Implement Native NVIDIA Reflex Low Latency (VK_NV_low_latency2)

- Enable VK_NV_low_latency2 and VK_KHR_present_id with present ID features
- Add VkSwapchainLatencyCreateInfoNV to swapchain creation
- Link present and submission IDs with standard Vulkan latency types
- Insert latency markers: simulation start/end, input sample, render submit, and present
- Gate all extensions and latency chains on reflex != off (RESTART setting)
- Log graceful notice when Reflex is requested on unsupported hardware
- Add UI menu setting and translations for en, ru, pt-BR, zh-Hans
- Document reflex setting in totk.ini.example and docs/settings.md
This commit is contained in:
Tears of the SteelTemple authored and itaskaev2 committed 2026-11-10 18:20:16 +01:00
1 parent 7a37fc3c34
commit 3209ea4358
12 files changed
+196 -9

No files matched your search

+1
View File
@@ -178,6 +178,7 @@ Many rows below are developer tools that only act together with another setting
| `mvprev_grow` (default `1`) | `0` keeps only three banks in the previous-frame tables. | Object motion that depends on the other banks is no longer tracked. | Caution |
| `mvprev_skip` | Hex bank mask of banks left out of the previous-frame copy, replacing the default. | Different banks are tracked, which changes object motion. | Caution |
| `mvprev_trust` | Hex bank mask of banks whose found previous-frame copy is taken without the check. | A copy that does not match is used anyway, which can give wrong motion. | Caution |
| `reflex` (default `off`) | `off`, `on`, or `boost`; enables NVIDIA Reflex Low Latency (`VK_NV_low_latency2`) to reduce system input latency. Read at start. | On NVIDIA GPUs supporting the extension, coordinates simulation and presentation cadence to lower latency; `boost` keeps GPU clocks high in CPU-bound scenes. Has no effect on non-NVIDIA GPUs. | Safe |
## Scheduling and host