Relatório #52 benchmark
Atestado, aparelho bloqueado válido 
Supremo apoiador
Supremo apoiador- GPU
- Adreno (TM) 740
- Driver
- turnip_faux123_v1.1.9-rc13 Mesa 26.3.0-devel (git-dd45fd0baa)
- Aparelho
- Samsung Galaxy S23
- Chip
- SM8550
- CPU
- 3 x 2.02 GHz + 4 x 2.80 GHz + 1 x 3.36 GHz, arm64-v8a
- Memória
- 6.9 GB
- Informado como
- samsung / SM-S911U1
- Recebido
- Android
- 16
- SHA-256 da biblioteca
- 49de278a13c27a6e1ead2293e4e4b2c4475b5289ee67b28ee81c18781023baf3
Condições
- 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
- cool_rule
- status_below_2_and_full_gpu_limit
- cooling_pauses
- 2
- cooling_s
- 38
- cooling_capped
- 1
- test_budget_s
- 180
- test_s
- 174
- 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 gráfico abaixo de 90% da velocidade máxima (clock da GPU) durante: compute_nbody. O aparelho estava segurando o chip gráfico (calor ou modo de economia de energia), ou a cena é leve demais para precisar de mais. Compare esses números só com uma execução em clock parecido.
Cenas
| Cena | Mediana (ms) | Média (ms) | p95 (ms) | Rodadas | Começou quente | Clock da GPU |
|---|---|---|---|---|---|---|
| oit_linked_lists | 26.26 | 26.26 | 26.47 | 3 | 0 | 719 de 719 MHz |
| subpasses | 3.56 | 3.57 | 3.83 | 3 | 0 | 719 de 719 MHz |
| compute_nbody | 7.56 | 7.56 | 8.22 | 3 | 0 | 561 de 719 MHz |
| pipeline_barriers | 2.20 | 2.22 | 2.49 | 3 | 0 | 712 de 719 MHz |
| subpasses_2160p | 12.83 | 12.84 | 13.70 | 3 | 0 | 719 de 719 MHz |
| pipeline_barriers_2160p | 8.17 | 7.90 | 8.69 | 3 | 0 | 667 de 719 MHz |
| compute_nbody_2x | 20.78 | 20.63 | 21.46 | 3 | 0 | 615 de 615 MHz |
Execuções individuais (21)
| Cena | Rodada | Estado | Mediana (ms) | Frames |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 26.26 | 195 |
| subpasses | 0 | ok | 3.56 | 1649 |
| compute_nbody | 0 | ok | 7.58 | 760 |
| pipeline_barriers | 0 | ok | 2.20 | 2596 |
| oit_linked_lists | 1 | ok | 27.39 | 185 |
| subpasses | 1 | ok | 3.80 | 1525 |
| compute_nbody | 1 | ok | 7.59 | 752 |
| pipeline_barriers | 1 | ok | 2.33 | 2477 |
| oit_linked_lists | 2 | ok | 29.99 | 173 |
| subpasses | 2 | ok | 4.17 | 1403 |
| compute_nbody | 2 | ok | 7.56 | 749 |
| pipeline_barriers | 2 | ok | 2.56 | 2266 |
| subpasses_2160p | 0 | ok | 12.83 | 426 |
| pipeline_barriers_2160p | 0 | ok | 8.17 | 700 |
| subpasses_2160p | 1 | ok | 15.04 | 358 |
| pipeline_barriers_2160p | 1 | ok | 8.52 | 646 |
| subpasses_2160p | 2 | ok | 15.03 | 359 |
| pipeline_barriers_2160p | 2 | ok | 8.54 | 633 |
| compute_nbody_2x | 0 | ok | 20.78 | 258 |
| compute_nbody_2x | 1 | ok | 20.78 | 258 |
| compute_nbody_2x | 2 | ok | 20.93 | 254 |