Commit Graph

317 Commits

Author SHA1 Message Date
chrg6
c1951d2b37 Keep a thread's log lines in order when the log queue's lock is taken.
A thread that found the queue's lock taken for 4,000 spins wrote its line itself, ahead of the lines it had queued
earlier. On a busy machine the lock's holder loses the processor inside the copy and the lock stays taken for a time
slice, so one thread's lines reached the log out of order. A line now waits for the lock, and a line that finds no
room, or is larger than the queue, is written after everything queued before it.

tests/logq_check.py failed on this in 8 of 30 runs beside four busy processes and passes 100 of 100 now. It gained a
check that holds the queue's locks itself and fails on the old code every time, and it no longer depends on time: it
waits for the queue to empty, keeps the line about slow writes back except in the step that checks it, and counts the
lines that waited instead of timing the slowest.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 10:26:51 -05:00
chrg6
07721c0058 Test an event wait against the value the event had when the submission took its copies, so a frame is no longer drawn from data the game had not finished writing.
Each frame the game sets one of two events to 0 from the CPU, submits its worker queues and the main queue, whose first command waits for that event to be 1, and signals 1 with nvnEventSignal once it has written what the frame's commands read. The recording of a submission takes the VRAM mirror sync and the uniform snapshot at its start and tested the wait a moment later, so a signal that arrived in between passed the wait and the frame was drawn from copies taken before the signal: single frames with the whole scene's shadowing missing (6 to 7 of 255 brighter, the sky and the interface unchanged) or a black scene, more of them the busier the CPU.

Every nvnEventSignal is now numbered and keeps the value it replaced, the recording notes the number before it takes its copies, and a signal with a later number does not count for that submission. The submission stops at the wait like any wait reached before its signal and goes on at once in a submission of its own, whose copies are taken after the signal. NX2NAVI_EVENT_AT_SYNC=0 gives the earlier test. NX2NAVI_EVO_TRACE=1 logs the order in which every frame's submissions, waits and signals were replayed, which is how the frames were found.

Measured with the flight recorder's thumbnails, 1,800 presented frames a run, standing in Hyrule Field by day with the lazy write-back on, DLSS Performance, frame generation 4x and HDR: the build before this change showed 34 single-frame spikes with eight busy threads beside the game, 20 with four and 8 with six, most of them in frames whose signal came during the replay; with this change two runs with eight busy threads showed 0 and 0, with 667 and 724 such frames. A session of the user's with the lazy write-back off ran 25,200 frames without a spike in its three automatic dumps while the change stopped 4,744 wait tests.

Not measured: runs of this same build with the switch off (the two tried failed for other reasons, a device loss during the boot beside another game and a load with cold caches), any run with the lazy write-back off under load, the frame rate and GPU time against the switch off, and the differential tests, which this change does not touch. The flicker with the lazy write-back off that was reported has not been reproduced in a capture; its mechanism is the same signal and occurs there too.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 10:26:51 -05:00
chrg6
cdaab81727 Merge the texture detail setting into the combined test line.
One conflict, in the build kit's notes, which keep both the shader cache item and the Texture detail text.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:51:33 -05:00
chrg6
e3f623942b Check the texture detail in --probe-vkmem: ASTC textures are uploaded and rewritten, and every level and layer of their images must hold the game's level it stands for.
The probe takes the level from NX2NAVI_TEXTURE_DETAIL. It covers a 1024x1024 texture, a 256x256 array of three layers, and a 128x128 and an unmipped texture that stay whole, with the images as RGBA8 or BC3, and the sampler LOD clamp of a reduced texture. It passes at full, reduced and low on an RTX 5090, with NX2NAVI_ASTC_BC 0 and 1.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:38:08 -05:00
chrg6
364a40ae9b Add the Texture detail row to the settings menu's Screen tab, in the four menu languages.
The row offers Automatic, Full, Reduced and Low, names the level Automatic picks on this card, and notes that a change takes effect after a restart.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:38:08 -05:00
chrg6
8603b0e1e9 Add the texture_detail setting, which makes large ASTC textures without their largest one or two mip levels on cards with little video memory.
The textures of a loaded area are what fills a 6 GiB card: with the budget taken as 4,730 MiB a walk through Castle Town held 6,907 MiB of device memory, 4,302 MiB of it textures, 201 pools were refused their mirrors and the game ran at 20 fps. With texture_detail = reduced a mipmapped 2D or 2D-array ASTC texture of 256x256 and more that the game's CPU fills is made without its largest level, with low without its two largest when it is 1024x1024 or more. The same walk then held 5,472 MiB (textures 2,357) and 4,987 MiB (textures 1,997), and the ASTC texels decoded fell from 2,589 M to 826 M and 503 M. auto, the default, picks full from 8,192 MiB of device-local budget, low under 6,144 MiB and reduced between. full changes nothing.

The image holds the game's levels from the one it starts at (VkTexImage.skip), and the upload with its ASTC regions and BC3 encoding, WriteTexels, the write-back, the views and the sampler LOD clamp of combined bindings count from there. Render targets, storage images, 3D and cube textures, small and unmipped textures and textures the device samples as ASTC itself are left whole, as is a texture made over a live one that holds GPU-written content. A shader that fetches texels by position or uses a texture's size gets the texture whole: gfx_shader.c marks such bindings from the SPIR-V (the layer count of an array, which the translator's layer clamp asks for, does not count), and the replay makes a reduced texture bound there again with every level.

Not run on a card with 6 GiB: the figures come from an RTX 5090 with NX2NAVI_VRAM_BUDGET_MB=4730.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:38:07 -05:00
chrg6
f16554cb8e Keep the game's buffers mirrored in video memory up to half the budget, even when textures have filled it.
mirror_create refused a pool whose mirror did not fit under seven eighths of the VRAM budget. It first evicts idle
mirrors and asks idle textures for room, but on a 6 GiB card a loaded area's textures in use pass the budget by
themselves, so neither helps and the pools stay imported: the GPU then reads vertices, indices and storage over PCIe
at every draw. Two reports from RTX 3060 Laptop cards (6 GiB, a budget of about 4.7 GiB) measured 70 to 250 ms of GPU
time a frame and 5 to 13 fps in that state.

Now a mirror is made although the check fails while the mirrors together stay within half the budget; the textures
are still asked for the room, and past that share a pool is refused as before. A mirror the driver cannot keep in VRAM
is paged to system memory, where the imported pool already is, so it does not read slower than its pool.

Measured with the budget capped at 4,730 MiB on a 32 GiB card (1080p window, DLSS Balanced, no frame generation,
standing in Hyrule Field): before, 4 pools of 244.6 MiB stay imported, the largest pool among them (244.4 MiB), with
634 MiB mirrored; after, none stay imported and 878 MiB are mirrored, in two runs. The area still needs 5.6 to 6.3
GiB there, 3.9 GiB of it textures, so a 6 GiB card stays over its budget: this ends the buffer starvation, not the
overflow. Not run on a 6 GiB card.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:31:21 -05:00
chrg6
1f2b320736 Say "after restart" in the menu only while a restart would change something, and count the waiting settings on Restart.
A setting read at the start showed "after restart" under its value always. The values the game started with are now
kept (cfg.c start_values), a row shows the note only while its value differs from them, and the Restart button counts
the settings that wait, the upscaler, frame generation and HDR among them. A value the environment sets never waits.
--probe-cfg checks the count.

From pull request #377 by mooki000. Three conflicts in the menu resolved against the frame generation rows that came
in since: the upscaling row keeps its description by what can load, and the frame generation restart test knows both
ways NVIDIA's runs.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:14:23 -05:00
chrg6
a1fcbb0b07 Name NVIDIA's Shader Cache Size limit when the library warm finds the driver's cache cold.
The driver keeps the prepared shaders' libraries in its shader cache, and under Windows that cache has a size limit
set in NVIDIA's settings. A limit smaller than the set drops the oldest libraries as new ones come in (a 2048 MB cache
could not hold them on the reporter's RTX 5070 Ti), so every start builds them again in the background and play
stutters until that is done. The cold lines of the library warm now say so on NVIDIA under Windows, most plainly when
the cache is cold right after a warm that finished on the same driver; the build kit's notes and the example file say
it too. tests/warm_hint_check.py checks which hint each case gets.

From pull request #403 by tarballz; two conflicts resolved (an include and the build kit's notes).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:13:35 -05:00
chrg6
25e31815fd Keep a texture's finalization on its registered slots, so a stale slot stays stale after its image was evicted.
Whether a slot was stale was read from the released image's entry, which eviction, the released cap or a new image
at the address can destroy before the slot is looked up again; the slot then revived the texture from storage the
game had freed (the access violation in the block copy during a pool refresh). The flag now lives on the slot: a
release sets it on the slots registered with that descriptor, a registration clears it, and a finalized slot of a
CPU-written texture follows only live GPU content at its address.

From pull request #348 by TophC7, taken as it is.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:13:08 -05:00
chrg6
87bf554637 Render the scene of a picture of 1440 lines or fewer at the share its DLSS or FSR mode names.
The game sizes its scene against its own 1440-line picture only while the picture is taller; under a smaller picture
it measures against that picture itself. The share was scaled by the picture's height over 1440 in both cases, so a
1080-line picture got three quarters of the scene its mode names: Quality drew 960x540 instead of 1280x720. A picture
of 1440 lines is unchanged; a 1080-line one now draws 1.78 times the pixels in every mode, which costs frame rate on
slow cards and is what the mode asks for.

From pull request #393 by mooki000, taken as it is.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:12:33 -05:00
chrg6
bbcce968b0 Run DLAA on the pass the HUD is drawn into, so its picture reaches the screen in gameplay.
In DLAA the pass the HUD is drawn into has the scene's size and the light format, and the game's upscaler has just
written the picture there. The frame used to end at the 8-bit output pass instead, which put DLSS's picture back into
a light target nothing reads any more: gameplay showed no DLAA at all. With an upscaling share nothing changes.

From pull request #382 by mooki000, taken as it is.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 09:12:33 -05:00
chrg6
d0b15e4578 Merge the two performance changes into the 0.7.0 release line: a signalled event wakes only its own waiters, and a thread of its own writes the log.
One conflict, the list of setting names, which keeps both sides' additions.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 07:32:34 -05:00
chrg6
449b5f73b0 Merge the Linux pull requests into the 0.7.0 release line.
Eighteen commits, one per Linux pull request that was not in yet: the build fix for a source checkout, NVIDIA's shader
disk cache only with NVIDIA's driver, tools/run_game.py for a Linux game folder, a memory limit the low-memory handling
can read, the recording thread's core on Linux, shadow storage on Linux and Proton, the Steam Deck profile and prompts,
FSR 3.1 offered only where its library loads, DLSS frame generation through NGX on Linux, the AppImage with its window
and its workflow, and the processor level from /proc/cpuinfo. Two conflicts: the settings table keeps the area-load
settings under the new comment, and the example file keeps the lazy write-back as off by default and adds that it
stays off with shadow storage.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 07:31:55 -05:00
chrg6
a03e059d2b Write the log from a thread of its own, so a stalled write no longer holds the thread that logged.
Every log line was two writes on the thread that logged it, to stderr and to the log file. Such a write can stall for
tens or hundreds of milliseconds (a busy disk, a virus scanner, a console or a pipe that is slow to take it), and the
render thread logs too: a frame it spent in a write was a hitch with nothing else to show for it.

In a game run the lines now go into a queue that a log thread writes out in order (runtime/logq.c). A fatal error,
the crash report and the end of the process write the queue out on their own thread first and write their own lines
directly, so nothing is lost to an exit. A thread that finds the queue's lock held for long, or the queue full, writes
its line itself. NX2NAVI_LOG_ASYNC=0 writes every line where it is logged, as before.

Every write is timed in both modes: a "log: ... writes of the log took over 2 ms" line counts the slow ones, gives
the longest and says whose time they took.

tests/logq_check.py checks order and completeness with eight threads, a slow destination, a stopped destination with
the queue full, and the synchronous flush.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 07:22:41 -05:00
chrg6
c2a51a334a Merge GitHub main into the 0.7.0 release line: uniform blocks copied at the submit call with the replay on its own thread, the overlay's frame times measured where the pictures go out, and early pictures kept back.
The two commits main gained since the last merge. docs/releases/v0.6.2.md stays removed; the two notes they added to
it are in docs/releases/v0.7.0.md. Checked on a dev build of the merged tree: the settings, self-test, graphics ABI,
input and kernel probes pass, and a scripted run with six DLSS mode changes presents no dark or black frame, makes the
area's textures in one frame at the load and ends without a fatal error.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 07:17:01 -05:00
chrg6
094573bd26 Wake only the threads that wait for the event that was signalled.
A signalled kernel event, or a thread that ended, woke every thread blocked in WaitSynchronization. Each woken thread
takes a virtual core before it looks at its handles, asking a running thread of lower priority for its core when all
are held, finds nothing signalled and blocks again. The audio renderer signals its event 200 times a second, so every
thread that waits for a message, a timer or another thread's end did this 200 times a second at the cost of the
threads that were working.

A wait now records its handle list, and a signal wakes the waits that hold a handle of the signalled event or thread.
NX2NAVI_SYNC_WAKE_ALL=1 (or ab) wakes them all as before, and the sched line counts the waits woken and left asleep.

tests/sync_wake_check.py builds kernel.c with the rest of the runtime stubbed and checks the wakes, the timeouts, the
cancel and that none of 4,000 signals to eight looping waiters is lost, in both modes.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 07:15:30 -05:00
chrg6
9dbfed207f Turn the lazy write-back off by default and offer it in the settings menu as Experimental FPS boost.
With it on, single frames come out with the whole scene lit differently (brighter, shadows off). The flight recorder's
thumbnails of 1,800 presents standing in Hyrule Field show none with it off in every run, and with it on 43 to 181
while four other threads keep the CPU busy (10 to 97 in earlier runs, 0 on an idle machine); the cause is not found.
Two candidate fixes (arming only against a sync whose copies were handed over, and snapshots waiting for GPU writes in
flight) did not change the count, and fetching at every release made it far worse.

So wb_lazy is 0 unless set, on every platform (mem_init loses its special case), and the Screen tab has the row
Experimental FPS boost for it on Windows, with its text in the four menu languages; like every setting read at the
start it notes "after restart". The 0.7.0 notes describe it as experimental and off, say about 1.6 GiB for the video
memory a full shader cache no longer holds (2,484 to 846 MiB at the title screen in the measured run), and list the
two fixes before this one.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 07:12:23 -05:00
chrg6
71eb5fbe26 Make an area's textures at once after a load instead of over the first seconds, which showed the ground and walls black.
The texture pool creates 16 entries a refresh and stops after 6 ms a frame, so that textures streaming in do not make
long frames. An area load leaves thousands of slots at once (4,936 loading the test save), and at that rate they came
in over the frames after the load screen: the scene's first frames showed a quarter of the picture as black stand-ins,
for 22 presented frames on a free machine and for about three seconds with the CPU busy.

While a refresh leaves pool_load_backlog slots or more (512; 0 never), the pool is loading: the count limit is off, a
frame's refreshes may take pool_load_ms (50), and frame_hold leaves out the presents of frames drawn meanwhile (up to
2 s), so the picture before the load stays until fewer than 64 slots are left. Measured with the flight recorder's
thumbnails of every present: the 4,847 textures are made in one frame of 345 ms, 30 frames before the scene fades in,
and the black share of the picture goes from the fade straight to its final value. The streaming limits are as before
below the backlog.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:55:13 -05:00
chrg6
75b0dca907 Add Steam Deck button prompts beside the Xbox and PlayStation ones (prompts = steamdeck).
The Controls tab's Button prompts row and nx2navi.ini take steamdeck: the Deck's own labels in the game's
text, action prompt and ocarina notes, which are A B X Y where an Xbox pad has them, L1 R1 L2 R2 and L3 R3,
Menu and View. The style is drawn by tools/pad_prompts.py like the others, into romfs-patches-steamdeck
and romfs-patches-steamdeck-label, and every build with button art writes them.

Pull request #107 by loteran asked for PlayStation and Steam Deck prompts; it was closed, and the tree
took the PlayStation half in another form, drawn from button art instead of redrawn font glyphs. This is
the Steam Deck half in that form, written here: the art has no Deck style, so its entry in
tools/prompt_art.py names the Xbox pictures for the face buttons, Menu, View, the d-pad and the sticks
and the PlayStation pictures for the shoulders and stick clicks. It needs four pictures of the Xbox set
that no other style used (the white letters on a light button, for the ocarina's notes); a release made
with --prompt-art copies them with the rest.

The Windows files compile and tests/launcher_test.py passes, with the prompts step's test following the
number of folders (seven now); every picture the style names is in the art used for releases. The style
was not drawn here (that needs the game's font), and --probe-cfg, which has a new check, was not run.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:53:30 -05:00
chrg6
eb2608296b Generate frames with DLSS on Linux through NGX itself: 2x to 6x or dynamic, switched while the game runs.
DLSS Frame Generation went through Streamline, which only the Windows build has, so framegen = dlss did
nothing on Linux. There it now calls NGX's frame generation feature directly (vk_dlaa.c vk_ngxfg_*), with
the depth, motion vectors, jitter, camera and HUD-less picture the Streamline path gets. With it on, each
frame is composed into an image of its own instead of a swapchain image, the generated frames are made at
the end of the frame's command buffer, and a presenter thread shows them and then the rendered frame, each
copied into a swapchain image it acquires itself, spaced over the time between rendered frames
(gfx_present.c ng_*). fg_mult is the multiplier: 2 to 6, or dynamic for only the frames the display's
refresh rate needs. NVIDIA's libnvidia-ngx-dlssg.so.<version> goes beside the game; it is not in the
repository or any kit.

Pull request #124 by spidercraft. Its base was the present path of 0.5, so it is ported by hand:
- taken as written: the NGX calls and the presenter (the block is lifted from the pull request's diff);
- wired again into present_image, create_swapchain, the output rate and the HUD-less picture as they
  are now, with every new branch behind vk_ngxfg_wanted, which is 0 in the Windows build: the code is
  compiled there and never reached;
- added: frame generation's feature and parameters are released before NGX shuts down, the presenter's
  images, semaphores and command pool go when the device is released and are made again for a new one,
  and a failed submit on this path settles its fence without an acquire semaphore;
- the menu: the Frame generation row follows the setting at once on Linux and says "after restart" only
  when the game started without DLSS upscaling; the multiplier row lists what the GPU allows and Dynamic;
- the overlay row of the pull request it builds on (#123) is not part of this.
It touches vk_dlaa.c, which another session is changing: one field in N, the FG state after it, one FN
line, the instance extension query, the capability read in vk_dlaa_init, the release, and a block appended
at the end.

Known gap, as in the pull request: on this path fps_limit counts the frames the game draws. The Windows
files compile without new warnings; nothing was run, and the Linux path is not compiled here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:45:59 -05:00
epicmeme546
a710c6193d Measure the overlay's frame times where the pictures go out, and keep an early picture back to seven eighths of the recent interval.
The overlay's rate, lows and graph were fed from the game's present calls. With the replay on the submitting thread, work held for an event is replayed with the next frame, so the calls come in uneven steps although each frame costs about the same: 36 and 9 ms apart in turn in a village, a sawtooth in the graph and a 1% low of 14 fps, while the pictures went out 19.7 ms apart on average and changed by 3.9 ms from one to the next. The present thread now reports each picture (perfmon_shown) and the overlay takes its intervals from that; the game's calls are used only where no present thread reports.

A picture that arrives early now waits until seven eighths of the recent interval have passed since the one before (vk_backend.c pace_smooth, NX2NAVI_PACE_SMOOTH, on by default; not with frame generation). In that village the change from one picture to the next went from 3.9 to 3.0 ms at 51 fps both ways, in a graveyard from 3.1 to 2.6 ms at 54.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:35:28 -05:00
chrg6
d985e0ecb0 Offer FSR 3.1 in the Screen tab only where its library can load.
On Linux the Screen tab listed the five FSR 3.1 upscaling modes and AMD's frame generation, but only the
Windows build loads amd_fidelityfx_vk.dll: a player who picked a mode got the scene at the mode's share of
the picture with nothing to scale it back up. vk_ffx_available answers from the load's result once it ran,
and before that from the library file being there, so the menu can ask every frame. Where it says no,
the menu lists neither, a mode that is still set shows "in use: off", the scene keeps the game's own
share (vk_dlaa_fsr3), frame generation keeps the plain swapchain with one log line, and the texts name
what does run.

Pull request #371 by mooki000, taken as it is; two hunks merged by hand (vk_fg_wanted, which now also
stays off after a failure, and a README line that had gained Texture filtering). It touches vk_dlaa.c,
which another session is changing: vk_dlaa_fsr3 gains the availability test and one log text changes.

On Windows the menu changes only where the DLL is missing. The Windows files compile; nothing was run.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:33:22 -05:00
chrg6
5b6dc0cfa0 Give the Steam Deck profile four virtual cores, BC3 for ASTC textures and a shorter spin hand-off.
On a Steam Deck the settings the player has not set now also default to cores = 4 (the game's six virtual
cores share the Deck's four physical ones), astc_bc = 1 and spin_handoff_us = 30. Like the profile's other
values they are starting points that no Deck measurement stands behind yet.

Pull request #404 by PlayerJV55 (closed on GitHub, no description). Taken: the three profile values, with
the profile's comment and nx2navi.ini.example brought up to them. Not taken, each for a reason:
- play.sh exporting the same values on a Deck: the game finds the Deck itself and applies the profile;
- folding the virtual cores onto the physical ones on every machine with fewer than six cores: that
  changes the default on Windows PCs too, and nothing was measured;
- keeping one unwritten page inside a run of written pages in the shadow copy-in (vk_memory.c): the
  extra page is copied from guest memory over what a shader may have stored there through the device
  address table, which never comes back to guest memory, for a gain nobody measured;
- the release workflow: it publishes a release, not a draft, and puts an empty file in the translator's
  place when its build fails. The workflow of pull request #273 builds the same AppImage and refuses to
  attach a broken one.

cfg.c compiles; nothing was run, and there is no Steam Deck here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:32:37 -05:00
chrg6
4d12238e69 Let a shadow write-back clear the write watch's protection of its range in one call on Linux (shadow_bulk_write = 1).
On Linux the write watch protects pages, so a write-back from shadow storage into guest memory took a fault
at the first store into every page. plat_mem_prepare_write clears the protection of a range with one
UFFDIO_WRITEPROTECT call; the pages count as written, as they would after the faults. Off by default;
Windows has nothing to clear.

Pull request #327 by theurbanninja1993-sketch (a draft on GitHub). The platform function and its Linux
test are taken as they are. The call moved: the write-back it was written for is now shadow_write_back in
runtime/vk_memory.c (a file other sessions are changing), where it covers the runs of pages a submission
changed, and the setting is registered in cfg.c and described in nx2navi.ini.example, which also says
that the lazy write-back stays off with shadow storage.

The Windows files compile; the Linux code and its test are not compiled or run here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:31:27 -05:00
chrg6
3134f52475 Let shaders follow guest pointers into shadow copies, and keep those copies current for the device address table's readers.
With shadow storage (Linux, and Windows builds under Wine) a CPU-visible pool is a host-visible copy with
no memory object of its own, and only pools that owned one went into the device address table: pointers
the game's shaders read from memory reached nothing. Shadow copies are now in the table. A shader that
reads through the table resolves no pool, so nothing queued the pool it reaches for the copy-in: the part
is marked where its pipeline is drawn or dispatched (VkPipeInfo.gpa, vk_mem_gpa_use), and its prologue
brings the shadow of every pool in the table up to date with the CPU's writes and queues the same pages
for those pools' VRAM mirrors (vk_memory.c vk_mem_gpa_sync). --probe-vkmem reads a word through the table
from a pool that is never bound, before and after a plain CPU write.

Pull request #353 by TophC7, ported onto the base copies of the black-world fix:
- taken as it is: the table registration, the mark in vk_exec_draw.c and vk_pipeline.c, the prologue
  call and vk_sync_probe_submit in vk_sync.c (two hunks merged by hand), the probe's test;
- written again: vk_mem_gpa_sync, on top of the snapshot-based shadow_sync_pool; a lookup no longer
  queues a pool for being in the table, which every shadow pool now is;
- narrowed: the sync runs only with shadow storage. Without it (Windows) a mirrored pool stays unsynced
  for the table's readers as before, so the frame there is unchanged, and the probe makes the source's
  mirror only with shadow storage and skips when the device has no address table;
- the probe's shader was an array of SPIR-V words in tex_probe.c; it is now the source
  runtime/shaders/gpa_read.spvasm, built like the other runtime shaders;
- the exact re-upload count in the texture probe stays checked on Windows.
Files other sessions are changing: runtime/vk_memory.c (vk_pool_init's registration, mem_resolve's touch,
the new section before vk_mem_use).

The Windows files compile and the shader assembles and validates; no probe was run, and nothing was run on
Linux here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:30:06 -05:00
chrg6
df2427d00a Check that a part's CPU inputs reach the GPU ahead of its own noted writes, and let a frame dump pick shaders and keep raw texels.
This pull request fixed lighting that added up frame after frame under shadow storage on Linux: a GPU write
noted while a part was recorded kept that part's CPU inputs (the game's resets of its lighting accumulators)
out of the shadow. Its fix marked noted ranges as submitted in vk_memory.c; the base copies that came with
the black-world fix already move every CPU-changed byte in before the part runs, so that part is not taken
and no SHADOW_PENDING_INPUTS setting is added. Taken from it:
- tex_probe.c (--probe-vkmem): a range noted as a future GPU write still gets the CPU's bytes before the
  GPU reads it. The pull request's other check, that a CPU write made after a GPU result loses to it until
  the write-back, is left out: with base copies the later CPU write wins, as it does on the console.
- vk_dump.c: NX2NAVI_DUMP_SHADERS=<hash>,... copies images only for passes that use those shaders, and
  NX2NAVI_DUMP_RAW=1 also saves each copied image's texel bytes.
- tools/fix_linux_ambient_power.py, as it is: patches one translated shader of a player's own cache so a
  zero exponent no longer gives NaN. It holds two hashes and no shader data.

Pull request #264 by intellq. The Windows files compile; the probe was not run, and nothing was run on
Linux here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:24:56 -05:00
chrg6
f740e95a62 Fix the black 3D world under shadow storage on Linux and Proton, and copy only what each side wrote.
Shadow storage noted a GPU write with the whole range its binding names: the copy-in skipped that range and
the fence copied all of it back, so CPU writes to other fields of the same records never reached the GPU.
Ocarina's lighting parameter is such a field: the lighting came out NaN and the fog pass drew the scene
black. Each page a noted range covers now keeps a base copy, the copy-in moves only the bytes the CPU
changed and the write-back only those the GPU changed (vk_memory.c merge_page). The mirror's merge shader
marks the 4 KiB pages it changed, and one job per submission copies only those back (shadow_wb_cb); the
copy-in reads the CPU-side generation tables through the shared write-watch snapshots; and a caller that
reads guest memory itself resolves with vk_mem_lookup, which does not queue the pool for the copy-in.

Pull request #394 by jacc. Its changes are taken as they are; one hunk met the lazy write-back that came
later (vk_gpu_written_back) and is merged by hand. Added here: the lazy write-back stays off with shadow
storage, because its fetch copies the mirror into the pool's buffer, which is guest memory only for an
imported pool. Files other sessions are changing: runtime/vk_memory.c (the shadow section, the merge
record, vk_gpu_written_back, wb_lazy) and three one-word call changes in runtime/vk_usnap.c.

Without shadow storage (Windows outside Wine) the merge pipeline gains an unused fifth binding and two
push constants and nothing else changes. The Windows files compile; nothing was run, on Windows, Wine or
Linux.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:24:18 -05:00
chrg6
f97358ddc4 Give the recording thread a fast core and its sibling on Linux, and pick the thread that does the recording.
On Linux recorder_core reserved the last logical processor of the mask (an efficiency core on a hybrid
CPU) without its sibling, for the first thread to call vk_exec_record, and the first process-wide affinity
call took it back. plat_cpu_reserve there now takes the fast core that clocks highest with both of its
logical processors (none when fewer than four cores are fast), threads the holder starts get the other
processors, plat_process_affinity leaves the core with its holder, and a sweep every 300 presents moves
threads that inherited the core and gives it back once the holder has ended.

Shared code, so Windows changes too: the priority and the core go to the first thread that has spent half
a second in vk_exec_record (vk_exec.c rec_claim) instead of the first to call it, and the log names the
logical processors.

Pull request #358 by mooki000, taken as it is. The Windows files compile; nothing was run, and the Linux
code is not compiled here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:20:40 -05:00
chrg6
b2c5052ff5 Give Linux a memory limit that the low-memory handling can read.
Linux overcommits, so plat_commit_enforced was 0 there and nothing the runtime does when memory runs short
ever ran: no stale-texture drops, no idle or disuse eviction. plat_commit_info on Linux now reports the
limit with the least headroom of the cgroup v2 limits the process lives under (memory.max, memory.high,
against memory.current less its file cache), the machine's RAM (MemAvailable against MemTotal) and, with
vm.overcommit_memory = 2, the commit limit; a read is reused for 250 ms and the first one is logged. The
spare VRAM blocks stand down under low memory only where device memory counts against that limit
(plat_commit_counts_vram: Windows, and any integrated GPU). Windows behaves as before.

Pull request #378 by mooki000, taken as it is. The Windows files compile; the Linux code is not compiled
or run here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:20:03 -05:00
chrg6
c117cd8999 Set NVIDIA's shader disk cache on Linux only with NVIDIA's driver, in a folder that could be made and written, before any thread of the game starts.
The first part of this pull request (the cache beside the exe with an 8 GiB limit) was already in. This
is the rest: nothing is set without NVIDIA's kernel driver, neither variable is set when the folder cannot
be made or written (the driver caches nothing in such a folder), the log says which folder and limit hold,
and a game run sets the drivers' cache variables in main before any of its threads can load a Vulkan
driver (vk_device.c vk_driver_cache_env); the other modes still set them in create_instance. On Windows
that only moves the MESA_SHADER_CACHE_DIR setenv earlier.

Pull request #369 by mooki000, taken as it is. The Linux part is not compiled or run here.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:17:13 -05:00
chrg6
91a8da9eb3 Keep the previous picture on screen over the first frames after a DLSS or FSR 3.1 mode change, which came out dark or black.
Picking a mode in the settings menu changes the scene's size. The game makes its scene targets again at that size and
they start empty, and the first frames drawn into them are wrong: the first frame of the new size is lit without what
the frame before it left (a dark scene), and two frames later the scene can be black with the interface intact (seen
going to Ultra Performance and to DLAA). Captured over six scripted mode changes with every present saved: bad frames 3
and 5 presents after the change, the same with the lazy write-back on or off and with the frame hold off.

vk_dlaa.c notes a scene of another size within 60 presents of a settings change, and vk_backend.c frame_hold then
leaves out 6 presents from that frame on, once per change and beside the allowance for frames with skipped draws. This
hold also runs with DLSS Frame Generation on (the other one does not): a present left out is a longer gap between two
rendered frames to it, and a dark frame it is given comes out as several generated ones. frame_hold_ms = 0 turns both
off. Checked on a dev build with frame generation at 4x: the hold starts at the first frame of the new size at all six
changes and covers every bad frame of the capture, with no new Streamline error.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:05:29 -05:00
epicmeme546
7e23e7309b Copy a frame's uniform blocks at the submit call with the replay on its own thread, and say what that option can show.
With NX2NAVI_REPLAY_ASYNC the uniform snapshot was taken when the replay thread started recording a submission, up to a frame after the game submitted it. The game rewrites that memory without waiting for the GPU: in a graveyard the settings block of the shadow pass held another block's values in the frame its per-frame allocator moved on to the next stretch of memory, about every 364 frames. The submitting thread now takes the copy before it queues the submission (vk_usnap_take), and the replay thread takes it over and leaves out what GPU writes in flight touch (vk_usnap_begin adopt). A frame dump of such a frame shows the block as the game submitted it.

That frame still comes out dark with the option on: vertex, storage and index memory reaches the VRAM mirrors when the replay uses it, as late as the uniform blocks did, and the snapshot covers uniform bindings only. With the option off, 3,000 presents in a row were free of dark and odd frames in that graveyard and in a village; with it on, one frame in about 364 was dark. It gave 65.6 against 56.1 and 64.1 against 54.3 frames per second in those two places. The option stays off by default, and its menu text, the example settings file and the release notes now say that it can show a dark or flickering frame.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 06:04:14 -05:00
chrg6
b6beb72c8d Merge release 0.7.0 into the test line: version 0.7.0 and its notes, and GitHub main d1bebd3 (the previous picture kept on screen for a frame that lacks draws, the game's own VRAM in the overlay).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 05:38:34 -05:00
chrg6
9ecfdf1543 Merge GitHub main into the 0.7.0 release line: frames that lack draws are held back, and the overlay shows the game's own video memory.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 05:37:45 -05:00
chrg6
e473dd8826 Arm a lazily written range only when its mirror holds every CPU write to it, so a fetch no longer copies older mirror bytes over what the CPU wrote.
A fetch copies the mirror over the whole range, not the merge of the bytes the GPU changed that a write-back does. The
completion thread arms a range after its write-back reached guest memory; a CPU write into those pages in between, not
yet carried up by a sync of the mirror, was then overwritten by the mirror's older bytes at the first fetch. In play
that was single frames with another frame's constants: the night lighting missing from the whole scene in Hyrule
Field every 0.1 to 0.4 s, and a black scene in Kakariko, gone with wb_lazy = 0. Now the pages are made inaccessible
first and the back end then checks the CPU-write page generations against the mirror's last sync and the write-watch
bits nobody has read yet; when either shows a write the mirror lacks, the pages are given back and the range arms at a
later write-back. The lazy line counts the arms refused.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 05:37:14 -05:00
chrg6
69e7c59bcd Merge the cache memory branch: a large compute shader is built ahead only when a run has dispatched it, and the boot releases the shaders of pipelines it does not keep.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 05:24:58 -05:00
chrg6
bd9b48ff04 Keep a fault from releasing a lazily written range unseen while a part is handed over, merge what a part skipped and must write back after all, and leave the lazy write-back off on Linux unless set.
A review found a gap: a part checked what it had skipped at its end, and a fault between that check and the part's
hand-over to the queue fetched without the part's writes while nothing wrote them back afterwards. The replay now
opens a window from the check to the hand-over, per part, and a fault on an armed page waits for it to close (at most
20 ms; the replay thread's own faults and thaws do not wait and are counted). What a part skipped for a range that is
no longer armed goes back through the usual snapshot and merge, taken in that part's prologue, and not as a plain
copy, which would have put the mirror's words over what the CPU had just written there. A part split off earlier
makes the same check before its prologue. wb_lazy_touch is a test that reads armed ranges on purpose.

Dev build, Hyrule Field: 71.1 fps as before; standing, a fight, pause and unpause, and the touch test made 146 to 338
faults each, none inside a window, no fault of its own.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 05:23:43 -05:00
chrg6
314aea08b3 Let the background builder of large compute shaders always keep its pipeline again.
Only a shader a run dispatched reaches that builder now, so its pipeline stays, entered before its cache is merged, as before the usage record existed. The branch that destroyed an unkept pipeline before the merge could no longer be reached; had it been, a dispatch in that window would have found the pipeline in no table and in no cache and compiled it again.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 04:58:09 -05:00
chrg6
0f334310ec Write the first-dispatch statistics after the pipeline lock is released, and make the record of dispatched compute shaders safe to write from two threads.
Found by a review of the compute prebuild change:
- cf_log formatted and wrote its log line while holding the pipeline lock shared, on the autosave thread, which runs below normal priority; every dispatch needs that lock. It now copies the numbers and writes after the unlock.
- The record could be written by the autosave thread and by a save at exit at the same time, so the older copy could land on the newer file; and a failed write cleared the changed mark, so nothing tried again. One writer at a time now, the copy is allocated outside the lock a dispatch takes, and a failed write leaves the record marked.
- compute_keep read anything that was neither "all" nor a number as 0, which keeps nothing; it now reads as the default.
- The statistics called a pipeline "read from the pipeline cache file" when the driver said the pipeline cache held it, which is also true of what the same run built into the cache earlier. The lines now say the pipeline cache held it. The probe's skip line names the settings that also lead to it.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 04:56:26 -05:00
chrg6
f9f0505ed1 Build a large compute shader ahead only when a run has dispatched it, and release the shaders of pipelines the boot does not keep.
The 2 GiB of device memory a filled cache cost was not the thousands of compute pipelines but twenty of them: the compute shaders of 0.9 to 2.0 million SPIR-V words, the game's tensor-core upscaler programs, which nothing dispatches. A pipeline of one holds about 100 MiB of device memory from the moment it exists, and the driver keeps that memory when the pipeline is destroyed, so keeping only the recently dispatched pipelines did not help: the boot pass still created the twenty from pipeline-cache.bin at every start. Measured with --probe-prewarm on a copy of an installed copy's caches (RTX 5090, NVIDIA 621.01): the pass over all 4,066 compute shaders took the device memory from 386 to 2,398 MiB and the process's commit up by 2.5 GB; the same pass before the twenty were in the cache left the device memory at 386 MiB, and all 4,046 other pipelines kept at once cost 2 MiB.

A compute shader over NX2NAVI_LIB_PREBUILD_BIG is now built ahead, from the caches or by the background builder, only when the usage record says a run dispatched it. None of the twenty is among the 138 shaders eleven runs dispatched. Should the game dispatch one for the first time, that dispatch compiles it once and later boots build it ahead.

The boot also reads the shader of a pipeline it does not keep as a copy and releases it after the build, instead of leaving 3,900 shaders loaded (240 MB of commit); a first dispatch then reads its shader from the disk, 0.04 to 0.10 ms in the probe.

With both, the same pass on the same caches leaves the device memory at 386 MiB and raises the commit by 47 MB; 256 first dispatches after it took 0.13 ms on average, 1.8 ms at most, all read from the cache file. With compute_keep = all, which builds everything as before, the pass ends at 2,528 MiB. Not yet run in the game.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 04:53:00 -05:00
epicmeme546
d1bebd34cd Keep the previous picture on screen instead of showing a frame that lacks draws, and show the game's own VRAM in the overlay.
A draw whose shader or pipeline is still building is left out of its frame, and the frame was shown without it: a black or unlit picture with the interface intact when it was a lighting pass, a light going out, or ground missing for a frame. In a player's session a full-screen draw was skipped after its 50 ms and the frame came out black as a boulder hit.

The frame's present is now left out when draws were skipped (vk_backend.c frame_hold, NX2NAVI_FRAME_HOLD_MS, 120 by default, 0 off). The game runs on, so nothing waits. The hold comes from an allowance that fills again at an eighth of the clock's rate, so a long build or a run of them shows its frames as before and does not freeze the picture; a full-screen draw that would be skipped with the allowance spent waits on instead, 500 ms at most. Not with DLSS Frame Generation.

On a first walk through a village with no pipeline recorded, 21 of the 23 frames with skipped draws were held back; in the Lost Woods, 7 of 8.

The performance overlay: the VRAM line is the card's dedicated memory in use, which counts every program on it: a player read 14.5 GB as the game's while the game held 7.3 GB. The line's third cell now gives what this process holds on the device-local heaps (the driver's budget figure), in place of the GPU clock, which stays where the driver gives no budget.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 04:39:19 -05:00
chrg6
17c13e49ff Copy what shaders write into the game's memory back only when the CPU touches it, which takes Hyrule Field from 51 to 71 fps.
Standing in Hyrule Field the GPU spent 13 ms a frame, of which 2.4 ms were the game's passes and 7 to 9 ms the copy
of 66 MiB of shader-written buffers back into guest memory at the end of every submission, in case the CPU reads
them. The write-back probe found no CPU access to them in 40 s. Now a range goes back once and its pages are made
inaccessible; while they stay so, later writes stay in the mirror. The first CPU access faults, the bytes are fetched
with a GPU copy of their own after everything submitted so far, the pages are given back, and the range is written
back every submission again for a while (1 s, doubling to 32 s while it keeps being touched). Thaws before kernel
reads and writes and before mapping changes release armed ranges the same way, and so does a mirror that goes away.

Dev build, same spot, 80 s each: 51.5 to 71.0 fps median, 1% low 43.5 to 56.3, GPU time 13.1 to 7.5 ms a frame,
fence waits 9.8 to 4.4 ms. In that run the game faulted on armed pages 226 times and 124 fetches took 51 ms in all;
a walk into a fight made 283 faults and 186 fetches, and a test that touches eight armed ranges every 60 frames
(wb_lazy_touch) 480 faults and 364 fetches, none with a fault of its own. wb_lazy = 0 is the old behaviour.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 04:36:46 -05:00
chrg6
1b9016896a Say where the boot's list of compute shaders comes from: mostly the shader preparation, not play.
An installed copy's warm list has 42,344 variants, 42,142 of them from shader-prepared.bin, and its 4,066 compute shaders are what the boot kept pipelines for. The comments and the settings text said the list grew with the play history; a copy with prepared shaders held the 2.3 GiB from its first boot. Comments, docs and the ini text only.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
(cherry picked from commit ea984fe05b995c5dad1e0f49c5f44de9ee8f19b2)
2026-11-10 03:34:03 -05:00
chrg6
1567ff8df4 Compile the boot's compute pipelines below normal priority, and raise the thread when a dispatch waits for its shader.
After an update or a driver update every recorded compute pipeline is compiled again in the background: about 140 ms each on an RTX 5090's driver, so minutes of two threads for a long play history. Those compiles ran at normal priority, because a dispatch of a shader being compiled waits for that build and an idle-priority compile under load had held such a frame for seconds. On a CPU with few cores that put two more threads in equal competition with the game's own.

The compile now runs below normal priority, and the dispatch that comes to wait for it raises the thread to normal, as it already does for the background builder of large compute shaders. Not measured in play.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
(cherry picked from commit e2b38ffb22690b1656d22fbc504d000554877e0d)
2026-11-10 03:34:03 -05:00
chrg6
61a13c62b9 Keep only the compute pipelines of recently dispatched shaders from the boot, and build the others into the pipeline cache without keeping them.
The boot prebuild built the pipeline of every compute shader play ever recorded and kept all of them for the process. A pipeline that exists holds driver memory whether or not anything dispatches it: with a history of 4,066 compute shaders they held 2.3 GiB of device memory, and its share of the process's commit, from the title screen on (RTX 5090, NVIDIA 621.01), while a boot into the first village dispatched 95 of them.

The boot now keeps the pipelines of the 512 compute shaders dispatched most recently (compute-used.bin next to pipeline-keys.bin records which run last dispatched each; the setting is compute_keep, with "all" for the earlier behaviour). Every other one is still built at boot, so that the pipeline cache holds it after an update or a driver update, but destroyed at once, and created from the cache at its first dispatch. A dispatch that comes while such a build runs gets that build's pipeline.

Each boot stage now logs the device memory and the process commit it leaves ("mem: boot stage"), and the log says what the first dispatches cost. nx2navi.exe --probe-prewarm runs these stages without the game from the caches next to the executable and times first dispatches of pipelines the boot did not keep: 256 of them took 0.19 ms on average and 3 ms at most, all read from the pipeline cache file, and 372 pipelines built and destroyed at boot left the device memory where it was.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
(cherry picked from commit 16a796d623686bca5304eaf1b29981247453a413)
2026-11-10 03:34:03 -05:00
chrg6
9a22bea0f0 Merge the shader headers branch: the runtime keeps its shaders as source and builds the SPIR-V headers when the game is built.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 03:33:21 -05:00
chrg6
fa29f3fea5 Merge the second PR intake pass: anisotropic filtering in the Screen tab, the X3D die choice, the NVIDIA shader cache limit, the NGX core search and other fixes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 03:32:46 -05:00
chrg6
417fbcf5ff Merge the memory report branch: the device address table gives empty blocks back, and textures give way before VRAM mirrors are refused.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 03:32:30 -05:00
chrg6
2a9efee4c5 Merge GitHub main into the test line: the launcher's customisation, the settings and sound changes, and the warm stage-library cache.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 03:32:30 -05:00