報告 #1559 跑分
已認證，裝置已鎖定 有效
- GPU
- Adreno (TM) 660
- 驅動程式
- turnip_faux123_v1.2.1-rc4 Mesa 26.3.0-devel (git-dd45fd0baa)
- 裝置
- Samsung Galaxy S21+ 5G
- 晶片
- SM8350
- CPU
- 4 x 1.80 GHz + 3 x 2.42 GHz + 1 x 2.84 GHz, arm64-v8a
- 記憶體
- 7.2 GB
- 回報為
- samsung / SM-G996U1
- 收到時間
- Android
- 15
- 函式庫檔案 SHA-256
- 025b7cae3b63ba95b7f9ec73e9d8484b34122233cf2a94bd639c97781c03c445
測試條件
- 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
- 150
- system_log_unreadable
- False
- display_width
- 1080
- display_height
- 2400
- 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.
測試期間繪圖晶片頻率低於峰值的 90%（GPU 頻率）：compute_nbody。可能是裝置壓住了繪圖晶片（發熱或省電模式），也可能是場景太輕，用不著更高頻率。這些資料只適合和頻率相近的測試比較。
場景
| 場景 | 中位數 ms | 平均 ms | p95 ms | 輪次 | 開測時已發熱 | GPU 頻率 |
|---|---|---|---|---|---|---|
| oit_linked_lists | 30.03 | 29.98 | 30.19 | 3 | 0 | 840 / 840 MHz |
| subpasses | 6.04 | 6.08 | 6.95 | 3 | 0 | 830 / 840 MHz |
| compute_nbody | 11.26 | 11.05 | 13.08 | 3 | 0 | 686 / 840 MHz |
| pipeline_barriers | 3.70 | 3.74 | 4.16 | 3 | 0 | 809 / 840 MHz |
| subpasses_2160p | 22.99 | 22.89 | 23.82 | 3 | 0 | 809 / 840 MHz |
| pipeline_barriers_2160p | 14.18 | 14.16 | 14.83 | 3 | 0 | 765 / 840 MHz |
| hdr_2160p | 35.01 | 34.97 | 35.17 | 3 | 0 | 840 / 840 MHz |
單次執行（21）
| 場景 | 輪 | 狀態 | 中位數 ms | 幀數 |
|---|---|---|---|---|
| oit_linked_lists | 0 | ok | 30.07 | 166 |
| subpasses | 0 | ok | 6.04 | 940 |
| compute_nbody | 0 | ok | 11.26 | 518 |
| pipeline_barriers | 0 | ok | 3.70 | 1531 |
| oit_linked_lists | 1 | ok | 30.03 | 165 |
| subpasses | 1 | ok | 6.34 | 911 |
| compute_nbody | 1 | ok | 11.94 | 486 |
| pipeline_barriers | 1 | ok | 3.83 | 1515 |
| oit_linked_lists | 2 | ok | 30.03 | 163 |
| subpasses | 2 | ok | 6.42 | 899 |
| compute_nbody | 2 | ok | 12.03 | 487 |
| pipeline_barriers | 2 | ok | 3.88 | 1497 |
| subpasses_2160p | 0 | ok | 22.99 | 232 |
| pipeline_barriers_2160p | 0 | ok | 14.18 | 373 |
| hdr_2160p | 0 | ok | 35.05 | 137 |
| subpasses_2160p | 1 | ok | 24.67 | 216 |
| pipeline_barriers_2160p | 1 | ok | 14.55 | 361 |
| hdr_2160p | 1 | ok | 35.01 | 137 |
| subpasses_2160p | 2 | ok | 24.92 | 213 |
| pipeline_barriers_2160p | 2 | ok | 14.73 | 357 |
| hdr_2160p | 2 | ok | 35.06 | 136 |