Commit Graph

18 Commits

Author SHA1 Message Date
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
0cebadcfac Leave the shader preparation modes on every processor the process was given.
The large-cache die's placement is for the game's own threads. --prepare-shaders and --warm-shaders translate and build
on as many processors as they find, so on a two-die processor the placement would have halved them.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 02:02:11 -05:00
ordinarybob
662a6e88ee Run the game on the die with the larger L3 cache on processors whose dies differ (AMD's two-die X3D processors).
Windows places a game on the V-Cache die only when it recognizes the exe as a game, and it does not know this one, so the threads were spread over both dies by frequency preference. cache_die = 1 (the default) narrows the process to the logical processors that share the largest L3; it never widens the set the process was given, and does nothing where every L3 has the same size. The recorder's reserved core is then chosen inside that set.

Co-Authored-By: Claude Fable 5.2 <[EMAIL]>
2026-11-10 02:01:35 -05:00
chrg6
202fc247d0 Name the gamepad probe probe_gamepad, so it does not clash with ov_probe.c's own static probe_input.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 23:54:29 -05:00
chrg6
be8c2620e5 Run the gamepad update on a thread of its own, so a controller that comes or goes no longer stalls the game.
When a device came or went, SDL's gamepad update first found every device again, 100 ms and more, on the game's
polling thread with the input lock held: a controller disconnecting gave five frames of 120 to 240 ms in a row, with
the game's other pollers queued on the lock. The pad thread now makes SDL's initialisation and every update. A poll
asks for an update and waits at most 2 ms for it; an ordinary one is done in microseconds and the poll reads fresh
state as before, and during a device search the poll goes on with the state it read last. Rumble, the motion samples
and the menu's stick reading skip a beat then instead of waiting.
--probe-input checks it on a virtual gamepad, with an update made to take 300 ms.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-09 23:51:58 -05:00
chrg6
f63b6796ee Decode Ocarina 1.1.1's loading streams on the host decoder, behind the same zstd_native = 1 switch.
The loading threads feed each chunk they read to the game's stream decoder, which is where most of the
decompression time goes. That call now reaches a host stream that writes straight into the game's output
buffer and keeps the game's state fields and results. A stream is taken from its first chunk or left to
the game; zstd_check = 1 runs both and compares the outputs. --probe-zstd checks the host streams on
frames it makes itself.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-09 21:21:48 -05:00
Michael Schienbein
a103673341 Make the SDL window honour monitor, --monitor and --list-monitors.
On Linux the window ignored NX2NAVI_MONITOR (the log said it had no effect) and --list-monitors only printed that monitor selection is Win32-only. The SDL window now picks a monitor with the same rules as the Win32 one: auto (the system places it), primary, a 1-based index in listing order, or part of the monitor's name, ignoring case, the first match in list order winning. The monitors are SDL's displays; --list-monitors prints their index, name (the make and model, with the connector on Wayland and X11), pixel size and position, primary flag and display scale, then what NX2NAVI_MONITOR would pick, and the log says the same when the window opens.

The window is created centred on the chosen monitor and centred again at its final size, and that position also names the display the fullscreen setting covers, which is how a Wayland window, which a client cannot move, opens fullscreen on the chosen output. On Wayland a windowed window opens where the compositor puts it; the log says so once. With a chosen monitor, the size widescreen.c reads for fullscreen before the window exists is that monitor's.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-11-09 20:51:09 -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
Tyler
2270664be2 Total each allocation once in the commit census, add a size breakdown, and write the profile on a crash
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HtayeqEG2x5woYzWuEQBGV
2026-11-09 08:20:01 -05:00
xyzzyy
a4ee74b74e Stop flushing the shader cache files every read checks, so shader preparation translates twice as fast.
Each translation flushed its .spv and .res.json to the disk, wrote its .use mask with a flushed, written-through
rename and renamed its outputs written through: about six waits for the drive per shader. An NVMe drive does about
1,100 flushed files a second, a SATA SSD or a hard drive far fewer, so the translators sat mostly idle. Every read
already checks these files (spirv_complete, reflection_valid, the .use magic and size) and a torn one is translated
again, so they are now written whole but not flushed (plat_file_write_cached, plat_file_replace without durable).
The .in files stay flushed: they hold the guest's code and only their header and size are checked.

4,683 shaders of the install's preparation on a Ryzen 7 7700X and a Samsung 990 PRO: translation 36.4 and 37.2 s
before, 18.4 and 18.9 s after; every .spv, .res.json, .use and .in file and shader-prepared.bin are the same.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 08:18:54 -05:00
Thiago Cabral
d0c8588e3f Open the game window on a chosen monitor: the monitor setting and --monitor pick it by index, primary, or part of its device or monitor name, and --list-monitors prints the monitors.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 08:18:08 -05:00
Thiago Cabral
bb0ac8caeb Play the sound on a chosen output device: the audio_device setting and --audio-device pick it by index or part of its name, --list-audio-devices prints the devices, and a chosen device that goes away hands the output to the default one.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 08:17:35 -05:00
chrg6
93a38b5d12 Check the selftest's physical memory limit against the title's own pool size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 08:09:26 -05:00
chrg6
42ae87bca6 Runtime: power opt-out, faster fence wake-ups, feedback barrier, texture re-upload skip
- Opt the process out of Windows power throttling (execution speed and
  timer resolution) at startup; NX2NAVI_POWER_FULL=0 turns it off.
- Fence completion thread wakes waiters before collecting freed memory,
  so collection no longer delays them.
- Add a by-region barrier when a draw or clear writes an attachment that
  an earlier draw in the same pass sampled; count it and inline uniform
  updates in the per-frame stats.
- Hash small texture contents at upload and skip re-uploads whose bytes
  are unchanged (removes ~420 redundant uploads per frame in Kokiri
  Forest); NX2NAVI_TEX_SAME=0 turns it off.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 06:04:57 -05:00
chrg6
9bb3c6c55a Hand the frame limit to RivaTuner Statistics Server where it runs, and take it back when RTSS does not hold to it.
Where RTSS is installed and running, the frame limit from the menu goes into RTSS's profile for the game's executable
through RTSS's hooks library, loaded at run time, and the game's own pacer stands aside while RTSS has hooked the game.
Menu changes apply live, unlimited clears the limit, and closing the game (or any exit path) puts back what the profile
held, or removes a profile the game created. Each change is read back from the saved profile: without administrator
rights RTSS's profile folder cannot be written, and the game then keeps its own limiter. While RTSS limits, RTSS's own
frame counter for the game is checked against the limit; well past it for three seconds, the game takes the limiting
back for the run. The log says which limiter is in use and why, and a note under the frame-rate row says when RTSS
limits, when its profile is read-only, and when it does not hold the game to the limit. rtss = 0 and frame generation
keep RTSS out.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 01:25:12 -05:00
chrg6
c8738a948c Name the settings, files and tools NX2navi
The names are NX2NAVI, NX2navi or nx2navi: the settings prefix (NX2NAVI_*), the ini file
(nx2navi.ini), the shader translator (nx2navi_xlate), the Windows resources, the installer and the docs. The 8-byte
file magics keep their size (NX2NSANS, NX2NSPRG, NX2NSPRP, NX2NPKEY, NX2NRFS1), so caches and the RomFS index from
older builds are not read. cfg.c and the settings pages took the prefix length as 5; it now follows the prefix.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 05:04:39 -05:00
chrg6
77d0c0b84e Port Ocarina of Time (Switch 2) to the recomp host
The NVN2 front end and the SM86 to Maxwell shader lowering (tools/xlate/AmpereLowering.cs, mesh and task stages,
bindless texture pools, BRX jump tables, the NVN2 compute c0 layout) with four translator patches (0017-0020) bring the
opening of the game to 58-60 fps on the Vulkan renderer.

This round fixes the haze: SM86 IPA is lowered as a plain Maxwell IPA.PASS (texture coordinates were corrected for
perspective twice); LDSM, TXD, both F2IP byte forms, HMMA, MOVM and HFMA2.RELU are lowered and spill mode has eight
uniform register groups; conditional rendering keeps the newest counter report per address and treats a report as
pending until its value is in guest memory, so occlusion tests and the depth clears around the depth copy behave; and
the upscaler stand-in decodes the post pass's sRGB picture before writing the linear target. Tensor-core programs keep
the stand-in unless NX2NAVI_NATIVE_TENSOR=1, because their lowering does not match the hardware yet.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-07 05:04:39 -05:00
Valiantsin Dzerakh
0478c13e45 Import the base tree (MIT, see LICENSE) 2026-11-07 05:04:38 -05:00