Relatório #154 benchmark
Atestado, aparelho bloqueado válido
- GPU
- Adreno (TM) 730
- Driver
- turnip_faux123_v1.1.9-rc14 Mesa 26.3.0-devel (git-dd45fd0baa)
- Aparelho
- Samsung Galaxy S22
- Chip
- SM8450
- CPU
- 4 x 1.79 GHz + 3 x 2.50 GHz + 1 x 3.00 GHz, arm64-v8a
- Memória
- 7.1 GB
- Informado como
- samsung / SM-S901U
- Recebido
- Android
- 16
- SHA-256 da biblioteca
- 8161e98ff95e1449935eaf6d3ed0a51d1b2fe4591576378f99b1fb2275077c76
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
- 1
- cooling_s
- 40
- cooling_capped
- 1
- test_budget_s
- 180
- test_s
- 176
- display_width
- 1080
- display_height
- 2340
- display_refresh_hz
- 120
- rounds
- 3
- scene_set
- 5
- 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.
Chip gráfico abaixo de 90% da velocidade máxima (clock da GPU) durante: pipeline_barriers_2160p, hdr_2160p. 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 | 24.09 | 24.27 | 24.92 | 3 | 0 | 818 de 818 MHz |
| subpasses | 4.66 | 4.73 | 5.23 | 3 | 0 | 790 de 818 MHz |
| compute_nbody | 9.16 | 9.12 | 9.91 | 3 | 0 | 753 de 818 MHz |
| pipeline_barriers | 3.01 | 3.06 | 3.59 | 3 | 0 | 740 de 818 MHz |
| subpasses_2160p | 17.27 | 17.55 | 19.56 | 3 | 3 | 776 de 818 MHz |
| pipeline_barriers_2160p | 11.59 | 11.68 | 13.31 | 3 | 3 | 678 de 818 MHz |
| hdr_2160p | 63.72 | 81.79 | 114.15 | 3 | 3 | 686 de 818 MHz |
Execuções individuais (21)
| Cena | Rodada | Estado | Mediana (ms) | Frames |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 24.12 | 214 |
| subpasses | 0 | ok | 4.66 | 1219 |
| compute_nbody | 0 | ok | 9.16 | 622 |
| pipeline_barriers | 0 | ok | 3.01 | 1874 |
| oit_linked_lists | 1 | ok | 24.09 | 213 |
| subpasses | 1 | ok | 4.95 | 1024 |
| compute_nbody | 1 | ok | 9.19 | 625 |
| pipeline_barriers | 1 | ok | 3.19 | 1753 |
| oit_linked_lists | 2 | ok | 27.23 | 171 |
| subpasses | 2 | ok | 6.76 | 839 |
| compute_nbody | 2 | ok | 11.20 | 496 |
| pipeline_barriers | 2 | ok | 3.67 | 1481 |
| subpasses_2160p | 0 | ok | 17.27 | 299 |
| pipeline_barriers_2160p | 0 | ok | 11.59 | 460 |
| hdr_2160p | 0 | ok | 63.72 | 49 |
| subpasses_2160p | 1 | ok | 32.13 | 155 |
| pipeline_barriers_2160p | 1 | ok | 21.24 | 249 |
| hdr_2160p | 1 | ok | 136.90 | 12 |
| subpasses_2160p | 2 | ok | 38.83 | 123 |
| pipeline_barriers_2160p | 2 | ok | 17.68 | 277 |
| hdr_2160p | 2 | ok | 113.60 | 21 |