Commit Graph

54 Commits

Author SHA1 Message Date
epicmeme546
e38f42a959 Test for NaN on the bits of the number on AMD's driver for RX 5000 and 6000 cards, so that no shader compiler can leave a test out.
The reports of black and white blocks on Navi, on Link next to her and on bright surfaces seen from inside a house come from RX 5000 and 6000 cards, whose Windows driver compiles with "AMD proprietary shader compiler" (vk_caps.amd_sc); an RX 7900 XT (LLPC) draws the same scenes clean. The game's shaders test for NaN with OpIsNan in 48,717 of an install's 54,959 translated modules, 26 tests each on average, and the translator's guard that keeps NaN out of every float colour output, so that one bad texel does not spread through blur and bloom into blocks, is such a test too. SignedZeroInfNanPreserve asks the driver to keep those tests; whether that compiler does is not known.

With that driver, vk_pipeline.c spirv_nan_bits now turns every 32-bit isnan, scalar or vector, into (bits & 0x7fffffff) > 0x7f800000 on the number's bits, and a float select with a constant whose bits are a NaN into a select of the bits (issue #156), when the module is created. NX2NAVI_VK_NAN_BITS=1 does it on every driver, 0 on none. Run over every module of an install's shader cache, the rewrite changed 1,281,675 tests and 57 selects with every output well formed (each id defined once, below the bound, the uint types declared once); --selftest checks it on a small module, and Link's house with it forced on (RX 7900 XT) draws as without it. Not yet tried on an RX 5000 or 6000 card.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 13:08:03 -05:00
chrg6
0e16e58cf3 Merge the shader stutter fixes into the combined test line.
Eight commits: a draw that misses its pipeline has the rest of its submission read ahead, the library workers link
the pipelines of skipped draws, a pipeline whose fragment shader reads a target of its own pass is fast-linked like
any other, and diagnostics. The merge was clean. Their before and after matrix had not finished when this was merged.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 11:05:17 -05:00
chrg6
fdf2fb89d3 A draw that misses its pipeline has the rest of its submission read ahead, and the stage libraries of the pipelines the later draws need are queued at once.
The next draw with a new pipeline was only found when the replay reached it, so the draws of an area's first frame,
or of a turn that brings several new materials into view, paid for their pipelines one after another while the
workers that could have built them together sat idle. The submission is recorded before it is replayed: the first
draw of a submission that finds a shader or pipeline missing now has the ops after it read (vk_exec.c vk_exec_ahead)
with the binds that decide a draw's shaders and shader libraries applied to a copy of the replay state. Each draw
there looks its shaders up as the real draw will, which also queues a shader that is not in memory, and names its
state to vk_pipeline_hint, which queues the pre-rasterization and fragment shader libraries that are missing. No
pipeline is entered and no key recorded, so a wrong guess costs two libraries at most. The draw's own lookup then
links on its thread when both libraries are there.

On a first visit to Kokiri Forest a scan read 6,900 ops in 0.78 ms on average (the longest 5.5 ms; a scan ends
after 3 ms), and the scans of the load and the walk named 377 states without a pipeline and queued 104 libraries
for them.

pipe_ahead = 0 (NX2NAVI_PIPE_AHEAD) turns it off.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 10:00:20 -05:00
chrg6
b121f90e41 The library workers link the pipelines of skipped draws, so a burst of new materials is linked on several threads instead of by the one pool worker that is not inside an optimised build.
A draw that is skipped while its pipeline builds leaves the pipeline to the pool: a job is fast-linked first and goes
back in the queue for its optimised build. The pool keeps one worker out of optimised builds; with the other three
inside one (100 to 350 ms each) that worker linked every new pipeline of a burst one after another. The library
workers, which so far served only draws that wait, now take the fast link of a draw-queue job too (vk_pipeline.c
fast_take, lib_worker), and there are as many of them as pool workers (four on sixteen logical processors, two
before).

Measured on a first visit to Kokiri Forest (RTX 5090, libraries in the driver's cache): of the 444 pipelines draws
missed, 180 took over 50 ms to become usable, the longest 1.3 s, and their draws were missing from every frame until
then. With this change and the two beside it (feedback loops, the look-ahead) 23 did, 19 of them mesh pipelines,
which have no fast link.

pipe_fast_workers = 0 (NX2NAVI_PIPE_FAST_WORKERS) gives the old behaviour.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 10:00:19 -05:00
chrg6
1d9b0dc962 A pipeline whose fragment shader reads a target of its own pass is fast-linked like any other: the feedback loop flags are part of the fragment output library.
Such a pipeline (soft particles and water reading the depth buffer, full-screen passes that read the target they
write) had no fast link: gpl_link refused it, so its draws were skipped during, or waited for, the whole optimised
build. The flags belong to the fragment output state alone, so the fragment output library carries them and its key
names them (FoKey.fbl); the shader libraries are the ones the same shaders use without a loop.

Measured on a first visit to Kokiri Forest (RTX 5090, stage libraries in the driver's cache, DLSS Frame Generation
on, where no frame is held back and a full-screen draw waits on): full-screen draws of such pipelines waited 267, 42
and 61 ms in the area's first frame and 410 ms in the middle of the walk; fast-linked they wait 2 to 3 ms.

gpl_feedback = 0 in nx2navi.ini (NX2NAVI_GPL_FEEDBACK) gives the old behaviour.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 10:00:19 -05:00
chrg6
eeeeec683b The pipeline statistics say how long a missed pipeline took to become usable and which stage libraries were slow, and a draw counts as skipped for its pipeline only when it was skipped.
- Every pipeline a draw missed is timed from the miss to its first usable pipeline, the fast link or, without one,
  the build itself (vk_pipeline.c ready_note): the gpl lines of a save give the counts under 4, 8, 17, 50 and 150 ms
  and over, the average, the longest, and how many had no fast link. That time is how long the pipeline's draws were
  missing from the picture or waited.
- The stage library lines add the libraries of 25 ms or more and their sum, and the pre-rasterization libraries that
  had outputs added for their fragment shaders: those are another module than the one the preparation built, so the
  driver's cache has none of them.
- "a draw waited" lines name a pipeline with a feedback loop.
- The "draws skipped for a pipeline" counter (overlay, perf lines, flight records) was raised by every lookup that
  found the pipeline building, also when the draw then waited for its link and was drawn. It is raised where the draw
  is skipped now (vk_exec_draw.c draw_skipped).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 10:00:18 -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
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
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
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
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
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
DeepDaddyTTV
53ae6c192e Stop scanning shader instructions after descriptor declarations have been read. 2026-11-10 01:55:26 -05:00
epicmeme546
e10ef60fd5 Keep the driver's cache of stage libraries warm, link a missing pipeline instead of skipping its draw, and count the texture cache's waits in time.
The preparation builds every stage library once so the driver's disk cache holds it and a library a draw needs later takes under a millisecond. Turning dynamic vertex input off for AMD's RDNA 3 and newer driver changed the dynamic states every library lists, which gave each one another entry in the driver's cache, and nothing built them again: an update carried the prepared shaders over without the driver step. On an RX 7900 XT (26.10.1) all 42,142 prepared libraries were cold, 93 ms a vertex and 242 ms a fragment library on average. With no pipeline recorded, a walk through a village skipped 11,180 draws while their pipelines built and made 94 draws wait 5.5 s in all, four of them 1.0 to 2.0 s; a player's session log shows up to 114,834 draws skipped in 600 frames and 181 waits of 251 ms on average. Skipped ground and walls appear and disappear, and a skipped lighting pass is a black frame with the interface intact.

- The game checks the driver's cache at every start (vk_pipeline.c lw_start): a sample of the prepared fragment libraries is built, and when their median time says the cache is cold the whole prepared list is built into it again on idle-priority threads while the game runs. shader-warm.txt records a warm in progress, so the next start goes on with one a run ended, and stops the tries on a driver that does not keep the libraries. This also covers a driver update and a cache the driver emptied.
- An update that carries the prepared shaders over runs the game's --warm-shaders (tools/make_game.py warm_driver_cache): 11 s with the libraries there, about 8 minutes with all of them cold on that card.
- A draw whose pipeline is missing waits for its fast link from a budget of 6 ms a presented frame, 3 ms at most each (NX2NAVI_PIPE_LINK_MS), before it is skipped: with warm libraries the link is done within that.
- Full-screen draws wait from their 50 ms budget again instead of being skipped (NX2NAVI_PIPE_SKIP = any is the default; fullscreen stays selectable). With warm libraries the wait is a millisecond.

The same walk afterwards: libraries 0.3 and 0.7 ms on average, 1,605 draws skipped, 1,473 of them in the scene's first 600 frames and 8 to 80 in each 600 after, and 19 waits of 60 ms in all. First visits to four other saves (a mountain pass, the Lost Woods, Kokiri Forest, a river) waited 12 to 84 ms in all except the Lost Woods, where mesh shader pipelines, which have no stage libraries, and vertex libraries that need added outputs still compiled once: 23 waits, 2.1 s in all, the longest 776 ms.

The texture cache counted its waits in presents chosen at 60 a second: at 165 presents a second the 1800 that stood for thirty seconds were 11 s, so a released render target went sooner than meant and a texture out of view for 11 s was retired and showed its stand-in for some frames when it came back. The counts are now taken times the present rate over 60 (presents_for), and a texture is retired after two minutes without a sample instead of thirty seconds.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 01:36:29 -05:00
chrg6
00f06e669e Fix nine runtime faults a tester's report named: a stack overrun on mesh draws, lost YMM halves on preemption, and seven more.
- The mesh stage's storage table starts 0x90 bytes before the end of the 2 KiB constant bank, and all sixteen slots
  were written: 0x6C bytes past a stack buffer on every mesh draw. It holds the nine slots that fit.
- The prebuilt runtime is compiled without AVX, so its preemption stub saved only XMM0-15 while the lifted code of
  an AVX2 processor keeps data in the upper YMM halves, which the stub's callees may clear. Both bodies are built
  now and the one for the processor is chosen at the start.
- After an FSR 3.1 frame generation error the window's swapchain was still AMD's object but went to the plain Vulkan
  calls. Swapchain calls follow whose swapchain it is, and a failure takes it down as a switch in the menu does.
- A movie is paced at its own 60 fps under a lower limit too: at 40 fps it ended 25 s behind its sound.
- A lost device left the wait for an upload spinning for good; it ends the run with the device's report.
- The compute pipeline key had four bytes of padding that were hashed and compared, so a prebuilt pipeline could be
  missed and built again.
- A thread's TLS pointer was published before the TLS was allocated, so the slot was always 0.
- A fatal exit puts RivaTuner Statistics Server's profile back, and an ini saved as UTF-16 is read.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-09 21:54:40 -05:00
chrg6
a87f6e1bd6 Merge the test line's texture retirement fix into the combined branch.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-09 21:27:08 -05:00
chrg6
22103a57bf Merge main into the test line: the pull requests taken there and two render target fixes.
Main brought the fixes of eleven pull requests (the texture pool set sealed when an early replay part is submitted, every location reflected in interface arrays, RGB9E5 texels recognised for integer storage views, the upscaler a frame started with kept, GPU pass timestamps without vendor breadcrumbs, the Linux build, window and NGX fixes), render targets released when drawn over at another address, the vertex layout kept in the pipeline on newer AMD drivers, and the upscaler choice read once per evaluation.

Four hunks conflicted and take both sides: pool_sync returns for a sealed set before the per-frame creation budget's clock (vk_exec_draw.c); make_module keeps the test line's early_ok argument and main's module hash (vk_pipeline.c); a texture taken back counts as sampled again and records how long it was away, and the texture line logs the disuse counters and the overwritten render targets (vk_texture.c).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-09 21:10:23 -05:00
chrg6
f1127f8be9 Retire textures evicted by disuse before freeing them, take them back on any use, and add tex_disuse = 2 to tell the freeing from the marks.
0.6.1.14 faulted the GPU (a read of an invalid address in a pass) about 30 seconds after its last disuse evictions, and
no path by which an evicted image is still read was found in the code. An evicted texture is now first retired: the
pool refresh gives its slots the stand-in while the image stays whole. It is destroyed only once the texture pool has
taken every set of its ring since and the GPU has finished the submissions recorded until then, so no pool set can
still be bound with its view. A mark on one of its slots or any lookup outside the pool refresh takes it back as it is,
and the perf line counts those, which shows whether the marks miss a real use. tex_disuse = 2 retires and never frees,
so the next fault can be put on the freeing or on the marks and stand-ins.

The registration shortcut also read a slot's cached entry without checking that the resolution was current, so it could
read the record of a destroyed texture; it now checks the slot's generation first.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 4c5b2ae2e030ab00a910d8f071c030e610fd78e1)
2026-11-09 21:09:33 -05:00
chrg6
0703cfa944 Mark the texture pool in SPIR-V 1.4 to 1.6 shaders too, and name in the log each shader the marks cannot take.
The translator's mesh shaders are SPIR-V 1.4, and the marks took only 1.3, so the first mesh shader that indexed the
pool turned eviction by disuse off for the whole run. From 1.4 on an entry point lists every global variable it uses,
so each entry point now gets the marks variable too. Over the 44,255 shaders of a test install's cache, 4,728 are
marked, none is refused, and every marked one passes spirv-val for Vulkan 1.3; 11 of them are 1.4 mesh shaders. The
log names up to eight refused modules by stage, SPIR-V version, size, hash and reason.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit af50808a1cb56f450f99938c9d420e1f5deb333b)
2026-11-09 20:45:04 -05:00
epicmeme546
76c3661aff Keep the vertex layout in the pipeline on AMD's RDNA 3 and newer driver, and save the pipeline cache while a large compute shader builds.
AMD's driver for RDNA 3 and newer compiles a pipeline that has dynamic vertex input again at every boot: neither pipeline-cache.bin nor the driver's own disk cache gives it back. On an RX 7900 XT (26.10.1) a player's key file of 3,979 records used the whole 20 s boot budget at every boot. Dynamic vertex input is now off by default on that driver (vk_caps.amd_llpc); with the vertex layout in the pipeline the third boot of that file built 4,273 pipelines in 0.9 s, all from the file. NX2NAVI_VK_DYN_VERTEX=1 turns it back on. The RDNA 1 and 2 driver branch is not measured and keeps it.

The background builder of large compute shaders now compiles into a pipeline cache of its own and merges it into the main one when the build is done. A create into the main cache holds the cache's lock for its whole length and the cache is only saved while nobody holds it, so a build of minutes kept pipeline-cache.bin from being written at all: on the same card one compute shader of 4,874,502 SPIR-V words was still compiling 590 s after the boot, and nothing built in that session reached the file.

NX2NAVI_PIPE_FEEDBACK=2 also logs every graphics pipeline build with hashes of its modules and its fixed state, which is how the recompiles were found.

Co-Authored-By: Claude <noreply@anthropic.com>
2026-11-09 18:17:12 -05:00
chrg6
dc9f164afc Evict textures no shader sampled for 30 seconds while video memory or the system's commit runs low.
The texture pool refresh looks up every registered slot, so the textures of every area the game keeps loaded never
counted as idle and their memory only grew. Marked shaders now store into a buffer with one word per pool slot. Every
four submissions that recorded work, the replay copies it out and clears it, and the texture side notes when each
texture was last sampled. Under VRAM pressure or low commit, once idle textures are gone, live textures that come back
intact and were not sampled for 1800 presents go too. Their keys are held, so the pool refresh keeps the stand-in until
a shader samples that slot again, and the next refresh makes the texture again.

Fragment shaders that neither discard nor write depth, sample mask, stencil reference or memory keep early depth tests
(EarlyFragmentTests), so the marks do not take away early depth rejection. Alpha to coverage leaves the dynamic state
while marks are on, so each pipeline knows whether early tests are safe. Disuse eviction waits until every module that
indexes the pool was marked and two reads arrived. NX2NAVI_TEX_DISUSE=0 (tex_disuse = 0) turns it off.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 1a4c896150a748f9275c3024e96af3055db94af4)
2026-11-09 14:39:07 -05:00
chrg6
d016a6dc86 Mark the texture pool slots that shaders index, for eviction by disuse (work in progress: not built; the runtime side follows).
vk_pipeline.c spirv_pool_mark gives each module that indexes the texture pool a storage buffer at set 2, binding
VK_POOL_MARK_BINDING, and a store of 1 into the slot after every access chain into a pool texture array; modules that
cannot be marked are counted in vk_pool_marks_missed. NX2NAVI_SPV_MARK_TEST=<list> runs the rewrite over files for
spirv-val under --selftest. Still to do: the marks buffer and its read-back (vk_exec_draw.c), the pool lookup context,
the holds and the eviction by disuse (vk_texture.c).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
(cherry picked from commit 7ae86070f166d935a9949e95dae7a95e2cf3272b)
2026-11-09 14:39:07 -05:00
epicmeme546
5cb85adb45 Stop the fog leaving dark trails behind nearby objects.
The fog's first compute pass skips froxels behind a coarse depth table from the previous frame and writes them as empty, so the columns a near object had just left came out with no fog, and the fog's history smeared that into a trail, worst at the screen edges. The comparison is now never true, so those froxels are computed. The shader is found by its shape, so this holds across translator updates. NX2NAVI_FOG_CULL=1 keeps the game's skip.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 12:45:14 -05:00
epicmeme546
0379b003c1 Stop the fog leaving dark trails behind nearby objects.
The fog's first compute pass skips froxels behind a coarse depth table from the previous frame and writes them as empty, so the columns a near object had just left came out with no fog, and the fog's history smeared that into a trail, worst at the screen edges. The comparison is now never true, so those froxels are computed. The shader is found by its shape, so this holds across translator updates. NX2NAVI_FOG_CULL=1 keeps the game's skip.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 12:35:12 -05:00
twisted89
417d1a3740 Keep the pipeline cache save from copying the cache while pipelines are built into it.
Intel's driver crashed in vkGetPipelineCacheData when the
autosave copied the cache while the replay thread and the library workers were building
pipelines into it. Builds now hold a shared lock while they build. The save only copies
when it can take that lock exclusively with no build running, so it never makes a build
wait. The autosave tries again on its next tick; the save at exit waits up to 5 s.
2026-11-09 12:18:17 -05:00
chrg6
66927b8f94 Ask every driver but NVIDIA's to keep NaN and infinity in the game's shaders, which should bring Navi's orb back on AMD GPUs.
The game's shaders rely on IEEE NaN and infinity results: unordered comparisons compile to x > c || isnan(x), a
zero-length normalisation gives an infinity that a later test catches, integer masks travel through float selects,
and the translator's own NaN guards are isnan tests. Our SPIR-V never declared SignedZeroInfNanPreserve, which lets a
driver assume floats are never NaN or infinite. NVIDIA's driver keeps the IEEE results anyway; AMD's compilers do not
(issue #156: a NaN-bit select read as a signed integer gave 2^32; #41 and #110: black and white blocks on Navi and on
Link next to her). The player report: AMD GPUs draw Navi's sparkles but not her orb, whose light sits at her own
centre.

vk_pipeline.c spirv_nan_preserve now adds the capability, SPV_KHR_float_controls and the mode for 32-bit floats (16
and 64 where the module declares them and the driver can) to every game shader module. NX2NAVI_VK_NAN_PRESERVE: unset
on every driver except NVIDIA's own, 1 everywhere, 0 off. --selftest checks the rewrite; the rewritten modules of 600
translated game shaders pass spirv-val for Vulkan 1.3. Not yet seen on an AMD GPU.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 11:17:08 -05:00
chrg6
dfc5b90b59 Fix what the 0.6.0 review found, and ship DLSS Frame Generation in the launcher release.
The commit census of the perf trace walked the address space on the presenting thread outside mem_census, which
brought back the hitch mem_census was added to remove; it now runs only with mem_census = 1. DLSS's output pass at
the mode's share fell back to no pass at all when the scene was not at that share (the first presents, a dynamic
resolution step): after such a frame the first pass wider than the scene is taken again for 120 frames. The launcher's
nx2navi.ini editor no longer rewrites a file it cannot read, keeps the byte order mark and bytes that are not UTF-8,
reads an empty line as the game does, and leaves no temporary file behind. The build kit carries the two modules
build_game.py imports on Linux, the Linux steps list the right packages and Python, and stale comments and notes are
corrected (Discord on by default, two prebuild threads, Enhanced HDR gone).

DLSS Frame Generation needs nx2navi_dlssg.dll, NVIDIA Streamline's runtime and nvngx_dlssg.dll beside the game, which
no release carried, so the menu offered it and the game turned it off. tools/make_launcher.py --dlssg and --streamline
put them with their licences and a notice in the release's bin/dlssg/, and tools/make_game.py place_dlssg copies the
whole set beside the game. THIRD_PARTY_NOTICES.md has the row; the notes and README say RTX 40 and 50.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 09:10:36 -05:00
Tyler
032f59bb44 Build the boot library prebuild on two threads by default instead of half the CPUs
Sixteen builders on a 32-thread CPU spent about eight cores spinning on NVIDIA's driver lock and never finished the list
in a session; the ini text also said a quarter of the CPUs while the code took half.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HtayeqEG2x5woYzWuEQBGV
2026-11-09 08:16:25 -05:00
chrg6
fe3cca739b Keep compiled pipelines as pipeline binaries under the runtime's own keys, and let the one-shot draw wait be set.
NVIDIA 621.01 reuses a pipeline-cache.bin entry only in the executable that wrote it, so every renamed or updated exe
compiled all of its pipelines again (23 s boots, 17 % read from a 470 MB file). With NX2NAVI_PIPE_BINARIES=1, where the
driver has VK_KHR_pipeline_binary, every pipeline, stage library and compute pipeline is looked up by its driver
pipeline key in pipeline-binaries.bin and made from the stored binaries; anything not stored is compiled once with its
data captured and appended. Each binary is stored once under its own key: nearly every graphics pipeline carries the
same 2 MiB binary, which made a first version of the file 7 GB. pipeline-cache.bin is not used while this is on. The
knob is off by default while it is being tested; NX2NAVI_PIPE_BINARIES_MAX_MB caps the file.

NX2NAVI_ONESHOT_WAIT_MS sets how long a draw into a target the previous frame did not render waits for a pipeline built
for the first time before it is skipped; the default keeps the old 30 s.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 08:09:26 -05:00
chrg6
b0d420db3d Land the shader and pipeline stutter pass, and the fixes it needed.
Large compute shaders that no cache holds are built on one background thread after the boot prebuild, smallest first, so their first dispatch no longer compiles them on the replay thread. NX2NAVI_BIG_BUILD_MAX_MB stops that builder once the process has grown by that much: on a 31 GB machine one of these shaders took the process up by 12.8 GB and the game stuttered while Windows paged. The builder takes the queue under its lock and copies each entry out before compiling it, so a shader queued meanwhile cannot free the arrays under it. The same change reports what pipeline-cache.bin gives back, and starts over when the file grows past NX2NAVI_PIPELINE_CACHE_MAX_MB.

A tensor-core program is now tested before its shader is asked for, in both dispatch paths. It runs the stand-in while NX2NAVI_NATIVE_TENSOR is off, and translating it anyway recorded four AI-upscaler shaders of 0.87 to 4.4 million SPIR-V words that this game never dispatches natively. Process memory went from 29.3 GB to 24 GB and the multi-gigabyte builds during play are gone.

The frame-time summary says which part a slow frame went to, and with NX2NAVI_REPLAY_TIME how the replay splits between draws, binds and transfers; NX2NAVI_SVC_SLOW_MS logs the kernel services that block, with the thread they blocked on. prof_report.py reads the map this build writes and adds the image base to a runtime Rip, so a profile resolves to function names instead of question marks.

build_xlate.py applies the patches with GIT_CEILING_DIRECTORIES set to the build folder's parent. Inside a checkout git read 0021-prmt-byte-permute.patch's paths from the repository's top, skipped every file of it and still exited 0, so PRMT was missing from locally built translators and every byte permute was a no-op. A Skipped patch line now fails the build. The note in AmpereLowering.cs that said the translator emits nothing for PRMT is corrected.
2026-11-09 03:34:46 -05:00
chrg6
1f7e9c975b Speed up the replay and fix what the perf pass found, and add a frame capture key for chasing rendering faults.
Performance: draws reuse the bindings that did not change and record only the dynamic states that differ from what
the command buffer holds; small uploads come from a staging arena; finished submissions are held briefly and handed to
the queue in batches; the recorder thread can keep a CPU core of its own; ASTC block-linear textures are deswizzled on
the GPU; dynamic resolution steps the upscaler mode to hold a frame-time target. Each has a setting in nx2navi.ini
(bind_reuse, dyn_delta, stg_arena, submit_batch, recorder_core, recorder_prio, astc_gpu_deswizzle, dyn_res) and the
staging cache now frees what it holds at shutdown.

Capture: NX2NAVI_DUMP=key saves the frame after each press of Insert, with mesh draws listed by task, mesh and fragment
shader, depth test and face culling, and mesh_prims.txt giving each mesh draw's primitive, clipping and fragment counts.
All of it is off unless NX2NAVI_DUMP is set.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 03:34:46 -05:00
chrg6
3bb2ee71f9 Run guest shaders that use subgroup operations with maximal reconvergence when the driver supports it.
Guest code runs ballots and shuffles where the guest compiler had the warp reconverged, for example right after a loop
each lane leaves at a different iteration. Vulkan only promises that with VK_KHR_shader_maximal_reconvergence, so
the pipeline code adds the extension and the MaximallyReconvergesKHR mode to every module that declares subgroup
capabilities. vk_reconverge = 0 in nx2navi.ini turns it off.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 03:34:46 -05:00
Claude
b1421faaf9 Show Prepare the Shaders moving in the launcher: the game prints its counts and the step sends them on.
The step sat at 0 % until it was done, an hour on some PCs, because nothing it ran reported progress to the launcher. nx2navi.exe --prepare-shaders now prints how many shaders it has translated and how many it has built into the driver's cache every 2 s. make_game.py reads them as they come and fills the bar, the translation the first half and the build the second, with the counts in the step's text. An event every 10 s keeps the text current while nothing is printed, and after 3 minutes without a count moving it says so, and that the step is still running.

The selftest draws the step as a tenth screen. Its made-up update was version 0.3.11, so from 0.4.0 on the update-ready screen showed Up to Date and was no longer drawn; it is now a minor version past the launcher running it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BSHQpLnScF9sNv4LNAaaS3
2026-11-09 08:32:13 +00:00
epicmeme546
754ded99e0 Raise the frame rate in Kokiri Forest and apply more settings during a run.
The foliage's sun shadows took most of the GPU time: one mesh draw shaded about 1,000 million fragments in the far cascade. The far cascade now shades them at a 2x2 rate, and the two far cascades drop one side of the double-sided cards. At the forest entrance the frame rate went from 18 to about 43 fps on an RX 7900 XT.

FSR 3.1, its frame generation and the console mode now take effect without a restart. The full performance overlay lists the settings shown in the options menu.

NX2NAVI_GPU_PASSES times each pass and counts its fragments, and NX2NAVI_SET_AT changes settings at a given frame for test runs. Both are off by default.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 02:40:51 -05:00
chrg6
2cd6f5290b Leave the boot prebuild's huge compute shaders to their first dispatch, so memory no longer climbs to 30 GB at the title screen.
Four play-recorded compute shaders of 0.87 to 4.4 million SPIR-V words (the game's tensor-core upscaler passes, which run through the stand-in here) are recorded and so prebuilt at boot. The driver spent minutes and gigabytes on each, four at once, none finished, and every start began again until RAM ran out and the screen went black. The boot prebuild now creates a compute shader over 512K words only from a pipeline cache (VK_PIPELINE_CREATE_FAIL_ON_PIPELINE_COMPILE_REQUIRED_BIT) and leaves it to its first dispatch otherwise. NX2NAVI_LIB_PREBUILD_BIG=<words> sets the limit, 0 the old behaviour. From a tester's fixes: memory flat at 13 GB on the title screen, prebuild done in 463 ms.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 15:51:48 -05:00
chrg6
9a8f74fe53 Refresh read-back ranges in the VRAM mirror, guard the boot pipeline prebuild against driver crashes and count out-of-order event waits.
Small ranges the game invalidates and reads back (the exposure meter) are copied from guest memory into the mirror at every submission that uses their pool, so a CPU write made between recording and the GPU's run is not lost; NX2NAVI_READBACK_SYNC=0 turns it off.

While the boot builds the recorded pipelines a marker file exists next to the pipeline cache. A start that finds it left over records the GPU and driver in pipeline-prewarm-skip.txt, and starts on them build those pipelines at their first draw instead.

CommandBufferWaitEvent is now recorded as OP_WAIT_EVENT. The replay waits for nothing but counts the waits it reaches before their signal, and how many submissions later that signal comes, in the NX2NAVI_TRACE=gfx frame line.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 15:51:47 -05:00
chrg6
092379def8 Frame dumps keep each shader's guest program, and a test switch runs an edited SPIR-V in place of a compute shader.
NX2NAVI_DUMP writes sh_<hash>.code next to sh_<hash>.spv: the guest program the shader was translated from, as its
stored inputs hold it, for a disassembler (a compute program as it is, a graphics stage after its 128-byte header).
NX2NAVI_SPV_OVERRIDE=<dir> runs <dir>/<hash>.spv in place of the compute shader whose SPIR-V has that hash, an edited
copy with the same interface, to look at a shader's intermediate values in a frame dump.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 04:10:35 -05:00
chrg6
8daedbd806 Redraw the in-game menu with the game's own interface textures, and bring in the launcher's save import and faster builds.
In-game menu: the settings window, its tabs, rows, buttons and cursor, the performance overlay and the Preparing
shaders box are drawn with the game's interface textures where the RomFS holds them (runtime/ui/menu_skin.cpp,
perf_panel.cpp; plain shapes until they are decoded). Restart joins Continue and Quit, each behind a confirmation;
VSync is an on/off switch; DLSS is listed only on NVIDIA GPUs; the menu sounds are quieter; Picture shape is gone and
the setting descriptions are shorter; edge cases of input, layout and fonts are fixed. tools/menu_preview.py draws the
menu without the game.

Launcher: Import Saves takes a save from the game folder's saves/ folder or one the player picks; downloads fall back
to Windows' own certificate check when Python's refuses a server; updates are faster; the title bar is drawn in the
window and Navi is every icon. tools/make_game.py builds with CLANG64's clang where the launcher installed it, packs
the RomFS beside the lift and the compile, takes a prebuilt runtime, and compiles the game's resources without cmd.exe,
so a user folder with a space in its name builds.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 03:57:01 -05:00
chrg6
e884abc226 Build a waiting draw's shader libraries and fast link on two library workers, so the drawing thread never compiles.
A draw that waits for its pipeline used to build a library itself when every pool worker was busy (16 times in a cold
run, up to 77 ms; once in a warm run, 97 ms). Two workers now take only those jobs, wake on their own condition so a
pool job's signal always reaches a pool worker, and run the fast link too; the drawing thread only waits.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 17:36:21 -05:00
chrg6
501d5bd084 Release pass: fix crashes, freezes and races, cut VRAM use, and translate more shaders.
Crashes: the render-target heap (HeapDef DynamicTextureAllocatorMem and its parent) grows with the widescreen
picture, so the pause menu no longer reads a null block at 5120x2160; texture uploads keep the game's memory mapped
while they copy it, so UnmapPhysicalMemory no longer pulls it away mid-copy; DLSS Frame Generation no longer crashes
in Streamline's set-up (physical devices and the window surface go through its proxies, its swapchain images are
counted first, resources are tagged per frame); a stale core-wait target is cleared before its thread is freed.

Freezes and races: a resize during a swapchain rebuild is kept, a failed frame generation swapchain is retried
instead of replaced by a plain one, three acquire timeouts in a row rebuild the swapchain, device waits take the
queue lock, a translator child that stops answering times out, an in-flight compute pipeline builds at normal
priority, a save Commit started before the window closes finishes and none starts after, a settings change just
before closing is saved, and a movie sample taken before a flush is dropped.

HDR: Enhanced HDR extends the game's own tonemap so highlights go above the picture's white (the hue slider,
which no longer applies, is gone from the menu); frame generation gets a HUD-less picture, the HDR flag and the HDR10
metadata under HDR too.

Memory: ASTC textures are encoded to BC3 unless the PC has 20 GiB of VRAM and 48 GiB of RAM, as Windows charges video
memory to the commit charge (a long session held 17 GiB of RGBA8 textures and 45.7 GiB of commit on a 32 GiB PC).

Shaders: the translator lowers spill-mode programs with more than eight uniform register groups in a wider spill
layout, and local loads and stores with a uniform-register address (36029 of the game's 36031 variants translate,
20 failed before).

The launcher release ships the shader tools and AMD's FidelityFX library (make_launcher.py --ffx); windres there gets
the toolchain on PATH.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 16:02:30 -05:00
chrg6
1d7bc90848 Fix shadows, colour writes and present pacing on drivers that read Vulkan's undefined cases differently.
A depth-compare read through a sampler whose compare is off now gets the slot's comparing sampler, as the Switch
compares there and only NVIDIA's driver did so on its own. Colour components a fragment shader does not write are
masked out, as Maxwell leaves them alone. Without mailbox presentation the swapchain takes relaxed FIFO, or
immediate, so a late frame no longer halves the frame rate. NX2NAVI_VK_NOOPT=1 builds pipelines without the
driver's optimiser, for a driver whose compiler fails on one.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 10:59:59 -05:00
chrg6
375ecf27e2 Wait for the whole boot prewarm and show its progress on a boot screen.
The game used to start after at most 3 s of prewarm, so after a translator, GPU or driver change it met the rest of
its shaders in play and stalled on each one. It now waits for all of it: a warm start is ready in about half a second
and shows nothing, while a cold one shows a "Preparing shaders" screen in the menu's colours and the game's fonts, with
the shader and then the pipeline count and a bar. The shader and pipeline prewarm report their numbers every 100 ms.
The present path takes a frame without a game image for the screen. The RomFS opens on the first host-side read, so
the screen's fonts load before the guest's first file access. NX2NAVI_PREWARM_WAIT_MS now defaults to 0 (no cap). With
no progress for 60 s the game starts anyway and the prewarm finishes in the background.

Measured with an emptied cache: 2,988 shaders translated and 2,399 pipelines built in 9.4 s behind the screen, then
0 ms shader and pipeline waits in Kokiri Forest. Warm: the game starts 0.47 s after launch.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 09:26:51 -05:00
chrg6
99de7b943f Give each file of copied code one license line.
Each file that contains copied code names its copyright holder and license and points at THIRD_PARTY_NOTICES.md; zlib code keeps its full notice and the mark that it was altered. Comments and probe text only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 05:04:40 -05:00
chrg6
1b39aabd37 Describe what the code does in comments and docs.
Comments say what the code does and why, docs/maxwell.md keeps the Maxwell facts, and fetch_refs.sh clones only the checkout the build reads. Code is unchanged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 05:04:40 -05:00
chrg6
4943b50ff2 Unlock the frame rate, shorten cold starts, and describe the Ocarina build in the docs.
Ocarina steps its game by the clock (the same frame-numbered walk covers half the distance at 120 fps), so in a build
without the fps60 and realtime patch sets the pacer holds frames to the frame limit alone: any rate from 30 to 1000,
the monitor's rate, or unlimited (164 fps average in Kokiri Forest). The menu always shows the row, with 165, 240 and
Unlimited added. NX2NAVI_PACE_HZ sets the pacer's rate for tests.

A compute pipeline is compiled outside the pipeline lock, and one compile serves the replay and the boot prebuild
alike; the prebuild uses half the CPUs. The guest waits at most NX2NAVI_PREWARM_WAIT_MS (3000) for the boot prewarm,
which then goes on in the background (a cold start waited 9.8 s). NX2NAVI_TEST_PAD_AT attaches the test gamepad late
and presses it, to test a controller switched on in play.

README, docs/architecture.md, docs/controls.md and AGENTS.md describe the Ocarina build.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 05:04:39 -05:00
chrg6
c7257fe652 Fix NVN2 compute constants, indirect mesh draws and empty descriptor sets, and cut the texture pool refresh.
NVN2 compute banks get the dispatch's group counts in bytes 0-0xb, for direct and indirect dispatches; the fog pass
after the integration divided by them. Indirect mesh draws read NVN's {count, first} record as {x, y, z}, so y = 0
drew nothing: each now draws from a ring entry holding {count, 1, 1}, copied on the GPU before the draw. An empty set 1
no longer leaves set 0 pushed with 0 bytes. Compute stages with subgroup operations whose width is a whole number of
subgroups require full subgroups.

The texture pool refresh fell from 3.1-3.7 ms to 1.0 ms a frame in Kokiri Forest: slots with the same descriptor,
address generation and entry generation share one lookup (about 14,500 of 15,000 refills a frame), and registering a
texture and view identical to what the slot holds keeps its resolution. Under 20 GiB of VRAM, ASTC textures are
encoded to BC3 by default (Kokiri: 15.9 to 8.2 GiB, same GPU time). The pool log counts refills by cause and what
invalidates them; frame dumps write BC textures as raw blocks and print a storage buffer's backing span; a profile with
NX2NAVI_PROFILE_FRAMES is written when its window ends; the alpha test logs once that it is not applied.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 05:04:39 -05:00