Report #20 benchmark
Attestato, dispositivo bloccato valido
- GPU
- Adreno (TM) 730
- Driver
- turnip_faux123_v1.1.9-rc13 Mesa 26.3.0-devel (git-dd45fd0baa)
- Dispositivo
- Samsung Galaxy S22
- Chip
- SM8450
- CPU
- 4 x 1.79 GHz + 3 x 2.50 GHz + 1 x 3.00 GHz, arm64-v8a
- Memoria
- 7.1 GB
- Riportato come
- samsung / SM-S901U
- Ricevuto
- Android
- 14
- SHA-256 della libreria
- 49de278a13c27a6e1ead2293e4e4b2c4475b5289ee67b28ee81c18781023baf3
Condizioni
- seconds_per_scene
- 6
- warmup_frames
- 30
- render_width
- 1920
- render_height
- 1080
- heavy_width
- 3840
- heavy_height
- 2160
- heavy_below_ms
- 8
- heavy_particles
- 2
- display_width
- 1080
- display_height
- 2340
- display_refresh_hz
- 120
- rounds
- 3
- scene_set
- 3
- vsync
- OFF
Every scene draws at 1920 by 1080, whatever the screen. A scene under 8.0 ms there is too light for the chip and runs again at a heavier load: at 3840 by 2160, as the row named with _2160p, or, for compute_nbody, with 2 times the particles, as the row named with _2x. Compare drivers on one device; across devices, compare only rows that kept the GPU busy.
Chip grafico sotto il 90% della sua velocità massima (clock della GPU) durante: compute_nbody, pipeline_barriers, pipeline_barriers_2160p. Il dispositivo teneva frenato il chip grafico (calore o modalità di risparmio energetico), oppure la scena è troppo leggera per richiedere di più. Confronta questi numeri solo con un test a un clock simile.
Scene
| Scena | Mediana (ms) | Media (ms) | p95 (ms) | Giri | Partito a caldo | Clock GPU |
|---|---|---|---|---|---|---|
| oit_linked_lists | 24.05 | 24.16 | 24.85 | 3 | 0 | 818 di 818 MHz |
| subpasses | 4.66 | 4.73 | 5.33 | 3 | 0 | 790 di 818 MHz |
| compute_nbody | 9.33 | 9.46 | 10.74 | 3 | 0 | 721 di 818 MHz |
| pipeline_barriers | 3.00 | 3.02 | 3.45 | 3 | 0 | 731 di 818 MHz |
| subpasses_2160p | 17.00 | 17.34 | 19.10 | 3 | 0 | 795 di 818 MHz |
| pipeline_barriers_2160p | 11.25 | 11.37 | 12.93 | 3 | 0 | 595 di 818 MHz |
Singole esecuzioni (18)
| Scena | Giro | Stato | Mediana (ms) | Frame |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 24.05 | 214 |
| subpasses | 0 | ok | 4.66 | 1218 |
| compute_nbody | 0 | ok | 9.33 | 602 |
| pipeline_barriers | 0 | ok | 3.00 | 1920 |
| oit_linked_lists | 1 | ok | 24.07 | 213 |
| subpasses | 1 | ok | 5.07 | 1144 |
| compute_nbody | 1 | ok | 10.88 | 536 |
| pipeline_barriers | 1 | ok | 3.07 | 1830 |
| oit_linked_lists | 2 | ok | 28.88 | 179 |
| subpasses | 2 | ok | 5.15 | 1018 |
| compute_nbody | 2 | ok | 10.97 | 513 |
| pipeline_barriers | 2 | ok | 5.06 | 1247 |
| subpasses_2160p | 0 | ok | 17.00 | 314 |
| pipeline_barriers_2160p | 0 | ok | 11.25 | 483 |
| subpasses_2160p | 1 | ok | 20.23 | 261 |
| pipeline_barriers_2160p | 1 | ok | 15.31 | 332 |
| subpasses_2160p | 2 | ok | 24.89 | 191 |
| pipeline_barriers_2160p | 2 | ok | 17.52 | 289 |