Commit Graph
20 Commits
Author SHA1 Message Date
itaskaev2andClaude Opus 5.5 c811d0e06d Carry Reflex's present ID through the recorder's submission
vk_sync_submit chains a VkLatencySubmissionPresentIdNV when the device has VK_NV_low_latency2, and on dev the
recorder thread (on by default except on AMD) makes that submission. rec_submit stopped the process on any pNext,
so every NVIDIA GPU with the extension would have failed at its first recorded submission. The recorder now copies
the present ID into its packet and chains it again in submit_run.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 18:20:16 +01:00
Valiantsin DzerakhandClaude Opus 5.5 bb8b4b1797 Turn the recorder thread on by default on AMD GPUs too; vk_recorder = 0 turns it off where the device is lost
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-10 19:25:37 +03:00
ipavlin98 6b4d84ec50 Record large submissions in chunks on several threads
replay_workers = N (0, the default, keeps the sequential replay) records a submission of enough draws in chunks that start between passes, on N threads and in twice as many chunks, and submits them in order. In the town at 4K on an RTX 5070, 4 threads take the replay from 8.2 to 4.5 ms a frame and the frame rate from 71 to 79.

A sequential scan on the submitting thread applies only what is queue state (fixed-function and bind ops, render targets, render enable and conditions, samples-passed counting) and keeps a copy of it where each chunk starts, with how far its lists got: inline uniform updates, RENDER_COND results, contact shadow marches and the ops that drop uniform copies. A chunk takes those from the lists instead of from the chunks before it, starts with every image in GENERAL and ends with a full barrier, so its recording depends only on the copy and the lists.

Each thread records with a context of its own: the replay's memos, descriptor state, occlusion query segments and per-command-buffer state moved from file statics into VkExec and VkExecDraw, and the tables the contexts share (stand-ins, depth twins, views, mirrors, timestamps, completion callbacks, crumbs) take locks or atomics. The scan makes render targets live in replay order and notes the op (vk_texture_revive), since a chunk can sample a storage before the chunk that renders it got there or after the scan went past a later target there: a chunk's texture slots resolve as of its own op, and the chunks after a texture with no entry yet wait for the chunk that makes it. Uniform copies are dropped at the op that writes them (vk_usnap_drop_at).

Contact shadows plan their march in replay order (vk_contact_plan) and the chunk that holds its op records it; the HDR source keeps the copy that comes last in replay order. DLSS and fxaa = 0 act on the frame draw by draw and keep the replay sequential. TOTK_REPLAY_STATE_CHECK=1 compares the state after the last chunk with the scan's.

A draw or dispatch whose shaders write storage buffers drops the uniform copies they cover from its own op on, as the other GPU writes do (scan_writes). The scan still translates no shader: it reads the shaders the recording contexts translated from a table shared with them (vk_exec_draw_writes), and an op whose shader no context translated yet holds the chunks after it until it is recorded. Before, the chunk that recorded such a write dropped the copies for every position at that moment, so a later chunk recorded first bound the copy taken at the submit call: on an RX 7800 XT on RADV the grass near the camera came out dark or unshaded in some runs with 4 threads.

TOTK_TRACE=perf counts the chunks held per submission by reason and logs when each chunk of the last submission began. The settings menu has the thread count under Advanced, Scheduling, with the count this run uses under it.

The recorder thread begins, ends and submits the submission's open part (vk_rec.c rec_end_cb), so a chunk's mirror prologue stays off it: vk_sync_part waits until the recorder is idle, as the part pool allows one thread at a time, then records, ends and submits the prologue itself. Through the recorder the prologue could reach the queue before it was ended, and the GPU lost the device at the title screen.

(cherry picked from commit b94e2e9642)
2026-11-08 19:39:17 +03:00
Valiantsin Dzerakh b16c4c8938 Merge task/pcore: frame-critical threads prefer the P-cores of a hybrid CPU
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	runtime/vk_rec.c
2026-11-08 12:03:08 +03:00
Valiantsin DzerakhandClaude Opus 5.5 90fa6e1788 Let the recorder submit parts without the submitting thread waiting for it
rec_submit queued each part's submission and then drained the ring until the recorder had submitted it: 0.29 ms a
frame in the town on a Ryzen 7900X, 0.34 ms on 4 cores. Now it publishes the submission and returns
(TOTK_REC_ASYNC=1, default). The queue order the present, uploads, readbacks and device waits rely on is kept by
vk_queue_lock: a thread's first lock waits until the recorder submitted what was queued before (rec_queue_wait).
The recorder itself and a thread that already holds the lock skip the wait. rec_submit reports the first failed
submission the recorder made. Town, in-run A/B: replay -4.1% on all cores, -2.9% on 4 cores / 8 threads; queue
users waited about 0.02 ms a frame. fight2 with TOTK_REC_CHECK and the town under sync validation are clean.

Where the recorder does not poll (fewer than 6 usable logical processors) the producer now publishes the ring head
every 8192 words instead of 64, as Savage Wind Recomp does (runtime/nvn/vulkan/record.c rec_init): each publish
there costs an event set and a wake-up. Town on 4 logical processors: frame interval -1.3%. TOTK_REC_PUB=ab
compares both; the perf log counts the recorder's wake-ups and the queue waits.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 12:02:53 +03:00
Valiantsin DzerakhandClaude Opus 5.5 3a26046cde Let the threads every frame goes through prefer the P-cores of a hybrid CPU
On an Intel CPU with P-cores and E-cores a thread on an E-core runs at about 60% of a P-core's speed, and the frame
waits for its slowest critical thread. The game's main thread, the thread that presents, and the vk replay, recorder
and present threads now select the CPU sets of the P-core logical processors the process affinity allows. Nothing is
selected on a CPU with one efficiency class or when the affinity leaves only one kind of core. TOTK_PCORE=0 turns it
off; "power:" log lines say what was selected and which threads took it. LAS Recomp does the same for its game,
render and vsync threads.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 11:46:10 +03:00
Valiantsin DzerakhandClaude Opus 5.5 2d92565ada Poll briefly before kernel waits and the recorder sleep
Guest waits and waits for a virtual core usually end within microseconds. A thread now polls for 20 us with the
global lock released before it sleeps on its condition variable, so a quick wake costs no OS wake-up
(TOTK_KSPIN_US, 0 turns it off). The recorder polls by the clock for 60 us instead of 4096 pauses, which last a few
us on Zen 4 and about 140 us on Coffee Lake (TOTK_REC_SPIN_US). Both stay off with fewer than 6 usable logical
processors. Savage Wind Recomp polls the same way before it parks.

Machine A, town save, in-run A/B: frame interval -1.8% on average for the kernel poll (5 of 7 block pairs), -0.7%
with the process limited to 4 cores / 8 threads; the recorder poll is neutral there.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 11:05:33 +03:00
Valiantsin DzerakhandClaude Opus 5.5 0f4e0af554 Declare the recorder queue's put_h field by its own name, which the move into Q had rewritten as Q.put_h.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 16:24:56 +03:00
Valiantsin DzerakhandClaude Opus 5.5 b578d26628 Keep the recorder queue's head, tail and producer state on separate cache lines and publish head in batches
The recorder spins on head while it waits, and tail, put_h, head and the producer's statistics shared one cache line,
so every packet moved that line between the two cores: put took 6% of the replay thread in the fort with the recorder
on. head, tail and sleeping now have a line each, the producer keeps its own state and the last tail it read, and pub
publishes head once 64 words wait (TOTK_REC_PUB; 0 publishes every packet). Every wait publishes everything first.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 16:18:56 +03:00
Valiantsin DzerakhandClaude Opus 5.5 895d202cce Let the recorder thread begin, end and submit the parts it records.
The part command buffers and their pool were used by two threads. The submitting thread still waits for the
submission, so the queue order is unchanged. TOTK_REC_END=0 brings the old split back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 10:07:45 +03:00
DizzyMan1337andClaude Opus 5.5 ad3ecd8f3c Per-object motion vectors for DLSS, camera motion in double precision, Ultra Performance and DLSS presets.
Solid scene draws whose position reads an object's own uniform blocks (bones c5, place c7, c6) are drawn a second time
with a vertex shader variant (translator patch 0012) that computes last frame's position from last frame's blocks; the
game writes those into two copies that take turns, and the uniform snapshot keeps both (vk_mvprev.c). The draws are
listed during the replay and recorded through the recorder thread with repeated state skipped. Blocks whose last-frame
copies measured wrong (c9 and c11 of walls and cliffs) keep this frame's; positions without an object block (terrain,
grass) keep the camera's motion, which measured as good.

The camera motion is reprojected in double precision on the CPU: the float inverse made noise on far surfaces and a
still camera that DLSS followed into a wobble. DLSS gets Ultra Performance (a third of the output, also in the F1 menu)
and NVIDIA's recommended preset per mode (K, M for Performance, L for Ultra Performance; TOTK_DLSS_PRESET overrides).

Test switches: TOTK_MV_CHECK measures the motion vectors and DLSS's output against the picture, TOTK_DLAA_TIMES times
DLSS and the motion passes on the GPU. A reactive mask pass for transparents is included but off (TOTK_DLSS_REACTIVE):
its mask covers sky and fog too.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-03 17:31:58 +08:00
Valiantsin DzerakhandClaude Opus 5.5 328589abbe Add TOTK_REC_CHECK and TOTK_REC_DELAY_US to find objects the recorder still names
TOTK_REC_CHECK=1 searches the packets of the part being recorded for each image, view and buffer vk_memory.c defers or
destroys. A deferral stamped below the part's value, or a destruction of an object a packet names, is logged with the
packet op, both stamps and the GPU's value, and counted by kind and op in a summary at exit. put() zeroes each packet's
room while the check is on: packers reserve room for optional arrays they may leave unwritten, and those words held
handles from the ring's previous lap. TOTK_REC_DELAY_US=N makes the recorder wait N us before each batch, as on a slow
machine. rec_begin takes the part's value for the check. Both are off by default; off, the recorder pays one test per
batch and per packet.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 15:02:38 +03:00
Valiantsin DzerakhandClaude Opus 5.5 710b7f5dd0 The device-lost report names the pass or dispatch the GPU was running
The replay marks the start and the end of every render pass and dispatch
(vk_exec.c vk_exec_pass_begin and vk_exec_pass_end, vk_exec_draw.c
op_dispatch and op_dispatch_ind), outside the pass so no pass is broken.
With VK_AMD_buffer_marker the GPU writes the last started and finished mark
into words 2 and 3 of the breadcrumb buffer; with
VK_NV_device_diagnostic_checkpoints the same points are checkpoints, read
with vkGetQueueCheckpointData2NV after the loss. A ring of 4096 records maps
a mark to its submission, index, target formats and size, draw count and the
input ids of the first and last draw's shaders. vk_device_fault_report logs
both marks with their records. The calls go through the recorder thread.

TOTK_PASS_CRUMBS (menu: GPU pass marks): unset, AMD buffer marks only; 1,
also NVIDIA checkpoints, whose extension is enabled only then; 0, none.
The design follows Savage Wind Recomp 3fae40c; the code is ours.

--probe-vkexec gets a pass marks part: pass, dispatch, pass in one
submission; the marks read back after the fence name the last pass and the
report text says so.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-02 09:50:30 +03:00
eioo d7357368e8 Turn the recorder thread off by default on AMD GPUs again
0.2.8 turned the recorder on for every GPU (e38eaa8). The AMD device losses
and hangs came back the same day: a black screen or VK_ERROR_DEVICE_LOST at
startup on RDNA 2, 3 and 4, under AMD's Windows driver and under RADV
(#277, #283), and vk_recorder = 0 still gets past it.

The submission recorder goes back to defaulting off on vendor 0x1002;
TOTK_VK_RECORDER=1 still forces it on for an A/B run, and the log says which
path was taken. The rec_end_cb line now prints only when a part really was
recorded by the recorder, so a log no longer suggests the setting was
bypassed (#315).
2026-11-01 11:31:17 +02:00
Valiantsin DzerakhandClaude Opus 5.5 e38eaa8224 Turn the recorder thread back on by default on AMD GPUs
The AMD device losses with the recorder (#5, #40) stopped after objects
were kept until their submission completed and the recorder began ending
its own parts; RDNA 1 and 2 cards in #5 ran with vk_recorder on and off.
vk_recorder = 0 still turns it off.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 18:41:38 +03:00
Valiantsin DzerakhandClaude Opus 5.5 43a18a9bb1 Merge pull request #60: Linux port (AppImage) and Steam Deck support (wdiasjunior)
The branch forked 79 commits before main and 98 before dev. Resolutions:

1. Aspect ratio: dev's implementation stays (camera patch at page +56 on 1.4.3, tools/ultrawide_layout.py layouts per
   size in romfs-patches-<w>x<h>, the aspect = fit|stretch setting). The PR's second implementation is dropped: the
   aspect sets of patches-v121.txt and patches-v143.txt (the 1.4.3 one patched the same viewport sites as dev's),
   tools/aspect_layouts.py, the resolution.c shapes that limited game resolutions to 16:9, 16:10 and 21:9, and the
   picture_fit setting. Its letterbox code (gfx_fit_rect) is kept and reads TOTK_ASPECT.
2. Code dev changed where the PR moved it: the stick dead zone, the test gamepad and the paddles go to input.c; the
   DPI awareness, keep-awake and IME detach of gfx_window.c go to gfx_window_win.c; device fault reports and GPU
   breadcrumbs to gfx_present.c. gfx_window_dpi gets an SDL version.
3. dev's Win32 calls in shared code go through platform.h: the shader cache pack reader (PlatFile), the romfs
   overlay checks, the audio pacing waits, the motion, ASTC and device fault locks. plat_cpu_usable and
   plat_commit_info get Linux versions; plat_cpu_count counts the machine's processors on both. dpi_probe.c becomes
   dpi_probe_win.c.
4. assume_focus defaults to 1 as the PR has it (a load interrupted by a focus loss can stop for good) and stays live,
   with dev's Game tab row.
5. The frame limits 40 and 45 join dev's list. The BC 3D storage fallback for Vega only runs with
   TOTK_BLOCK_VIEWS_3D=1, since dev makes 3D BC images without block views by default.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-31 13:26:42 +03:00
Valiantsin DzerakhandClaude Opus 5.5 25b200f94c Draw 3D BC textures through stand-ins and let the recorder end its parts
AMD driver 26.10.1 on RDNA2 cards wrote past the end of a 3D BC4 volume made
BLOCK_TEXEL_VIEW_COMPATIBLE and 2D_ARRAY_COMPATIBLE, which lost the device at the
logo (issue #5). 3D BC textures no longer get block views: draws into a level go
to an uncompressed 2D array stand-in that is copied back at the pass end
(TOTK_BLOCK_VIEWS_3D=1 restores the old path).

Parts the recorder thread recorded and the submitting thread ended turned the
scene green, then white, on the same driver once a submission was split. The
recorder now writes the closing breadcrumb and ends the part itself
(TOTK_REC_END=0 restores the old split). The recorder stays off on AMD by default.

Based on the patch Pelipooper posted in issue #5; stand-ins extended to every
mip level.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-30 23:50:02 +03:00
Valiantsin DzerakhandClaude Opus 5.5 43704c0d9f Turn off the recorder thread on AMD GPUs and GPL on AMD's RDNA 1/2 driver, and log GPU breadcrumbs on a lost device
AMD drivers lost the device at boot or at menu opens with the recorder thread; vk_recorder = 0 ended it for three
RX 9070 XT users (issue #5), and RADV saw an illegal opcode at the end of a command buffer (issue #40). It now
defaults to off on vendor 0x1002; TOTK_VK_RECORDER=1 turns it back on.

On AMD's separate driver branch for RDNA 1/2 ("AMD proprietary shader compiler") every device loss came with a cold
pipeline cache and draws waiting on fast-linked pipelines, and the recorder setting did not help there. TOTK_GPL now
has no fixed default: off on that branch, on elsewhere.

VK_AMD_buffer_marker breadcrumbs (vk_crumbs.c) mark the start and end of each submission part, upload batch, ASTC
decode chunk and present; on device lost the log names the last point the GPU reached and the last one it finished.

vk_fsr.c ensure_images held no queue lock around vkDeviceWaitIdle, which needs every queue externally synchronized.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-30 19:48:38 +03:00
Wellington Dias 1d51343ac1 Build and run the runtime natively on Linux.
Shared runtime code now goes through runtime/platform/platform.h, implemented by platform/win32.c and a new
platform/linux.c: futex locks, a userfaultfd and PAGEMAP_SCAN write watch, signal-based async preemption, our own
fiber switch, and a SIGSEGV handler for the thaw and crash hooks. The window, input, menu and software keyboard get
SDL3 back ends beside the Win32 ones, with the swapchain (gfx_present.c) and input merging (input.c) shared. SHA-256
replaces BCrypt, ELF builds get their own override sections, and the build tools gain Linux branches.

On Linux the selftest and the gfx-abi, astc, nvn and window probes pass. probe-vkmem still fails: imported guest
memory cannot be write-watched on Linux, which the shadow buffers in vk_memory.c will address.
2026-10-29 16:56:56 -03:00
Valiantsin DzerakhandClaude Opus 5.5 3fb4b8d4b9 Make the replay's Vulkan calls on a recorder thread: each vkCmd* into the replay command buffer becomes a packet in a ring that the recorder makes in order, every other command buffer is called at once, and the submit waits for the ring to empty. Town on an RX 9070: replay 9.98 -> 8.29 ms a frame (in-launch A/B), no new validation messages, same picture
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-28 16:41:46 +03:00