Commit Graph

1082 Commits

Author SHA1 Message Date
chrg6
5354aecdc5 Name the term that set the released textures' size bound in its log line.
The line said "a quarter of the video memory budget" whenever the card's rule raised the bound, also when the smaller term was an eighth of the installed memory: on the RTX 5090 with 32 GB of the 2026-11-13 session the bound of 4,008 MiB came from the memory, not from the card's 7,854. The line now names the term that won, and the default's own.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
1fa8b61b87 Give back the ASTC decoder's grown scratch 5 s after its last large texture, not at the next upload.
A scratch grown past 32 MiB for a large texture went back to the usual size only when the next ASTC upload asked for one, so in the 2026-11-13 session the decoder held 224 MiB for the 70 s after the first area load and from a later load to the session's end. Each present now gives it back once no texture needed more for 5 s; nothing is made then, the next request makes the usual scratch, and the buffer is freed once the upload batches recorded so far completed, as before. The present only tries the decoder's lock, which can be held while VMA makes a block. astc_scratch_trim = 0 keeps the scratch until the next upload.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
b81a9561ca Log how long the memory report took on the presenting thread.
The report runs at the present every 3600 frames in every run (600 with trace = perf) and walks the texture entries, the pipelines and the C runtime heap's summary; the 600-frame frames of the 2026-11-13 session carried 10-17 ms nothing else accounted for, and the report's own comment said it took well under a millisecond. A line after it now gives the time of the vram lines, the holes line and the owners' lines with what follows them, so the next session shows whether the report needs to move off that thread.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
7b0dbeb18d Write the session's reports when the window loses the focus in play, more often in play, and log every end of the game in the launcher.
The session of 2026-11-13 ended 8 s after its window lost the focus, after 7 minutes of play, with none of the game's exit lines: no frame-time summary of its last period, no stutter map of its last minute and no growth ranking at all, as the ranking came every 10 minutes. When the window loses the focus in play, the present thread now writes the frame-time summary so far (starting a new period), the stutter map and the growth ranking at its next present, at most once a minute; formatting only, nothing asks the device. The growth ranking comes every 2 minutes of play instead of 10, the stutter map every 5 instead of 10.

A process that ends through exit() rather than plat_exit now writes the log thread's queue last, after the frame-time summary's exit handler, instead of losing it.

The launcher logged a game's end only for a nonzero code, so the session's end with code 0 left no line anywhere. It now logs every end of a game it started, and when the game's log has no line of the game's own end (the window's close, the game's ExitProcess, a timed run's end, a FATAL or exit line), it notes the end there too.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
00081be563 Split the released textures' take-backs and remakes by kind and size, and say what keeps them past their bound with room.
Whether a shorter hold could take some of the released textures' memory without a take-back finding its entry gone depends on what comes back late: the log said 452 entries (72 MiB) were taken back after a minute in the 2026-11-13 session, but not whether any was large or held content only the GPU made. A second line after the reuse line now gives the take-backs and the makes again after a drop by age for each kind (intact, overwritten, made by the GPU) and own memory (under 1 MiB or more), with the megabytes taken back after a minute; the kind of a dropped entry is kept with its key for the remake.

The census of what keeps the released textures over their bound ran only above a quarter more than they may keep, which with room on the card is twice the bound, so the session's 7,150 MiB against a bound of 4,008 MiB never got one. It now also runs while they are over the bound itself, at most once a minute and 60 times a run. Log lines only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
2969005edc Past the hard count of released textures, drop the cheapest ones first, in one walk per batch.
Past RELEASED_HARD (16,384) the sweep dropped the first released entry in release order that was overwritten or unsampled for 2 s, render targets included, whose drop vk_texture.c already ties to a black frame, and it walked the list from its head for every drop. At the end of the 2026-11-13 session the count sat at 16,384 for a minute while 12,811 of 15,734 released entries owned no memory. The entries now go by class: overwritten ones, then ones that come back intact and are past their usual take-back gap, then other intact ones, and only then ones whose content only the GPU made; still only unsampled ones, and the one sampled longest ago when all were sampled lately, as before. One walk takes a batch down to 256 under the bound. tex_hard_order = 0 keeps the rule of 0.10.1.

The drops past the hard count get a reason of their own, so the texture origins line and the reuse line count them apart from the sweep's drops past RELEASED_MAX, with the classes they came from. The class rules are in vk_tex_release.h and checked by tests/tex_release_check.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
7aa29ff12a Record a pipeline in pipeline-keys.bin at its fast link, not only when its optimised build ends.
A session of 2026-11-13 met 46 pipelines late in adult Kokiri Forest (145 draws left out, mesh pipelines usable after up to 782 ms) and ended about 2 s later: the records waited for the optimised builds, and 23 of the 46 never reached the file, so the shared pipeline list folded from it would have missed them. A pipeline is now recorded as soon as a draw can use it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
0e0cfe0827 Keep the freezes of idle regions back after slow ones and around area loads.
After a slow freeze the passes wait 250 ms, doubled for each further slow one, but the first fast freeze after a hold started the doubling over, so in the seconds after a load a 4-5 ms freeze came every 250 ms (Kakariko, 2026-11-13: five in a row, 16 frames apart), and freezes of 4-10 ms pushed frames of 25-52 ms over the stutter line. The doubling now starts over only after freeze_quiet_ms (default 5000; 0: the old rule) without a slow freeze. No pass runs while the texture pool makes an area's textures, when the frames are held anyway and one freeze took 32.4 ms, nor for freeze_load_hold_ms (default 3000; 0: off) after that or after an area's load. The regions that go idle meanwhile stay queued and are frozen later; their write-watch queries go on until then. A region is now queued once instead of again every freeze_idle submissions while the passes are held.

The rules are in runtime/freeze_hold.h, checked by tests/freeze_hold_check.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:52 -05:00
chrg6
f7487ceee5 Make the memory census walk once and fire on the process's own commit, not on its private bytes.
With mem_census = 1 the census trigger compared the private bytes with the last census, and Windows charges the video memory to them, so every gigabyte of textures started another 130-260 ms walk on the presenting thread: 22 of the 33 walks of the 2026-11-13 session came from that trigger, while the process's own commit grew 307 MiB in play. The trigger now reads the private bytes less the write-combined memory of the last walk (and what the driver's device-local figure grew since), compares them with the highest figure seen at a census, and waits 60 s after the last walk; the 3600-frame censuses stay.

On Windows one walk of the address space now gives both the commit census and the guest regions' committed bytes, which mem_guest_census walked a second time. The census counts the driver's write-combined views apart instead of as guest memory, counts as guest only the reserved guest regions and the loaded modules, and ranks the process's own allocations wherever they lie. The frame after a walk charges its time to a new "census" cause in the frame-time summary and the stutter map instead of "unattributed".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:57:51 -05:00
chrg6
f1a2a64e83 Refuse to package a shader translator that was not built from the checkout's own sources: make_launcher prepares the translator's sources in a temporary folder, hashes them as tools/build_xlate.py does, and stops when the --xlate folder's nx2navi_xlate.id differs. 0.10.0 and 0.10.1 shipped the 0.9.2 translator, whose translations still clamp texture pool handles to slot 32767, so the ground could go see-through (issues #569 and #824).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 15:20:28 -05:00
chrg6
7e74c9efd9 Say in the architecture notes when mesh_fallback = auto takes the fallback, and that a count the GPU wrote is cut to the fallback's buffers.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
c99e9a94f8 Start every pass and dispatch mark with no mesh draws counted, where the mark is made.
The count was reset in vk_exec_pass_begin alone, so a dispatch's record kept the counts of the pass that last had its slot of the ring; the report prints them only for passes, but the record now holds what its mark was.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
bac47d2edb Order the write-back merge's writes after earlier writes of the imported buffers it writes.
The barrier before the merge (vk_memory.c vk_mem_mirror_end) made earlier writes visible to the merge's shader reads only; its shader writes to the imported buffers follow writes there too, and a write after a write needs the write access in the dependency's second scope. On for every device: the barrier was there already, it only covers one access more.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
edd5d04e8c Cut a mesh fallback draw's workgroup count that the GPU wrote to what the fallback's buffers hold before a dispatch reads it.
The record's copies put the count the game's culling pass wrote into the first dispatch and, without a task stage, into the draw's instances as it was. A garbage count launched up to millions of workgroups that write nothing and instances that draw nothing, enough to keep the GPU past the driver's timeout; with the fallback now the default on AMD's driver for RDNA 1 and 2, such a count would have moved a hang there instead of removing it. A single-thread compute pass (shaders/meshfb_clamp.comp) cuts the count to the buffers' room, which changes nothing that is drawn; the report word keeps the count asked for, so record_check still logs a mesh-only draw that asked for more than the buffers hold. On for every device that uses the fallback: one dispatch and one barrier per indirect fallback draw.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
46d71da8aa Draw task and mesh programs through the mesh fallback by default on AMD's Windows driver for RDNA 1 and 2, where native mesh pipelines lost the device in play; mesh_fallback = 0 draws them natively again.
Every RX 6000 loss whose pass marks named a pass was in one that starts with a native mesh draw, on every version from 0.6.0 to 0.9.2 and with every other setting tried each way; RDNA 1 cards on the same driver draw through the fallback and RDNA 3 and 4 on AMD's other driver draw natively, and neither has such a report. That the native mesh path is the cause is not shown. The decision moves into vk_mesh_path.h with a test of each device kind and setting; has_mesh_shader keeps saying what the hardware has, so the recorder thread and the low-end card test do not change. On those cards no native mesh pipeline is built any more: the seed list and the boot prewarm skip them. The early tail stays off with the fallback, a combination never measured. The fatal line names the mesh path, and NX2NAVI_VK_NOOPT's default applies with mesh_fallback = 0 alone.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
1f4818fb6b Name in a lost device's report the mesh draws of each marked pass, a group of draws the replay workers recorded between two marks, and in the fatal line how mesh draws are drawn.
A pass mark now counts its mesh draws and those that take their count from the GPU; the gap before a mark notes a group recorded by the workers, whose passes have no marks, where the report said "barriers and state only"; the fatal line names the mesh path (native, the mesh fallback, the emulation). The comment on the RX 6700 XT report in vk_exec.c called the last marked dispatch the replay's own: it is the game's (op_dispatch, cs d7566eb1).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
8df4311723 End the run as a lost device when a timeline reads above every value its signals carry, and log the submissions' state with the first occlusion query left unwritten.
The RX 6000 reports of 0.9.1 and 0.9.2 ran the completion callbacks of submissions the GPU never finished before any call returned VK_ERROR_DEVICE_LOST, although the completion thread polled the device first. Every value a queue hand-over or a host signal gives the submissions' timeline or the executed timeline is now noted before the signal (vk_sync_hw.h); the completion thread and the wait after a submit end the run when a timeline reads above that note. The first occlusion query found unwritten after its fence logs its submission, the submissions' values, both timelines' readings and the GPU breadcrumbs, and the lost device's report starts with the same line, so the next report shows whether the driver gave a value above the note.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 12:54:24 -05:00
chrg6
a84a3ab12d Make the release 0.10.1: every setting under the Game tab's Testing heading is off by default again, CPU helper threads (replay_workers = 0) and Start next frame early (tail_early = 0) among them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 10:49:01 -05:00
chrg6
5190f8e932 Make the release 0.10.0, with its notes; the notes of the unreleased 0.9.3 are folded into them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
v0.10.0
2026-11-13 09:53:26 -05:00
chrg6
26d26babe5 Bring public main's bug capture on F8 and its removal of the Steam co-op into the 0.10.0 line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	docs/architecture.md
#	launcher/steamlib.py
#	launcher/ui/app.py
#	runtime/boot.c
#	runtime/cfg.c
#	runtime/flight.c
#	runtime/flight.h
#	runtime/gfx_present.c
#	tests/launcher_test.py
2026-11-13 09:52:43 -05:00
chrg6
8a99af1080 Give back the graphics pipelines no draw has used in this run while video memory is short: over tex_vram_pressure percent of the budget, the autosave thread takes up to 256 of them out of the table every 5 seconds and destroys them once the GPU is past the submission being recorded; a draw that needs one later builds it again from the pipeline cache. Mesh pipelines, entries building or linking and compute pipelines stay, and the next pass logs the video memory in use before and after. pipe_release = 0 keeps them all.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 09:19:50 -05:00
epicmeme546
f5da269add Remove the experimental co-op through Steam.
This takes back the three commits that added it (cd2f9f1, e60677e, a01910d): its runtime layer and Steam binding, the Co-op tab and what it drew over the game, the launcher's copy of Steam's library file, its settings, tests and docs. The tree is as it was before them, with the bug capture that came after kept: its note on screen no longer makes room for co-op's lines, and dbg_area, which the co-op had brought and the capture uses, stays.

The four settings of that co-op join the retired names, so a settings file that still has them logs no unknown key. A steam_api64.dll that the launcher put beside the game is left where it is: nothing loads it any more.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-13 09:08:40 -05:00
chrg6
e4df494048 Turn the early tail on by default (tail_early = 1): the game starts its next frame while the graphics card runs the last one's upscaler and interface, and a frame whose end hands the game anything else runs as before; tail_early = 0 turns it off.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:58:03 -05:00
chrg6
482f7fdfb5 Stop logging a replay worker's deferred render target lookup as a target left out, and say why a target that is left out could not be rendered.
A chunk's lookup that needs its turn returns no image and its op is replayed in turn, but the first one was logged as "render target ... is not renderable here: left out", which read as depth and cube targets the replay could not draw. Nothing else changes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:36:46 -05:00
chrg6
5faa1687f4 Add quad_index, which draws an indexed quad list as two triangles per quad and closes an indexed line loop, from the game's own indices, and log the first such draw either way.
Vulkan has no quad or line-loop topology. Draws without indices were rewritten already; an indexed quad list went to the GPU with its indices under the triangle list topology, three at a time, joining corners of neighbouring quads, and an indexed loop lacked its closing line. Off by default and read at start; no log of Ocarina has shown such a draw so far, and the new line says when one comes. tests/index_rewrite_check.py checks the index lists.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:36:46 -05:00
chrg6
9d5f16bda4 Add oq_hold, which makes a samples-passed report whose draws the full occlusion query ring left uncounted repeat its record's last complete count, and log how often such reports happen.
A draw that finds every query slot still waiting for the completion thread goes uncounted, and the report after it said only what the other draws counted, at least 1: the game takes the object it tested for all but hidden for that frame. With the setting the report writes the larger of that and the last complete count reported into the same record. Off by default and read at start; the count of such reports is logged at the 1st, 10th, 100th and so on either way. tests/oq_hold_check.py checks the rule.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:36:46 -05:00
chrg6
cc5c8f87ad Add shadow_pcf, which makes every depth-compare sampler filter linearly so each shadow test blends the 2x2 shadow map texels around it, and log the filters of the compare samplers made.
Through a nearest filter each of the game's shadow compares tests one texel, so shadow edges are stair steps of shadow map texels that crawl over the ground as the sun cascades follow the camera. The setting is off by default and read at start; with shadow_scale above 1 the samplers were already linear.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:36:46 -05:00
chrg6
fadd4a6d5e Copy large textures out of the game's memory on several threads at once: a level of 1 MiB or more goes to a small worker pool as bands of rows (par_jobs.c, tex_deswizzle.c tex_bl_copy_mt), and so does a large block copy for the GPU's ASTC decoder, so the upload's storage copy no longer runs on the drawing thread alone. The bytes are those of the one-thread copy; par_jobs = 0 turns it off.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:35:42 -05:00
epicmeme546
346f10019c Give the bug capture page the size and time of a capture at full window size.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-13 08:25:02 -05:00
chrg6
e7c2fc6a6b Make the stutter map name the areas without the perf trace, and count a hitch only when the frames after it are shorter: a hitch is now measured against the median of the last 32 frames, so a steady change of pace (the game drawing at 60 fps after 200) is no longer counted as a run of hitches.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 08:23:11 -05:00
epicmeme546
cd0e87dd8c Say in the bug capture page what a replay does when a conversation holds Link, and what was measured.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-13 08:20:11 -05:00
chrg6
d499a828b7 Compress idle shader SPIR-V after 5 seconds while the system memory is tight, and after 1 second while it is critical.
The wait stays shader_compress_idle_s (30) at the roomy and normal levels; every level compresses losslessly, and a
shorter wait only means a shader read again soon after is decoded once more.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:55:56 -05:00
chrg6
0c153c124e Add mem_budget: one place that says how much room the card and the system have.
A thread samples every two seconds the video memory budget against this process's use (vk_mem_vram) and the system's
commit headroom and free physical memory (plat_commit_info, plat_mem_info), and turns each side into a level: roomy,
normal, tight or critical, with five points of hysteresis upward and a 256 MiB floor. Changes are logged, and the
memory report's system line ends with both levels. MEM_BUDGET_TEST_VRAM_MB and MEM_BUDGET_TEST_RAM_MB pretend a side
is that small, so that what gives memory back can be tried on a large machine; the texture cache's rules are unchanged.
tests/mem_budget_check.py checks the levels and the hysteresis.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:55:56 -05:00
chrg6
3573a96f46 Keep the SPIR-V of shaders nobody read for 30 seconds compressed in memory.
The shader memory cache held 777 MiB of SPIR-V for 7115 shaders for the whole session. A background thread now
compresses the SPIR-V of each shader no reader pinned for shader_compress_idle_s seconds (zstd level 1, 26% of the
bytes on the test install's 44,151 modules) and frees the plain copy; readers pin it through gfx_shader_spirv_pin and
get it decoded back. What the drawing thread compares at pipeline misses and draws, the module's FNV-1a and its Binding
decorations, is kept with the shader, so module_binding_missing, the water corrections and the DLSS, crumbs and skip
lists decode nothing. A compute pipeline created at a dispatch and a mesh shader's first pipeline key still decode on
that thread, and the memory report counts those decodes apart, with the SPIR-V as held against uncompressed and the
shaders held compressed. shader_compress = 0 keeps it plain.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:55:56 -05:00
chrg6
71e52159f9 Add spv_store.h, which keeps a shader's SPIR-V zstd-compressed while nobody reads it, and its check.
Readers pin the store and get the plain words, decoded from the frame when the plain copy is gone; one packer makes the
frame of a store unused for a while, checks it by decoding it, and frees the plain copy. The lock is held for a few
loads and stores only, never across a decode, an encode or a free. tests/spv_store_check.py walks a store through its
states and runs four reader threads against a packer for three seconds, comparing every word they read.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:55:56 -05:00
chrg6
97671e8ea7 Add the stutter map: each hitch of a play session with its area, what the frame waited for and the pipelines and shaders its draws met missing, and every 10 minutes and at exit the areas ranked by their hitches and the pipelines that cost the most (stutter_map = 1, off by default). tools/stutter_map.py turns a log into a report and counts what a game folder recorded that a pipeline list lacks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:31:57 -05:00
chrg6
cae09a2bcd Add floor_watch: hardware watchpoints on the floor the scan finds log which game code reads and writes it, at 60 fps and again at 120 fps or more.
floor_watch.c takes up to twelve of the floor scan's survivors (the platform's rigid body controller unit first, then one per object at the pivot's height), watches them four at a time through the debug registers on every thread (platform.h plat_watch_set, Windows only), counts each access's call chain in a lock-free table and logs the chains with the executable's symbol names after each pass. prof_syms gains a callback form for that.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:08:49 -05:00
chrg6
c84724da2c Make a moving floor carry Link above 100 fps as it does at 60 (set ofollow, floor_carry = 1).
The character controller's three follow-surface modules kept only a tenth of the floor's velocity whenever the physics' inverse step passed 100, which every update above 100 fps did. The gate now compares with 100 over frames per update from the patch page above 60 fps, and with the game's 100 at 60 and 30 fps.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 07:08:49 -05:00
chrg6
d9429b0c00 Break the memory report down past VMA, by owner in system memory, and by growth over a session.
Every report adds a line for video memory outside VMA (the driver's usage and budget per heap against VMA's blocks, and counts of pipelines by kind and by last use, stage libraries, compute pipelines, layouts and descriptor pools, with the swapchain, DLSS and FSR sizes), a line that splits the process's commit by owner (the game's heap and maps, device-local memory, VMA's host blocks, the C runtime heap with the shader caches, pipeline tables, texture cache, log queue and flight recorder in it, the driver's pipeline cache data and the rest), and a line naming what grew by more than 64 MiB since the report before and since play began. Every ten minutes of play and at exit a ranking line orders the categories by growth and marks those that only climbed; tests/mem_growth_check.py checks that bookkeeping.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:46:31 -05:00
chrg6
a74503cd86 Add physics_steps = 2: at least a 60 fps frame's solver steps in every update on 1.1.1.
Link is carried by the Deku Tree's floating platform fully at 60 fps, about a tenth at 160 and not at all at 240,
which follows the solver steps an update (4, 2, 1 with physics_steps = 1) rather than those a second. The new set
osolverfull raises the rounded-up count to the 60 Hz frame's 4 in every update; physics_steps = 2 switches it on and
osolver off at start, and the mode is logged. 60 and 30 fps keep the game's 4 and 8. It costs more physics time above
60 fps: 576 solver steps a second at 144 fps and 960 at 240, against 288 and 240 with 1, the default, which stays
until a run confirms the carry. frame_step_check runs the lifted words of all three counts.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:26:39 -05:00
chrg6
b912d72b87 Remove the Video memory use row; its low behaviour is the only one now.
Released textures go once they have gone unused for the hold, and what a switched-off upscaler or SMAA held is freed, with no setting to keep them. A vram_use line left in a settings file is known and read by nothing. Memory use is to be decided by the card's and the system's budget instead.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:23:01 -05:00
epicmeme546
4fd70e398f Make F8 write a bug capture and add a test run that starts from one.
F8 now always writes a folder under logs/captures: the area, Link's position and rotation, the camera of the frame on screen and the game's own, the presented frame as a PNG, frame times around the press, the machine, the settings that differ from the defaults, the end of the log, the save, and the game's flags and texts. A note on screen names the capture. The flight recorder's F8 dump goes into the capture's folder.

NX2NAVI_CAPTURE_REPLAY starts a run on a capture's settings, teleports to its area, walks Link to where he stood and puts the free camera where the camera was; tools/capture_run.py prepares the profile from the capture's save, runs it and compares the two captures. docs/bug-capture.md has the files and the steps.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-13 06:22:18 -05:00
chrg6
75ae5b0221 Read co-op's switch by its new name, coop_steam, in the launcher too.
Main renamed the switch so that an old "coop = 1" turns nothing on; the launcher's check for Steam's library still read the old name.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:07:26 -05:00
chrg6
b399d8f15c Keep a late HD rumble report from opening a Joy-Con pair again after the stop.
hd_tick picks a report under the locks and writes it to the pair after letting them go. When input_rumble_hd_stop
wrote the neutral value and closed the pair in between, that write opened the two devices again and left the
Joy-Con vibrating after the exit. The stop now ends the pair (hd_pair_end), and hd_pair_write checks that under the
lock it holds for the write, so nothing is written after the stop.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00
chrg6
d59488d308 Claim the anti-aliasing setting's frame with a compare-and-swap, so SMAA's idle images are freed once.
vk_aa_mode is asked at every compute dispatch, on whichever thread records it, and the replay workers record at once.
The frame was checked and claimed without atomics, so two threads could both free the idle work images. The first
call of a frame now claims it with a compare-and-swap, and only that call frees them and takes the setting.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00
chrg6
721da64866 Put Steam's library file beside the game only with co-op on, and look for it off the window's thread.
Every Play ran steamlib.ensure on the Tk thread, co-op on or off. Without the file that walks up to 60,000 folders
of the player's Steam libraries and checks signatures, and the window stood still meanwhile. Play and the Steam
shortcut's start now call it only when co-op is on in the game's settings (steamlib.wanted, read as the game reads
them), and Play runs it on a thread of its own and starts the game from the window's thread when it is done.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00
chrg6
0e76baad36 Limit replay_small to 0..63, where it can match a group.
A group too small to share out has fewer than 64 draws (2 x CHUNK_DRAWS), so a threshold of 64 or more never matched
in group_start and the setting did nothing. The setting's range is now 0..63, the menu's slider ends at 60 in steps of
4, and a value of 64 or more from nx2navi.ini reads as 63 with one line in the log.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00
chrg6
e7dead8663 Take the low-latency lock around AMD's anti-lag calls, so the switch-off is the driver's last word.
The stage calls ran on guest threads and the present thread without the lock the NVIDIA path holds, and a stage call
with the mode on could come after the switch-off on another thread and leave the driver on. The stage calls now hold
the lock shared and make none once the path is off; the switch-off holds it exclusively and waits for a stage call in
flight. Shared, because the input stage waits inside the call while the present thread makes the present stage of the
frame before, which must not wait for it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00
chrg6
c656532cd3 Warn in the log when replay workers are set by number on AMD's driver for RX 6000 and older.
The automatic count gives that driver no workers, since a game with workers lost its device there, but a number in
nx2navi.ini or the menu starts them without a word. The number still applies; the log now says that workers on this
driver have caused device loss and that auto or 0 avoids it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00
chrg6
5c5b1914d5 Keep the sizes frame generation still uses when the upscaler's idle sizes are freed.
With frame generation and no upscaler, idle_release freed every DLSS size other than the last one at each present
from 600 presents after the switch, without waiting for the GPU. The scene's size can change from frame to frame, so a
size the frame before used could still be in flight. A size now goes only after it went unused for as many
evaluations; its DLSS feature, unused since the upscaler went off, is released as before.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-13 06:06:27 -05:00