报告 #697 跑分
- GPU
- Adreno (TM) 830
- 驱动
- turnip_faux123_v1.1.9-rc15 Mesa 26.3.0-devel (git-dd45fd0baa)
- 设备
- AYN Odin 3
- 芯片
- Snapdragon 8 Elite (CQ8725S)
- CPU
- 6 x 3.53 GHz + 2 x 4.32 GHz, arm64-v8a
- 内存
- 10.9 GB
- 上报为
- ayn / Odin3
- 收到时间
- Android
- 15
- 库文件 SHA-256
- ae899f7a9fe495faa67b02c7f7849c60e3c96bdc866cccb3362dbce79aac9d21
无效 oit_linked_lists round 0 started while the device reported thermal status 3; oit_linked_lists round 1 started while the device reported thermal status 3; oit_linked_lists round 2 started while the device reported thermal status 3; subpasses round 0 started while the device reported thermal status 3; subpasses round 1 started while the device reported thermal status 3; subpasses round 2 started while the device reported thermal status 3; compute_nbody round 0 started while the device reported thermal status 3; compute_nbody round 1 started while the device reported thermal status 3; compute_nbody round 2 started while the device reported thermal status 3; pipeline_barriers round 0 started while the device reported thermal status 3; pipeline_barriers round 1 started while the device reported thermal status 3; pipeline_barriers round 2 started while the device reported thermal status 3
测试条件
- 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
- 20
- cooling_capped
- 3
- test_budget_s
- 180
- test_s
- 173
- display_width
- 1080
- display_height
- 1920
- display_refresh_hz
- 60
- 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.
测试期间显卡芯片频率低于峰值的 90%(GPU 频率):subpasses, compute_nbody, pipeline_barriers, subpasses_2160p, pipeline_barriers_2160p, hdr_2160p, compute_nbody_2x。可能是设备压住了显卡芯片(发热或省电模式),也可能是场景太轻,用不着更高频率。这些数据只适合和频率相近的测试比较。
场景
| 场景 | 中位数 ms | 平均 ms | p95 ms | 轮次 | 开测时已发热 | GPU 频率 |
|---|---|---|---|---|---|---|
| oit_linked_lists | 17.51 | 17.53 | 17.71 | 3 | 3 | 1100 / 1100 MHz |
| subpasses | 2.64 | 2.75 | 3.50 | 3 | 3 | 934 / 1100 MHz |
| compute_nbody | 3.46 | 3.54 | 4.22 | 3 | 3 | 945 / 1100 MHz |
| pipeline_barriers | 1.59 | 1.70 | 2.45 | 3 | 3 | 922 / 1100 MHz |
| subpasses_2160p | 10.34 | 10.47 | 11.88 | 3 | 3 | 934 / 1100 MHz |
| pipeline_barriers_2160p | 5.97 | 6.47 | 7.62 | 3 | 3 | 900 / 1100 MHz |
| hdr_2160p | 16.45 | 16.52 | 17.64 | 3 | 3 | 934 / 1100 MHz |
| compute_nbody_2x | 12.94 | 12.98 | 13.65 | 3 | 3 | 900 / 1100 MHz |
单次运行(24)
| 场景 | 轮 | 状态 | 中位数 ms | 帧数 |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 17.51 | 305 |
| subpasses | 0 | ok | 2.76 | 2096 |
| compute_nbody | 0 | ok | 3.67 | 1535 |
| pipeline_barriers | 0 | ok | 1.59 | 3340 |
| oit_linked_lists | 1 | ok | 18.16 | 292 |
| subpasses | 1 | ok | 2.78 | 2038 |
| compute_nbody | 1 | ok | 3.80 | 1469 |
| pipeline_barriers | 1 | ok | 1.71 | 3125 |
| oit_linked_lists | 2 | ok | 19.27 | 278 |
| subpasses | 2 | ok | 2.64 | 2153 |
| compute_nbody | 2 | ok | 3.46 | 1635 |
| pipeline_barriers | 2 | ok | 1.66 | 3457 |
| subpasses_2160p | 0 | ok | 10.34 | 540 |
| pipeline_barriers_2160p | 0 | ok | 5.97 | 872 |
| hdr_2160p | 0 | ok | 16.45 | 323 |
| subpasses_2160p | 1 | ok | 10.39 | 531 |
| pipeline_barriers_2160p | 1 | ok | 6.02 | 874 |
| hdr_2160p | 1 | ok | 17.31 | 317 |
| subpasses_2160p | 2 | ok | 10.39 | 534 |
| pipeline_barriers_2160p | 2 | ok | 5.97 | 867 |
| hdr_2160p | 2 | ok | 17.38 | 316 |
| compute_nbody_2x | 0 | ok | 14.00 | 392 |
| compute_nbody_2x | 1 | ok | 12.94 | 424 |
| compute_nbody_2x | 2 | ok | 13.33 | 411 |