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>
AMD's RDNA2 driver places the depth compression metadata after the depth data. Above 1080p that tail of a depth
target bound into the game's texture heap lay over the next texture, and every depth write scrambled it: a garbage
band at the top of the screen, a pink glow, blocks in the grass and a blue checkered scene in the menu (RX 6600 to
6800, issue #185). Reproduced at 2560x1440 on an RDNA2 iGPU with driver 26.10.1; all 63 oversize images there were
D16 or D32 depth targets. Colour images keep their place in the pool.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A BC3 image takes whole 4x4 blocks or a part ending on the mip's edge; a WriteTexels region of a 5x5 or 6x6 footprint may end inside one. --probe-astc encodes every footprint to BC3 and holds the blocks to alpha, palette-place, flat-colour and PSNR bounds.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A GPU that cannot sample ASTC gets the textures decoded to RGBA8, four times the video memory of the ASTC blocks. With astc_bc = 1 (default 0, GPU decoder only) a second compute pass, bc3_encode.comp, encodes the decoded texels to BC3 and the image is BC3_UNORM or BC3_SRGB: 8 bits per texel instead of 32. The encoder is the usual bounding-box method with the box diagonal turned to the sign of the colour covariance, and the eight-value alpha mode.
A region of a WriteTexels that does not start on a 4x4 block corner is left as it was and logged. The setting is in totk.ini and the Advanced tab. The SPIR-V header was built with glslang 16.6 (build_shaders.py uses glslc) with the same source hash.
On a GTX 1650 (4 GiB) in the Fire Temple the GPU time per frame went from 10-23 ms to 3-12 ms and the frame rate held at 59-60 fps.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
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>
RADV on GFX9 returns a 0-byte image for a mipmapped block-compressed 3D image with COLOR_ATTACHMENT usage and no
STORAGE (the usage asks for a thin layout the GFX9 address library has no swizzle mode for), and VMA then fails the
allocation: "image creation failed (-3): nvn fmt 0x49 32x32x32" on a Ryzen 5 4600G. create_tex checks the size the
device wants for such an image and, when it is 0, adds STORAGE usage, which keeps RADV on a thick layout; the replay
never sees that usage. If the device still cannot lay it out, the image is made without block views. bind_pool_memory
refuses a 0-byte image. Forcing the storage path on an RX 7800 XT renders the same frames.
Every square 2D array of 6 or more layers was created cube compatible, though the replay makes cube views only of
images whose own target is a cubemap or cubemap array (vk_exec_draw.c get_view). On AMD's Windows driver the flag
changes the image layout, and Savage Wind Recomp traced rainbow blocks on terrain that moved with the mip level to
it (their issue #59, BotW on an RX 580 and a 7800 XT); our AMD and Intel reports show the same symptom (#42, #67,
#81). The flag now goes to cube targets only, on every driver.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
wb_fence_limit (TOTK_WB_FENCE_LIMIT, default 65536) replaces the fixed 64 KiB limit of the write-back done when the CPU waits for a fence. With trace = gfx the log names each dirty target left on the GPU because of its size and each target over 64 KiB that a raised limit wrote back. Meant to test whether the fuse weapon switch bug (#18) and the Purah Pad camera bug (#13, #63) come from a target the game reads on the CPU without an invalidate.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
On a 4 GiB GPU the released-texture list (up to 2048 entries, each ASTC texture decoded to RGBA8) filled video memory and the heap spilled into system memory: a Depths lava scene went from 12 ms to 60 ms of GPU time per frame and about 16 fps. Above tex_vram_pressure percent of the device-local budget (default 90, 0 = off), each submit now destroys up to 32 of the oldest released entries.
Only entries that come back intact are dropped: mirrored textures the GPU never wrote, which are uploaded again from their storage. A render target exists only in its image; dropping those made textures come back empty (black flashes in the Depths boss fight, about 170 "left uninitialised" aliases a minute).
Adds the setting to totk.ini and the Advanced tab, and a perf log line with the released count and drops.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
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.
Comments cited codes from local notes (port-lessons P1, backlog), task labels (T6c1-T6c3, M4), bare upstream commit
hashes and issue numbers, a file that no longer exists (nvn_api.c, now nvn_api_*.c), a generated file (main_0103.c)
and line numbers into upstream files that refs/ has moved past, so they pointed at unrelated code. Those now name the
file, function or project and say what the cited code does. Attribution of copied code keeps its pinned commits.
Corrected facts: TOTK_REPLAY_ASYNC defaults to 0, and the shader cache, pipeline cache and pipeline keys live next to
totk.exe, not in build/v121.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Comments named the agent task (T1-T7, M2-M5, Task 2.x) that once owned each file or block, and pointed at local
notes the repository does not carry (backlog items, milestone plans, research notes). They now say what the code
does. gfx_stubs.c held weak stand-ins for functions that every build has defined for a long time.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
TotK finalizes and initializes transient textures every frame: the global tex_gen and slots_gen moved about every 16
draws in the monsters fight, so every cache keyed on them (the slot cache in vk_texture_by_id_locked, the texture types
of answers_for, the texture descriptor memo) lived for a few draws. A slot resolves through the entries at its own
storage address only, so each address hash now has its own generation and each slot a token
(vk_texture_slot_token: registration serial and address generation, lock-free). The memos check the global generation
first and the slot's token only when it moved.
The descriptor memo no longer drops an entry at each submission (the first binding still makes the storage check; a
re-upload writes the same image) or pass (the feedback layout is set on each hit from the kept image), and is twice
the size. feedback_scan keeps each handle's sampled subresource across passes instead of looking up every fragment
texture after every texture bind. bind_vertex_buffers keeps each stream's resolved span while its range and
vk_mem_gen stay the same.
Monsters fight on the RX 9070: replay 12.0 -> 10.8 ms per frame; field 8.1 -> 7.4 ms. TOTK_TEX_MEMO=check and
TOTK_SHADER_MEMO=check runs found no difference.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Views made per command buffer were created anew every frame: vkCreateImageView under get_view took about 8% of the fight
replay on the 7900X. They now live in one table keyed as before, used under the texture lock, and destroy_tex hands an
image's views to the deferred release with the image (vk_exec_image_gone). The buffer range limits ubo_info and
ssbo_info read on every binding are read once. Fight replay 14.0 to 12.5 ms per frame (15.7 before the branch), field
9.5 to 9.2 ms; a fight run under the validation layer shows only the known cp_t_tcb_20 message.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A1B5G5R5 needs VK_KHR_maintenance5, so RGB5A1 stands in as A1R5G5B5 with R and B swapped by the view swizzle (TexVkFormat.chan); RGBA4 and RGB565 fall back the same way to mandatory formats on devices that lack A4B4G4R4 or B5G6R5. RGB5 and BGR5 now sample alpha as 1.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The point form of a sampler slot is built once (vk_sampler_point_by_id_locked). Translator patch 0009 rounds the 2DArrayShadow reference in Ryujinx's SPIR-V backend.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A guest WriteTexels of a small region deswizzled and reswizzled the whole level while its thread held a virtual core
and the texture lock: 80 ms preemption delays and 50-160 ms frames in the monsters2 replay (frames 765-790,
1225-1235), with the render thread waiting on the texture lock. nvn_texels_box copies the box alone; probe-vkmem
compares it with the whole-level path on random boxes of five block sizes, mip levels, array layers and 3D slices.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Imported pools put vertices, indices, constants and storage buffers in system memory, so discrete GPUs read them over
PCIe on every draw. A pool now gets a device-local mirror on its first use as a vertex, index, uniform, storage or
indirect buffer; bindings, buffer copies, fills and uniform updates use it at the same offsets. The first access of a
submission syncs the pages written since (write-watch snapshots shared with the texture checks, plus
nvnMemoryPoolFlushMappedRange ranges) in a prologue command buffer before the part; what the GPU writes into a mirror
goes back to guest memory at the end of the submission. TOTK_MEMORY=import|mirror|verify overrides the device class;
verify compares sampled mirror pages with guest memory at the fence. The vkexec probe gains a mirror part.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
nvn_pool_invalidate was a weak no-op, so nvnMemoryPoolInvalidateMappedRange never wrote anything back. TotK
invalidates its 260x260 R16 grass maps and 1x1 targets before reading them; they now go through guest_read.
The grass system also renders a 128x128 RGBA8 cut map into a CPU-cached pool every frame and reads it with no
invalidate. Without its texels the CPU saw no cut: swings left the grass standing, with no blades and no insects.
After nvnSyncWait or nvnQueueFinish, dirty mirrored targets up to 64 KiB rendered in a submission up to the waited
fence go back to storage (cpu_synced, vk_texture_write_back_small), unless the CPU rewrote it since.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>