Informe n.º 1133 benchmark
Sin verificar válido 
Colaborador supremo
Colaborador supremo- GPU
- Adreno (TM) 740
- Driver
- turnip_faux123_v1.2.0 Mesa 26.3.0-devel (git-dd45fd0baa)
- Dispositivo
- Samsung Galaxy S23
- Chip
- SM8550
- CPU
- 3 x 2.02 GHz + 4 x 2.80 GHz + 1 x 3.36 GHz, arm64-v8a
- Memoria
- 6.9 GB
- Informado como
- samsung / SM-S911U1
- Recibido
- Android
- 16
- SHA-256 de la biblioteca
- 47761a30ffdb063938c354d83246534c7f905807e0116a0402b5d88e73d5ad89
Condiciones
- seconds_per_scene
- 6
- warmup_frames
- 30
- warmup_max_ms
- 2000
- warmup_min_frames
- 5
- render_width
- 1920
- render_height
- 1080
- heavy_width
- 3840
- heavy_height
- 2160
- heavy_below_ms
- 8
- heavy_particles
- 2
- cool_rule
- status_below_2_and_full_gpu_limit
- cooling_pauses
- 2
- cooling_s
- 18
- cooling_capped
- 2
- test_budget_s
- 180
- test_s
- 174
- system_log_unreadable
- False
- display_width
- 1080
- display_height
- 2340
- display_refresh_hz
- 120
- rounds
- 3
- scene_set
- 6
- hdr_format
- R16G16B16A16_SFLOAT
- 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. hdr runs at the larger picture only. Compare drivers on one device; across devices, compare only rows that kept the GPU busy.
GPU por debajo del 90% de su velocidad máxima (reloj de la GPU) durante: compute_nbody, pipeline_barriers, hdr_2160p. El dispositivo estaba frenando la GPU (por calor o por un modo de ahorro de energía), o la escena es demasiado ligera para necesitar más. Compara estas cifras solo con una prueba hecha a un reloj parecido.
Escenas
| Escena | Mediana (ms) | Media (ms) | p95 (ms) | Rondas | Empezó caliente | Reloj de la GPU |
|---|---|---|---|---|---|---|
| oit_linked_lists | 25.14 | 25.14 | 25.63 | 3 | 0 | 719 de 719 MHz |
| subpasses | 3.56 | 3.58 | 3.84 | 3 | 0 | 719 de 719 MHz |
| compute_nbody | 8.17 | 7.97 | 8.79 | 3 | 0 | 500 de 719 MHz |
| pipeline_barriers | 2.23 | 2.25 | 2.56 | 3 | 0 | 636 de 719 MHz |
| subpasses_2160p | 12.83 | 12.85 | 13.60 | 3 | 0 | 719 de 719 MHz |
| pipeline_barriers_2160p | 7.64 | 7.78 | 8.64 | 3 | 0 | 667 de 719 MHz |
| hdr_2160p | 15.24 | 15.36 | 16.07 | 3 | 0 | 549 de 615 MHz |
| compute_nbody_2x | 17.00 | 16.99 | 17.90 | 3 | 0 | 669 de 680 MHz |
Ejecuciones individuales (24)
| Escena | Ronda | Estado | Mediana (ms) | Fotogramas |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 25.32 | 199 |
| subpasses | 0 | ok | 3.57 | 1624 |
| compute_nbody | 0 | ok | 15.58 | 363 |
| pipeline_barriers | 0 | ok | 2.23 | 2555 |
| oit_linked_lists | 1 | ok | 25.14 | 204 |
| subpasses | 1 | ok | 3.56 | 1647 |
| compute_nbody | 1 | ok | 8.17 | 719 |
| pipeline_barriers | 1 | ok | 2.23 | 2549 |
| oit_linked_lists | 2 | ok | 25.36 | 204 |
| subpasses | 2 | ok | 3.57 | 1645 |
| compute_nbody | 2 | ok | 15.68 | 362 |
| pipeline_barriers | 2 | ok | 2.24 | 2484 |
| subpasses_2160p | 0 | ok | 12.83 | 418 |
| pipeline_barriers_2160p | 0 | ok | 7.64 | 710 |
| hdr_2160p | 0 | ok | 15.24 | 314 |
| subpasses_2160p | 1 | ok | 14.68 | 376 |
| pipeline_barriers_2160p | 1 | ok | 8.50 | 645 |
| hdr_2160p | 1 | ok | 15.36 | 312 |
| subpasses_2160p | 2 | ok | 15.01 | 359 |
| pipeline_barriers_2160p | 2 | ok | 8.51 | 635 |
| hdr_2160p | 2 | ok | 15.25 | 334 |
| compute_nbody_2x | 0 | ok | 17.00 | 305 |
| compute_nbody_2x | 1 | ok | 18.63 | 273 |
| compute_nbody_2x | 2 | ok | 19.73 | 254 |