diff --git a/.claude/skills/run-game/SKILL.md b/.claude/skills/run-game/SKILL.md index 701a230e..2efc4122 100644 --- a/.claude/skills/run-game/SKILL.md +++ b/.claude/skills/run-game/SKILL.md @@ -22,6 +22,7 @@ prints `: rc=`. The game window opens behind the user's windows witho | `user-save-2026-10-21-monsters` | Moblins and Zonai constructs attack at once; use with `--script tools/input/fight.txt` | | `user-save-2026-10-21` | Hyrule field facing the castle, rainy; distant sky over the castle | | `user-save-2026-10-23-pillars` | Hyrule field by standing stone pillars, about 17:40, a Zonai construct beside Link; use with `--script tools/input/backrun.txt` (runs backward from 1550: phantom rocks, a one-frame glitch at about 1605) | +| `user-save-2026-10-24-brightbloom` | Cave, about 20:40: a Brightbloom plant at the lower left (its bulb floats beside the stem, `build/v121-bloom/NOTES.md`), teal Moblin and Bokoblin ahead or Zonai constructs (runs differ) | | `user-save-2026-10-22-island` | Sky island edge; use with `--script tools/input/island.txt` (runs off, skydives, opens the paraglider with B at frame 1975; X does nothing in a dive) | `--frames` counts presents. Pick `1500 + the frames you need in-world`. diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md index 15464cdc..a14ce1cf 100644 --- a/THIRD_PARTY_NOTICES.md +++ b/THIRD_PARTY_NOTICES.md @@ -6,9 +6,10 @@ Code copied or adapted from another project is listed here with its source, the |---|---|---|---| | MacNativeGames extraction scripts and verification hashes | https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11`, Copyright (c) 2026 MacNativeGames contributors | MIT | `tools/vendor/macnativegames/` (unmodified), `tools/data/expected-v*.json` | | LAS Recomp lifter, code generator, FP/SIMD lowering, CPU headers and differential tests | https://github.com/peiikai/LASRecomp @ `da35b83a9611d046a9a681aae668d7085954d37f`, Copyright (c) 2026 Peiikai | MIT | `recomp/lifter.py`, `recomp/simd_c.py`, `recomp/nso.py`, `recomp/gen.py`, `recomp/module.py`, `tests/jumptables_check.py`, `runtime/cpu.h`, `runtime/simd.h`, `runtime/simd_fp.h`, `tests/diff/` | -| LAS Recomp host runtime: NSO loader, host-function table, guest-space reservation and re-execution, guest thread start | https://github.com/peiikai/LASRecomp @ `da35b83a9611d046a9a681aae668d7085954d37f`, Copyright (c) 2026 Peiikai | MIT | `runtime/loader.c`, `runtime/hostfn.c`, `runtime/memory.c`; M3 tasks T2 and T6: `runtime/kernel.c`, `runtime/boot.c`; M4 T2: `runtime/vk_device.c`, `runtime/gfx_window.c`, M4 T5a: `runtime/tex_astc.c` (`runtime/nvn/astc.c`), `runtime/vk_formats.c` (format table of `runtime/nvn/vulkan/textures.c`), M4 T5b: `runtime/vk_memory.c` (page write generations of `runtime/nvn/vulkan/exec.c`, deferred destruction of `textures.c`), `runtime/vk_texture.c` (image creation, uploads and samplers of `runtime/nvn/vulkan/textures.c`), M4 T6a: `runtime/vk_sync.c` (timeline submissions and waits of `runtime/nvn/vulkan/exec.c`), M4 T6b: `runtime/vk_pipeline.c` (blend, compare and stencil mappings, vertex format table with its 3-component fallback and pipeline cache file of `runtime/nvn/vulkan/exec.c` and `device.c`), M4 T6c1: `runtime/vk_exec.c` (pass begin and end, scissor clip and attachment clears of `runtime/nvn/vulkan/exec.c`), M4 T6c3: `runtime/vk_exec_xfer.c` (copies of `runtime/nvn/vulkan/exec.c`), M4 T6c2: `runtime/vk_exec_draw.c` (uniform buffer spans, texture and sampler descriptors and dispatch flow of `runtime/nvn/vulkan/exec.c`) | +| LAS Recomp host runtime: NSO loader, host-function table, guest-space reservation and re-execution, guest thread start | https://github.com/peiikai/LASRecomp @ `da35b83a9611d046a9a681aae668d7085954d37f`, Copyright (c) 2026 Peiikai | MIT | `runtime/loader.c`, `runtime/hostfn.c`, `runtime/memory.c`; M3 tasks T2 and T6: `runtime/kernel.c`, `runtime/boot.c`; M4 T2: `runtime/vk_device.c`, `runtime/gfx_window.c`, M4 T5a: `runtime/tex_astc.c` (`runtime/nvn/astc.c`; its decode ported to GLSL in `runtime/shaders/astc_decode.comp`, compiled into `runtime/astc_decode_spv.h`, and its tables copied into `runtime/vk_astc.c`), `runtime/vk_formats.c` (format table of `runtime/nvn/vulkan/textures.c`), M4 T5b: `runtime/vk_memory.c` (page write generations of `runtime/nvn/vulkan/exec.c`, deferred destruction of `textures.c`), `runtime/vk_texture.c` (image creation, uploads and samplers of `runtime/nvn/vulkan/textures.c`), M4 T6a: `runtime/vk_sync.c` (timeline submissions and waits of `runtime/nvn/vulkan/exec.c`), M4 T6b: `runtime/vk_pipeline.c` (blend, compare and stencil mappings, vertex format table with its 3-component fallback and pipeline cache file of `runtime/nvn/vulkan/exec.c` and `device.c`), M4 T6c1: `runtime/vk_exec.c` (pass begin and end, scissor clip and attachment clears of `runtime/nvn/vulkan/exec.c`), M4 T6c3: `runtime/vk_exec_xfer.c` (copies of `runtime/nvn/vulkan/exec.c`), M4 T6c2: `runtime/vk_exec_draw.c` (uniform buffer spans, texture and sampler descriptors and dispatch flow of `runtime/nvn/vulkan/exec.c`) | | MacNativeGames TotK host runtime: dynamic linking, identity check, module permissions, guest memory and SVCs, threads, IPC, audio renderer, system services, RomFS and save storage, boot sequence | https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/runtime/`, `games/totk/scripts/prepare_runtime.py`), Copyright (c) 2026 MacNativeGames contributors | MIT | `runtime/loader.c`, `runtime/memory.c`; M3 tasks T2-T6: `runtime/kernel.c`, `runtime/svc.c`, `runtime/ipc.c`, `runtime/ipc.h`, `runtime/audren.c`, `runtime/audren.h`, `runtime/audio_mixer.c`, `runtime/audio_effects.c`, `runtime/audio_effects.h`, `runtime/audio_reverb.c`, `runtime/audio_reverb.h` (M5; SDL3 output replaces CoreAudio), `runtime/ov_system.c` (also `shared_font.c`: the BFTTF layout behind nn::pl), `runtime/ov_input.c` (also `hid_feedback.c`: vibration and six-axis handles and calls), `runtime/motion_fusion.c` (six-axis fusion of `motion_fusion.c`), `runtime/ov_media.c` (M5: hardware Opus decoder over libopus), `runtime/swkbd_win.c` (`swkbd_host.c`: ShowKeyboardArg offsets, UTF-8/UTF-16 conversion, disabled-key filter, result codes; Win32 window replaces the macOS text bar), `runtime/ov_gfx.c`, `runtime/romfs.c`, `runtime/romfs_path.h`, `runtime/fs_host.c`, `runtime/fs.h`, `runtime/boot.c`; M4 T2: `runtime/gfx_window.c` | | MacNativeGames TotK frame-rate patches: 60 fps present-interval controller, real-time frame step and its present sampling, hair and cloth clock, trampoline slow-motion check (instruction words and 1.2.1 sites), player position chain; quick-menu capture background RomFS overlay | https://github.com/ly05010419/MacNativeGames @ `ebe621de99bfc48f3c42f2d2aa73e04fbcc6eae2` (`games/totk/runtime/game_patches.c`, `game_version.h`, `world_survey.c`, `games/totk/scripts/make_romfs_patches.py`), Copyright (c) 2026 MacNativeGames contributors | MIT | `runtime/frame_rate.c`, `recomp/patches-v121.txt`, `tools/make_romfs_patches.py` | +| MacNativeGames TotK virtual-core preemption: asynchronous preemption of an owner in top-level game code, priority inheritance through guest mutexes, the SDK's preemption-disable protocol (TLR+0x100/+0x102, SVC 0x36), the core-wait diagnostics | https://github.com/ly05010419/MacNativeGames @ `33e8fa83052ea1ae09a3583137008e9797e12950` (`games/totk/runtime/threads.c`, commits 8bf0893 and 19730cd), Copyright (c) 2026 MacNativeGames contributors | MIT | `runtime/kernel.c` (SuspendThread and a register-saving stub replace SIGUSR2), `runtime/hostfn.c`, `runtime/svc.c` (host depth) | | MacNativeGames RomFS index builder (`TOTKRFS1` layout) | https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/scripts/prepare_romfs_backend.py`), Copyright (c) 2026 MacNativeGames contributors | MIT | `tools/romfs_index.py` | | d2r-mobile host thread environment (TLR, TLS, thread object), the origin of MacNativeGames' thread layer; d2r-mobile NVN host object layouts, command record format and NVN front end, as adapted for TotK in MacNativeGames' `d2r_gfx` copy | https://github.com/jhaizhou-ops/d2r-mobile @ `53e7c5bb9ca3ea53e2160005be8fbe920cd9cb53` (`dm/host/thread.c`, `dm/host/hle_thread.c`); the NVN layouts and front end via https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/third_party/d2r_gfx/gfx/nvn/nvn_obj.h`, the two types of `nvn_tex.h`, `hle_nvn.c`, `totk_nvn_ext.c`, `nvn_impl.h`, `nvn_hmap.h`, `nvn_pool_index.h`, the request checks and mapping semantics of `totk_vpool.c`, the generation stamps of `nvn_dirty.c`, texture mirroring and texel copies of `nvn_mtl.m`; licence in `games/totk/third_party/d2r_gfx/LICENSE`), Copyright (c) 2026 jhaizhou | MIT | M3 task T2: `runtime/kernel.c`; M4 task T1: `runtime/nvn_obj.h`; M4 task T3c: `runtime/nvn_api.h`, `runtime/nvn_api_core.c`, `runtime/nvn_hmap.h`, `runtime/nvn_pool_index.h`; M4 task T3d: `runtime/nvn_api_obj.c` (also `nvn_pace.h`); M4 task T3e: `runtime/nvn_api_cmd.c`, `runtime/nvn_ext.c`; M4 task T5b: `runtime/vk_memory.c`, `runtime/vk_texture.c`; M4 task T6a: `runtime/vk_sync.c` (side effects written after GPU completion, `hle_nvn.c`); M4 task T6b: `runtime/vk_pipeline.c` (pipeline key and state mapping of `nvn_mtl.m` `pso_key_fill` / `pso_desc`, its `vfmt` vertex formats and the missing-varying fix-up of `msl_varyings`); M4 task T6c1: `runtime/vk_exec.c`, `runtime/vk_exec.h` (op loop, pure-state ops and state defaults of `nvn_mtl.m` `mtl_exec` / `state_op` / `state_reset`); M4 task T6c3: `runtime/vk_exec_xfer.c` (copy, clear, event, counter and conditional-render semantics of `nvn_mtl.m` `copy_t2b` / `copy_b2t` / `copy_t2t` / `clear_tex` / `cond_eval`); M4 task T6c2: `runtime/vk_exec_draw.c` (bind ops, draw and dispatch flow, vertex streams of `nvn_mtl.m` `state_op` / `bind_vertex_streams` / `draw_inner` / `dispatch`) | | nxnative NVN front end (d2r-mobile's successor): texture view depth-stencil mode bits, stencil-view rule, `Downsample` and indirect draw and dispatch records | https://github.com/seedds/nxnative @ `d5b380b3a80495609c2e751bb994911a638935ad` (`dm/gfx/nvn/hle_nvn.c`, `nvn_obj.h`, `nvn_mtl.m`), Copyright (c) 2026 jhaizhou | MIT | M5: `runtime/nvn_obj.h`, `runtime/nvn_ext.c`, `runtime/nvn_api_cmd.c`, `runtime/vk_exec_draw.c` | @@ -19,7 +20,7 @@ Code copied or adapted from another project is listed here with its source, the | deko3d block-linear image layout, as ported in MacNativeGames' `nvn_tex.c` (Apple parts dropped, layout math unchanged; licence text in `games/totk/third_party/d2r_gfx/LICENSE.deko3d`, reproduced in the file header) | https://github.com/devkitPro/deko3d (`source/dk_image.cpp`), via MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/third_party/d2r_gfx/gfx/nvn/nvn_tex.c`, `nvn_tex.h`), Copyright (C) 2018-2020 fincs | zlib | M4 task T3b: `runtime/nvn_tex.c`, `runtime/nvn_tex.h` | | MacNativeGames texture auto-layout goldens (40 original-SDK size and block-height cases) | https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/tests/texture_auto_layout/probe.c`), Copyright (c) 2026 jhaizhou | MIT | M4 task T3b: `runtime/nvn_tex_probe.c`; T3f: `runtime/nvn_probe.c` (four of the cases, through the procs) | | MacNativeGames block-linear deswizzler (address function; copy loop split out as `tex_bl_copy`) | https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/third_party/d2r_gfx/gfx/tex/nvn_deswizzle.c`), Copyright (c) 2026 jhaizhou | MIT | M4 task T5a: `runtime/tex_deswizzle.c`, `runtime/tex.h` | -| SDL 3.4.18 (MSYS2 `mingw-w64-ucrt-x86_64-SDL3`), dynamic link, `SDL3.dll` and its dependency `libiconv-2.dll` (LGPL-2.1, unmodified, not linked into the exe) copied next to `totk.exe` | https://libsdl.org, Copyright (c) 1997-2026 Sam Lantinga | zlib | `runtime/input_win.c` (gamepad input, rumble, gyro and accelerometer) | +| SDL 3.4.18, dynamic link, `SDL3.dll` copied next to `totk.exe`. Developer builds use the MSYS2 build (`mingw-w64-ucrt-x86_64-sdl3`, which imports `libiconv-2.dll`, LGPL-2.1, unmodified, copied beside it); the installer release ships the upstream release `SDL3-3.4.18-win32-x64.zip`, which imports no libiconv | https://libsdl.org, Copyright (c) 1997-2026 Sam Lantinga | zlib | `runtime/input_win.c` (gamepad input, rumble, gyro and accelerometer) | | libopus (MSYS2 `mingw-w64-ucrt-x86_64-opus`), dynamic link, `libopus-0.dll` copied next to `totk.exe` | https://opus-codec.org, Copyright (c) 2001-2023 Xiph.Org, Skype Limited, Octasic, Jean-Marc Valin, Timothy B. Terriberry, CSIRO, Gregory Maxwell, Mark Borgerding, Erik de Castro Lopo, Mozilla, Amazon | BSD-3-Clause | `runtime/ov_media.c` (nn::codec hardware Opus decoder) | | Dear ImGui 1.91.9 (core and Vulkan back end, unmodified), as vendored by LAS Recomp | https://github.com/ocornut/imgui, via https://github.com/peiikai/LASRecomp @ `da35b83a9611d046a9a681aae668d7085954d37f` (`third_party/imgui/`), Copyright (c) 2014-2025 Omar Cornut | MIT | `runtime/third_party/imgui/` (for the in-game menu; not compiled yet) | | Vulkan Memory Allocator 3.4.0 (MSYS2 `mingw-w64-ucrt-x86_64-vulkan-memory-allocator`), header-only, compiled into `totk.exe` | https://github.com/GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator, Copyright (c) 2017-2026 Advanced Micro Devices, Inc. | MIT | `runtime/vk_vma.cpp` (the allocator behind `runtime/vk_memory.c`) | @@ -32,6 +33,26 @@ These tools run on the developer's or player's machine during the build. They ar | Tool | Source | License | Purpose | |---|---|---|---| -| hactool | https://github.com/SciresM/hactool @ `1d64a83450e025622f3468c28fc4164dad2c5ef6`, with patches from MacNativeGames | ISC | NCA and update container extraction | +| hactool (the installer release ships it, see below) | https://github.com/SciresM/hactool @ `1d64a83450e025622f3468c28fc4164dad2c5ef6`, with patches from MacNativeGames | ISC | NCA and update container extraction | | Capstone | https://www.capstone-engine.org | BSD-3-Clause | ARM64 disassembly for analysis | | Unicorn | https://www.unicorn-engine.org | GPL-2.0 (Python bindings BSD) | Differential testing of the lifter; never linked into the game | + +## Distributed in the installer release + +`tools/make_release.py` assembles these into the release folder of `docs/installer.md`. Versions and sha256 of every download are pinned in that script; licence texts are in the folder's `licenses/` and in each component's own folder. + +| Component | Source | License | Where in the release | +|---|---|---|---| +| CPython 3.14.9 embeddable package, with `tkinter` and Tcl/Tk 9.0.4 taken from the python.org 3.14.9 installer's component MSI (unpacked, never run); includes `vcruntime140*.dll` (Microsoft, redistributable with Python), OpenSSL, libffi, SQLite, zlib, libtommath | https://www.python.org/downloads/release/python-3149/ | PSF-2.0 (Tcl/Tk: Tcl/Tk licence, BSD-style) | `python/` | +| numpy 2.5.4 (with its bundled OpenBLAS), lz4 4.4.5, cryptography 50.0.2 (with its bundled OpenSSL), cffi 2.1.1, pycparser 3.11 | PyPI binary wheels, pins in `tools/requirements-installer.txt` | BSD-3-Clause; lz4 BSD-3-Clause; cryptography Apache-2.0 OR BSD-3-Clause; cffi MIT; pycparser BSD-3-Clause | `python/Lib/site-packages/` | +| llvm-mingw 20261020 (LLVM/Clang/LLD 23, mingw-w64, libc++, libunwind, compiler-rt), x86_64 subset | https://github.com/mstorsjo/llvm-mingw/releases/tag/20261020 | Apache-2.0 with LLVM exception; mingw-w64 ZPL-2.1/BSD/public domain; libc++ and libunwind Apache-2.0 with LLVM exception and MIT/UIUC; winpthreads MIT | `llvm/` | +| SDL 3.4.18 upstream Windows release (`SDL3.dll`) and mingw development package (headers, `libSDL3.dll.a`) | https://github.com/libsdl-org/SDL/releases/tag/release-3.4.18 | zlib | `bin/SDL3.dll`, `runtime/deps/` | +| libopus 1.6.1 (MSYS2 `mingw-w64-ucrt-x86_64-opus` 1.6.1-2; `libopus-0.dll` imports only KERNEL32 and the UCRT api-ms-win-crt DLLs), headers and import library | https://repo.msys2.org/mingw/ucrt64/ | BSD-3-Clause | `bin/libopus-0.dll`, `runtime/deps/` | +| libvpx 1.17.0 (MSYS2 `mingw-w64-ucrt-x86_64-libvpx` 1.17.0-1), headers and static library compiled into `totk.exe`; `libvpx-LICENSE.txt` and `libvpx-PATENTS.txt` come from the v1.17.0 source tag | https://github.com/webmproject/libvpx | BSD-3-Clause with the WebM patent grant | `runtime/deps/`, `licenses/` | +| Vulkan-Headers and Vulkan-Loader 1.4.363.0 (MSYS2 packages; headers and `libvulkan-1.dll.a` only, no loader DLL) | https://github.com/KhronosGroup | Apache-2.0 OR MIT | `runtime/deps/` | +| Vulkan Memory Allocator 3.4.0 (MSYS2 package), header | https://github.com/GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator | MIT | `runtime/deps/` | +| Ninja 1.13.2 (`ninja-win.zip`) | https://github.com/ninja-build/ninja/releases/tag/v1.13.2 | Apache-2.0 | `bin/ninja.exe` | +| hactool (SciresM @ `1d64a83450e025622f3468c28fc4164dad2c5ef6` plus MacNativeGames' `portable-patches.diff`: `MNG_TITLE_KEYS` and a relaxed BKTR size check; our `unicode-patches.diff`: an embedded manifest that makes UTF-8 the process code page), built with MSYS2 UCRT64 gcc; imports only KERNEL32 and the UCRT | https://github.com/SciresM/hactool | ISC | `bin/hactool.exe` | +| `totk_xlate.exe` (Ryujinx shader translator, NativeAOT build of `tools/xlate/`, see the Ryujinx row above) | built by `tools/build_xlate.py` | MIT | `bin/totk_xlate.exe` | +| MacNativeGames shader variant list | https://github.com/ly05010419/MacNativeGames @ `b75be8cfa704df3701e86130c8ced268e79d6b11` (`games/totk/assets/shader_list.tsv`), Copyright (c) 2026 MacNativeGames contributors | MIT | `data/shader_list.tsv` | + diff --git a/docs/agent-playbook.md b/docs/agent-playbook.md index 669a32e3..f20cee66 100644 --- a/docs/agent-playbook.md +++ b/docs/agent-playbook.md @@ -25,8 +25,20 @@ other `totk.exe` or `ninja.exe` runs. The log's first and last lines record the - `--env TOTK_TRACE=perf,sched`, then `python tools/perf_summary.py `: fps, max frame and the render-thread buckets per 60 frames. Per-thread run, core, host, lock and addr shares come per 120 presents. -- `TOTK_PROFILE=1 TOTK_PROFILE_FRAMES=lo-hi`: sampling profiler (`runtime/prof_win.c`). Resolve `exe+0x...` RVAs - with the build's `totk.map`. + A second `perf: frame N: gpu avg` line per window has the GPU busy time per frame (timestamp queries per submission + part, `vk_sync.c`; upload batches not included), fence waits of the render thread and of other threads, VRAM use and + budget (`VK_EXT_memory_budget`), process RAM and `bound: gpu|cpu|pace` (pace: the frame waited for pacing 15% of the + time or more; gpu: the GPU was busy 80% of the interval or more). +- The pool census (`mem: census`, `vk_memory.c` `vk_mem_census`) is logged at frame 1800, with `perf` every 1800 + frames: pools by kind and flags, and the bytes bound or copied per frame by pool class since frame 1200. Also at + frame 600. `mem: class` (once at start) says whether the GPU counts as uma or discrete and lists its heaps and types. +- With `perf`, `mem: dirty` every 60 frames: what a VRAM mirror of the buffer-bound pools would upload (pages the CPU + wrote per frame and per submit, eager and lazy, by pool class), FlushMappedRange calls and bytes, and the mirror + size. The dirty count costs about 1.1 ms of CPU per frame on the submitting thread here (3 ms on an 8th-gen i7); + `perf_summary.py` summarises it. +- `TOTK_PROFILE= TOTK_PROFILE_FRAMES=lo-hi`: sampling profiler (`runtime/prof_win.c`), read with + `tools/prof_report.py `. With `TOTK_PROFILE_RENDER=1` it samples the render thread only and keeps + call chains: the report adds inclusive time per function and the exe callers of the driver and system DLLs. - `tools/regress.py --base build/v121-m4 [--routes fight,rock,island,field] [--repeat 3] [--cold] [--validation] [--out dir]`: runs the routes through `run_game.py --quiet`, scores logs and `TOTK_SHOTS` frames (`tools/regress_score.py`, tested by `tests/regress_score_test.py`) and prints median and worst per metric. Run the candidate alone and judge it against @@ -55,11 +67,26 @@ RenderDoc cannot capture: the driver hides `VK_EXT_external_memory_host`. ## Other GPUs -The RX 9070 is the only GPU here; the build also has to run on NVIDIA and older AMD (Vega, wave64 only). New Vulkan code -queries the feature, extension, format or limit it uses and keeps a working path or a logged fallback when it is -missing (`vk_pipeline.c` provoking vertex and subgroup size pinning are examples). Never hard-code what this GPU +The RX 9070 is the only GPU agents can run; the build also has to run on NVIDIA and older AMD (Vega, wave64 only). New +Vulkan code queries the feature, extension, format or limit it uses and keeps a working path or a logged fallback when +it is missing (`vk_pipeline.c` provoking vertex and subgroup size pinning are examples). Never hard-code what this GPU reports: alignments, subgroup size, depth formats, `maxPushDescriptors`. +Numbers from this machine do not carry over. Measured on the user's other machines (2026-10-24/25, logs and analysis +in `build/mem-plan.md`): + +- GTX 1050 Ti (4 GiB, 214 MiB BAR, no ReBAR; i7 8th-10th gen) and RTX 3090 Ti: GPU time 110-120 ms per frame in the + world against 4.3 ms here, because the GPU reads imported host pools over PCIe. The VRAM mirror (cd6f490) brings + the 1050 Ti to 10-11 ms; that machine is now CPU-bound at 25-45 fps (replay 25-30 ms per frame, backlog 0b). +- The same write-watch scan costs about 3x the CPU time it costs here. +- NVIDIA has no ASTC: first texture uploads decode on the CPU, 0.4-0.7 s load frames (backlog 5a.2). +- `cannot alias its pool memory` fills its 16-line log limit on NVIDIA and on the RX 9070 alike (1920x1080, 1600x900, + 800x450 render targets); a suspect for the black patches of backlog 0a (`build/alias-plan.md`). + +A run on another machine goes through the user: copy `build/release/TotK-perf-log.vbs` next to the `totk.exe` you +hand over. It starts the game with `TOTK_TRACE=perf` and writes `logs\perf--