报告 #1394 跑分
已认证，设备已锁定 有效
- GPU
- Adreno (TM) 740
- 驱动
- Turnip-v27.0.0-20261029 Mesa 27.0.0-devel (git-1c3a936490)
- 设备
- Samsung Galaxy S23+
- 芯片
- SM8550
- CPU
- 3 x 2.02 GHz + 4 x 2.80 GHz + 1 x 3.36 GHz, arm64-v8a
- 内存
- 6.9 GB
- 上报为
- samsung / SM-S916B
- 收到时间
- Android
- 16
- 库文件 SHA-256
- 053e3e613da2c4f842961c177f11607902d8cd6ac03aa824bff6b59e47eb211d
测试条件
- 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
- 1
- cooling_s
- 15
- cooling_capped
- 0
- test_budget_s
- 180
- test_s
- 151
- 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.
测试期间显卡芯片频率低于峰值的 90%（GPU 频率）：compute_nbody。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 | 25.50 | 25.56 | 25.98 | 3 | 0 | 719 / 719 MHz |
| subpasses | 3.62 | 3.63 | 3.91 | 3 | 0 | 719 / 719 MHz |
| compute_nbody | 8.28 | 8.09 | 8.78 | 3 | 0 | 498 / 719 MHz |
| pipeline_barriers | 2.16 | 2.18 | 2.47 | 3 | 0 | 719 / 719 MHz |
| subpasses_2160p | 13.13 | 13.13 | 13.55 | 3 | 0 | 719 / 719 MHz |
| pipeline_barriers_2160p | 7.26 | 7.33 | 7.59 | 3 | 0 | 719 / 719 MHz |
| hdr_2160p | 17.06 | 17.64 | 19.14 | 3 | 0 | 660 / 719 MHz |
单次运行（21）
| 场景 | 轮 | 状态 | 中位数 ms | 帧数 |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 25.52 | 199 |
| subpasses | 0 | ok | 4.39 | 1121 |
| compute_nbody | 0 | ok | 8.28 | 701 |
| pipeline_barriers | 0 | ok | 2.16 | 2596 |
| oit_linked_lists | 1 | ok | 25.79 | 198 |
| subpasses | 1 | ok | 3.62 | 1602 |
| compute_nbody | 1 | ok | 8.29 | 710 |
| pipeline_barriers | 1 | ok | 2.16 | 2585 |
| oit_linked_lists | 2 | ok | 25.50 | 199 |
| subpasses | 2 | ok | 3.63 | 1598 |
| compute_nbody | 2 | ok | 8.31 | 702 |
| pipeline_barriers | 2 | ok | 2.16 | 2648 |
| subpasses_2160p | 0 | ok | 13.13 | 410 |
| pipeline_barriers_2160p | 0 | ok | 7.26 | 751 |
| hdr_2160p | 0 | ok | 17.06 | 282 |
| subpasses_2160p | 1 | ok | 15.27 | 359 |
| pipeline_barriers_2160p | 1 | ok | 8.45 | 637 |
| hdr_2160p | 1 | ok | 18.65 | 270 |
| subpasses_2160p | 2 | ok | 15.35 | 352 |
| pipeline_barriers_2160p | 2 | ok | 8.47 | 650 |
| hdr_2160p | 2 | ok | 18.66 | 281 |