Added a demo video link for DLSS Ultra Performance and removed duplicate mention.
This commit is contained in:
ayo authored and GitHub committed 2026-09-27 17:23:31 -04:00
1 parent 818dd8bf42
commit 508312ebf9
1 file changed
+2 -2
+2 -2
View File
@@ -8,6 +8,8 @@ It is an experiment. It has been tested on one GPU in two games, it depends on u
## Results ## Results
[DLSS Ultra Performance demo video](https://cdn.ayois.gay/dlss).
Radeon RX 7700 XT (RDNA3, gfx1101), SILENT HILL Townfall at 2560×1440, the same 62-second street walk for every run, frame rates from MangoHud frametime logs. Every DLSS result is presented in the frame it belongs to (no added latency). Radeon RX 7700 XT (RDNA3, gfx1101), SILENT HILL Townfall at 2560×1440, the same 62-second street walk for every run, frame rates from MangoHud frametime logs. Every DLSS result is presented in the frame it belongs to (no added latency).
| Mode | DLSS 3 CNN (preset E) | DLSS 4 (preset K) | DLSS 4.5 (preset M) | FSR 4 | | Mode | DLSS 3 CNN (preset E) | DLSS 4 (preset K) | DLSS 4.5 (preset M) | FSR 4 |
@@ -17,8 +19,6 @@ Radeon RX 7700 XT (RDNA3, gfx1101), SILENT HILL Townfall at 2560×1440, the same
| Performance (1280×720) | **87.8** | 84.0 | 69.9 | 94.0 | | Performance (1280×720) | **87.8** | 84.0 | 69.9 | 94.0 |
| Ultra Performance (853×480) | 88.9 | **94.5** | 90.3 | 107.3 | | Ultra Performance (853×480) | 88.9 | **94.5** | 90.3 | 107.3 |
[DLSS Ultra Performance demo video](https://cdn.ayois.gay/dlss).
For reference, native 2560×1440 without upscaling (the game's TSR at 100%) runs at 49.1 fps on the same walk. For reference, native 2560×1440 without upscaling (the game's TSR at 100%) runs at 49.1 fps on the same walk.
On the same GPU DLSS starts at a disadvantage: its networks were designed for NVIDIA's tensor cores, and parts of them still run as translated NVIDIA code. How the numbers were measured, and what each optimisation contributed, is in [docs/performance.md](docs/performance.md). On the same GPU DLSS starts at a disadvantage: its networks were designed for NVIDIA's tensor cores, and parts of them still run as translated NVIDIA code. How the numbers were measured, and what each optimisation contributed, is in [docs/performance.md](docs/performance.md).