changes with this pool size: after the update every install translates its shaders again
in the background, the earlier translations serve meanwhile, and a shader gets the ground fix once it is translated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-12 22:46:24 -05:00
Leyukaka
e0271c0298 Treat pool arrays of the old 32768 length as pool arrays, for translations carried over from the translator before.
After an update the game keeps the previous translator's translations until a background pass translates them again. Those still declare texture pool arrays of 32768, which spirv_pool_rebind no longer took for pool arrays once VK_POOL_TEX grew, so their textures were never bound and areas loaded with empty images. They now bind to the first 32768 entries of the larger binding.
2026-11-12 22:45:06 -05:00
Leyukaka
2388f1f581 Give the texture pool room for Ocarina's 33068 descriptors instead of 32768.
The game makes a texture pool of 33068 descriptors, and the translator clamped every pool handle to 32767, so the textures registered from 32768 up were drawn with whatever slot 32767 held, often an empty image: ground went see-through after an area load until the area was loaded again. VK_POOL_TEX and the translator's TexturePoolLength go to 40960, and a slot registered past it is logged once.
2026-11-12 22:45:06 -05:00
chrg6
c5cb67645e Write the flight dump and the memory map through a temporary file and a rename.
The window's close ends the process under the detached threads, so a dump file the flight recorder's thread was
writing stayed cut short under its own name. Its three files are now written as .part and renamed when complete
(runtime/part_file.h, with a check that kills a writer in the middle), and the allocator's map goes through
plat_file_write_cached. The shader identities and the other cache files already went through an atomic write.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:34:22 -05:00
chrg6
ec9dd522b1 Add texture compaction behind NX2NAVI_TEX_COMPACT, off by default.
With the setting on, textures no shader sampled for ten seconds are copied on the GPU out of the emptiest allocator
blocks into the holes of fuller ones, so the emptied blocks go back to the driver. A pass starts when the free space
inside the device-local blocks reaches NX2NAVI_TEX_COMPACT_MIN_MB (one block under VRAM pressure) and the block
table has blocks that hold nothing but such textures, with room elsewhere for what moves. It takes at most four
textures and NX2NAVI_TEX_COMPACT_FRAME_MB a frame, and none in a frame that loads an area, already made or uploaded
textures, or follows a long one. A released texture the size cap would drop is dropped instead of moved.

Only a texture whose image holds what the game's memory holds moves: uploaded, never written by the GPU, single
sampled, not depth. The entry takes the new image under the texture lock and its address generation moves, so every
slot, pool descriptor and memo resolves again. The old image and its views stay until the texture pool has taken
every set of its ring and the GPU is past the submissions recorded until then, as a retired texture's do.

Each pass logs what it moved and dropped, the blocks and bytes given back, and the time it took. A block emptied of
textures that the allocator keeps is left alone for ten minutes, and a pass that gave nothing back doubles the wait.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:33:29 -05:00
chrg6
d668a62854 Log how much of the allocator's blocks is holes, and how much of that a texture compaction could give back.
A log without the perf trace said nothing about the free space inside the allocator's device-local blocks, which the
driver counts as in use. Every 3600 frames (600 with the perf trace) a "mem: holes" line now gives the blocks and the
allocations in them, and for the memory type the textures use most the blocks that hold a texture, the textures and
VRAM mirrors in them, the blocks at most half full, and those of them that hold nothing but textures that could be
copied elsewhere or dropped: emptying those is the most a compaction could return.

The counting is runtime/vk_tex_compact.h, which also chooses the blocks to empty, with tests/tex_compact_check.py.
A texture entry keeps the block its memory lies in, so the table is built without asking the allocator per entry.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:33:29 -05:00
chrg6
f2a5800c1e Merge the stability pass's fixes for the points its review found.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>

# Conflicts:
#	runtime/cfg.c
2026-11-12 22:32:48 -05:00
chrg6
1a206434e0 Build the mesh pipelines' stage libraries ahead of their draws, at the preparation and at boot.
The preparation and the boot build the stage libraries of single shaders. A mesh pipeline's pre-rasterization
library needs its mesh stage and its task stage together, and its fragment shader library depends on what that mesh
stage leaves unwritten, so only a pipeline record names what they are made of.

Every listed mesh pipeline the preparation builds and every recorded one the boot queues now notes its two shader
libraries, each key once. The preparation builds them on every core after the listed pipelines and before the
pipeline cache is saved, inside the marker that covers a driver dying on a listed pipeline. The boot builds them on
one thread at idle priority beside the game, behind the memory gate, with the rest of the library prebuild
(lib_prebuild = 0 leaves it out). Each is destroyed once built, which leaves it in the pipeline caches and the
driver's own, as for the single shaders' libraries.

A mesh pipeline of known stages that a draw meets with other targets, another blend state or sample count then finds
its libraries in the caches and is linked, where it was compiled whole. The recorded and listed mesh pipelines are
still built whole ahead of play, also on a machine that leaves the rest of the shared list to its first draw.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:31:13 -05:00
chrg6
89ed3ffd17 Read ahead for mesh draws too, and let a mesh draw wait for its fast link like a vertex draw.
The look-ahead of a submission passed over mesh draws, as their pipelines had no stage libraries. Where they have
them now, a mesh draw the scan reaches is looked up with its mesh and task stages and its state is named to the
pipeline hints, so the library of its task and mesh stages, the one that takes longest to make, is building before
the replay gets to the draw. Never with the mesh fallback, which draws through vertex pipelines of its own.

A mesh draw that waits for a fast link was cut off once its pipeline had been building for 8 ms, since no link
could come. That rule now holds only for a mesh pipeline without stage libraries: with them the draw waits as a
vertex draw does, the few milliseconds of pipe_link_draw_ms from its pipeline's first miss. A one-shot mesh draw
keeps its 8 ms: when the caches lack the task and mesh library, making it is as long a compile as the whole pipeline
was, and the frame's wait pool is not spent on that.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:31:13 -05:00
chrg6
17aee6ea73 Link mesh pipelines from stage libraries like the vertex pipelines.
A mesh pipeline (task and mesh stages: the foliage, the grass, the terrain) had no stage libraries. Each new one was
a whole build, 0.2 to 1.1 s the first time foliage of a kind appeared, and its draws waited or were left out of the
picture until it was done.

Where the graphics pipeline library is on, a mesh pipeline is now linked at its first use from three libraries and
its whole build follows behind, as for a vertex pipeline. Its pre-rasterization library holds the task and mesh
stages and is keyed by both shaders. No vertex input library is linked: a mesh pipeline has no such state. Its layout
is a stage-independent pair, the mesh and task stages' bindings in set 0 and the fragment stage's in set 1, so the
fragment shader library can be the one a vertex pipeline uses. That library's key now also carries what a mesh
pipeline's fragment module gets filled in and whether the shading rate is dynamic state, which the pre-rasterization
and the fragment shader state both hold. The fragment output library is shared as it is.

The fast link on the library workers, the wait of a draw for its libraries and the pipeline hints take mesh pipelines
in. The summary counts them by themselves: fast links and their time, how long the ones a draw missed took to become
usable, and the libraries made for them.

NX2NAVI_GPL_MESH=0 (gpl_mesh in nx2navi.ini) keeps the whole build. It is also kept without the pipeline library, on
a device that draws no mesh pipeline, and where mesh pipelines alone are built without the driver's optimiser; the
start logs which is in use and why. The mesh emulation of the low-end GPU mode is not touched.

A mesh pipeline with libraries is another pipeline to the driver than the one built before, so an install's recorded
mesh pipelines are compiled once more at the first start with this change.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:31:11 -05:00
chrg6
b1f1ee3d48 Say in the log that the whole warm waits for the recorded pipelines only as long as it may take.
With the warm's time limit the line that promised a wait for all of them was wrong when the limit ended it first.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:30:56 -05:00
chrg6
9100509b00 Enable the drivers' low-latency extensions only in a run that starts with the setting on.
With the setting off the device is made exactly as before the mode existed, so the mode cannot change anything for a player who never turns it on. Turning it on in the menu then takes a restart, and the row says so; in a run that started with it on, changes still apply at once.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:30:56 -05:00
chrg6
b197136f56 Describe the profile-guided build of game 1.1.1 and the session that trains and measures a profile.
The section described the build of the other game versions with an example for 1.4.3. It now says how make_game.py
takes a kit's profile and when it leaves it out, which LLVM releases write and read the file, which packages the
instrumented build and the merge need, and the steps of a training session for 1.1.1: the build command, where the
game is started, what to play, where the counts land, the merge, and the comparison of both builds with the runtime's
sampling profiler and its frame timings.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:30:46 -05:00
chrg6
191a439fe4 Add a Low latency row to the menu's Screen tab.
Off, On, and On with boost where the mode is NVIDIA's, in English, Russian, Brazilian Portuguese and Simplified
Chinese. The row is greyed out with the reason where the mode cannot run: a driver with neither extension, a run in
which DLSS frame generation brings its own low latency, and NVIDIA's while a frame generation presents the frames. A
mode the driver refused says so under the value.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:29:59 -05:00
chrg6
c37fb7dc40 Hold each frame's start in the driver while low latency is on, and let that keep the frame limit.
The driver's sleep sits where the game's frame starts: at its first pad read or window image acquire after a present,
whichever comes first, before the input is sampled. The frame's number, the count of the game's presents, goes with
its work: the guest thread marks the simulation and the first submission, the replaying thread tags its queue
submissions and marks their end, and the present thread marks the host present, which carries the number too. The
window's swapchain is made with the latency mode while NVIDIA's path is on, and remade when the setting changes.

While the mode is in effect the pacer holds nothing, so a picture goes out as soon as it is drawn and the limit is
kept by the driver before the pad is read; RivaTuner Statistics Server is kept out as with frame generation. The pacer
takes the limit back while a movie plays, while no host present goes out, and for the rest of the run when the frames
show the driver does not hold it. With the mode off every hook returns at its first check.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:29:59 -05:00
chrg6
2f30f1a2e5 Add the low latency setting and the module that drives the drivers' own modes.
NX2NAVI_LOW_LATENCY (0 off, 1 on, 2 on with boost; live) is for low latency without frame generation: NVIDIA's mode
through VK_NV_low_latency2 and AMD's through VK_AMD_anti_lag, each enabled on the device only where the driver lists
it, NVIDIA's with VK_KHR_present_id, which it needs, and AMD's with its feature. A device made by the DLSS Frame
Generation proxies gets neither: that path keeps its own low latency. vk_lowlat.c holds the calls, the frame numbering
and the statistics line; nothing calls into it yet beyond the start and the end of the device.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:29:59 -05:00
chrg6
d9bc002d9a Play the game's own amplitude at the default vibration strength on the HD rumble path.
The default strength is 130 to make up for what two motors lose. A linear actuator that takes the game's value needs none of that, and 1.3 times the amplitude clipped the strongest pulses at the safe maximum. The HD path now divides by the default, so the setting scales from the game's own amplitude.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:29:04 -05:00
chrg6
aeb6c0d5c1 Add the HD vibration row to the Controls tab and describe HD rumble in the controls guide.
The row switches rumble_hd and is greyed out, with a note of what it needs, while the gamepad in use is not a Switch
Pro Controller or Joy-Con. Its texts are in all four menu languages.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:28:36 -05:00
chrg6
df8431da7b Send the game's vibration values as they are to a Switch Pro Controller or Joy-Con, behind rumble_hd.
With NX2NAVI_RUMBLE_HD=1 (live, off by default) the gamepad the game reads, when it is a Switch Pro Controller, a
single Joy-Con or a pair of them, gets each side's low and high band with its own frequency and amplitude in the
controller's rumble report, and no dual-motor call any more. A Pro Controller and a single Joy-Con take the report
through SDL's effect call, over USB and Bluetooth; SDL refuses that call for a combined pair, so a pair's reports are
written to its two HID devices directly. Every other gamepad, the Switch 2 controllers included, keeps the motors.

The game's thread posts its newest values and a thread of input.c writes the reports: at most one every 15 ms
(rumble_hd_ms), a held value again every 30 ms, and the neutral value when the game stops sending for 250 ms, when
another gamepad takes over, when the setting is turned off and before the process ends. The rumble strength scales the
amplitude and rumble = 0 silences this path as well. With the setting off nothing is written to the controller: the
log line at the take names it by its ids, and the first report is the trial.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:28:36 -05:00
chrg6
59e3c6c35a Add the encoding and the report schedule for HD rumble on Switch controllers, with their check.
runtime/rumble_hd.c turns one of the game's vibration values (a low and a high band, each with a frequency and an
amplitude) into the four bytes a linear actuator's rumble report takes, clamps the frequencies to each band's ends and
the amplitude to the last safe step, and decides when a report is written: the newest value only, a held one again
every 30 ms, the neutral value three times once the game stops. Nothing calls it yet.

tests/rumble_hd_check.py builds it alone, checks known values, the clamps and a batch reduced to its reports, and
decodes a sweep of values with formulae of its own.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:28:36 -05:00
chrg6
3572a4d433 Number draw marks atomically, since the replay's workers record them too.
The mark counter and the ring were written as if only the replay thread made draw marks, but a pass's chunks are
recorded by the replay's workers side by side, and each of them marks its draws. The number is taken atomically now,
and each number has its own slot of the ring. The report says what the numbers mean with workers on: the two marks
the GPU names are exact, the numbers between them are in recording order and not all later in the queue; the mark
the GPU last reached is always printed, also when the list does not come to it.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:28:26 -05:00
chrg6
96d656ba1d Time the staging allocation's wait for an upload batch, and say what the batch limit and the staging pool do now.
A staging buffer that does not fit the staging pool's blocks waits for the oldest upload batch with the upload lock
held, and a replay submission that sends its uploads waits for that lock. The wait cannot leave the lock: the caller
holds the open batch's command buffer and the buffer it asks for belongs to that batch. What the wait costs on an area
load was not measured anywhere, so it is timed and logged now: the first four waits, then at every doubling of their
count, with the total and the longest.

Since staging stays inside the pool's blocks every batch is submitted at 64 MiB of staging, so upload_batch_mb = 0 is
that limit and not "no limit", and the values above it (the low-end mode's 256, the menu's 128 to 1024) change
nothing; a discrete card keeps 256 MiB of staging for the run, not 128. The settings table, the menu's text,
nx2navi.ini.example, the audit's table and the comments say so.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:27:25 -05:00
chrg6
345b393acc Give a texture handle asked for with an id out of range the reserved slot 0, inside the pool arrays.
The handle named slot 1,048,575, past the 32,768 entries of the pool arrays shaders index. A draw that binds the
handle resolved it to the stand-in, but a handle the game stores in a uniform buffer would have indexed those arrays
out of bounds on the GPU. Slot 0 is one of the 256 slots the device reports as reserved, which no game registers
into: it holds the stand-in in the arrays, and a bound handle of 0 is "no texture" already.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:25:01 -05:00
chrg6
4a6ba66115 Tell a start that was closed or stopped during the boot's builds from a driver crash, and limit the whole warm.
A marker or a journal left by a start that died in the boot's builds was always read as a driver crash. Since the
whole warm those builds run for minutes, so a start ended from outside in that time (the task manager, a program that
stops the game, the power) switched the pipeline prebuild off for that driver for good, or put up to 32 variants on
the skip list that the driver had merely been building. Closing the window was already an orderly end and still is.

The crash handler now leaves a note while the boot's builds run. With the note the next start does what it did: it
skips the prebuild, or the variants the journal names. Without it the end is taken for a stopped start: the pipelines
are built again and the journal's variants are blamed on nothing. Three such ends in a row still skip the prebuild,
for a driver that ends the process without a fault the handler sees. The boot's journal has a file of its own, so the
preparation's keeps its meaning.

The whole warm waits prewarm_full_s seconds at most (600): when they are up the game starts, the builders step down
to the background's thread counts and priority, and the file says "done", so the boot screen has one turn per driver.

tests\boot_warm_check.py covers what a leftover marker means with and without the note.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:24:22 -05:00
chrg6
e548180da2 Hand a pool's device address record to its new mirror by a store the GPU runs after the mirror's first copy.
The table still named a new mirror at record time, as the pages' twin: parts already handed to the queue wrote
through the table into the new block before its first copy, the same early access the delayed read was made to stop.
The reads then moved to the mirror some submissions later by a second change that took a second record, cleared its
note before it knew the record was there, and until it ran left the table's readers on guest memory, without what
other shaders had written into the mirror through a buffer binding.

Nothing is changed when the mirror is made now. The prologue that holds the mirror's first copy also holds a store
into the pool's record, after the copy: what was queued before it reads and writes guest memory through the table as
if no mirror existed, what comes after reads the mirror and writes both. No second record, no second change, no
window in which the table is behind. gpa_late = 0 still changes the table at once, as up to 0.9.2.

--probe-vkmem makes a mirror in a recorded submission and reads the table's own memory back: the page names the
mirror with guest memory as the twin, and the mirror holds the pool's bytes. tests\gpa_check.py runs the store as the
GPU would, before and after. A table with no record left now says so once in the log.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:18:14 -05:00
chrg6
a8639f1cb6 Keep the scene and the picture inside the shipped render-target heap when the grown heap table is not served.
The scene's share followed the settings alone. When the grown table could not be built or written (a table in a form
that is not rewritten, as a mod's may be, or a profile folder that cannot be written), the game kept the shipped heap
and the scene still went to the whole picture inside it, which is the crash the growth was made for.

The start now asks for the table before the first present and looks at the answer: without the grown table the scene
is three quarters of the picture at most and the picture stays the game's own 2560x1440, with a log line that says so.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:09:37 -05:00
chrg6
7ff1a21ef2 Grow the render-target heap for the scene's share only where the start's mode needs it, and never past the pool.
The heap grew by the full-picture factor whenever the upscaler setting was on, in every mode, and without a limit:
915 MiB at 3840x2160 where the modes below three quarters need 382, and at 10240x2880 an application pool of 13.5 GiB,
past the 12 GiB heap region, where the game's SetHeapSize is refused and nothing starts.

The share is now the start's own mode: all of the picture for dlaa, the game's own most for the modes below it. The
growth stops at what the pool can take (2,478 MiB): the scene's share is lowered to what fits, with a log line, and a
picture too large even for the game's own scene gets the most there is and a warning. A mode chosen in the menu that
renders more than the start's keeps the start's share until a restart, as the log and nx2navi.ini.example now say.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:08:44 -05:00
chrg6
a79b0a5125 Remove the counters of what a moved texture slot generation costs the draws' kept bindings.
Two play sessions answered the question they were added for: about 0.3 whole-draw skips a frame are lost to the generation moving alone, too little to build the per-slot check for.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:06:15 -05:00
chrg6
85089408f0 Merge main's replay workers default and menu row into the 0.10.0 line.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 22:06:04 -05:00
chrg6
264dbe42cc Merge the stability and memory pass into the 0.10.0 line.
Conflicts: the settings key lists and section maps take both sides' entries.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 21:49:17 -05:00
chrg6
c4268779fc Write a V register with one 16-byte store.
A scalar result (an FP operation, a scalar load, FMOV, a compare, a conversion, a 64-bit vector operation) was assigned
to the register as a zero-extended 128-bit integer, which the compiler writes as two 8-byte stores, and INS and a
single-lane load wrote their lane alone. The next 16-byte load of the register then cannot take its value from the
store buffer and waits until the stores have left it.

Every such write now builds the whole value in a vector register and stores it once (runtime/simd.h): VSET puts a
scalar in the low bits with zero above it, VSET128 writes a 128-bit value built in an integer, and VINS loads the
register, replaces one lane and stores all of it. VINS passes the value through an empty asm statement, without which
the compiler turns the load, the insert and the store back into a store of the lane.

In the 360 guest functions a play profile sampled, stores of a part of a V register fall from 64322 to 4 and whole
stores rise from 10932 to 43665; the four left copy a 16-byte guest load that the compiler itself splits because the
memory was just written in halves. Host instructions fall from 1448075 to 1427163 and stores to the Cpu from 177160 to
145566; its loads rise from 141090 to 143521, as an insert loads the register it changes.

The lifted text of FP and SIMD code changes with this, so those files are compiled again.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 21:33:21 -05:00
chrg6
1f5ee67f7e Give every skinned character motion vectors of its own, not the player alone.
A scene draw whose vertex shader reads a matrix palette and whose vertex layout feeds its joint inputs unsigned integers is drawn a second time into the motion vectors with last frame's blocks and camera, as the player's meshes are, with the same depth test and the same guard for bones that turn sharply. Which draw of last frame it continues is decided when the vectors are made, so the replay's threads cannot change it; a draw in doubt keeps the camera's motion. The player's own draws stay with their ownership records.

skin_motion (NX2NAVI_SKIN_MOTION) is 1 by default and 0 turns it off. The motion status line now counts the skinned draws seen, those drawn with their own motion and the others by reason. It has compiled and passed its checks; it has not been played.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 20:03:59 -05:00