首页 / PanVK-G77 MC9 / mali-panvk-27.0.0-devel-r10

报告 #1859 跑分

已认证，设备已锁定无效

速度得分

没有速度得分：驱动没能完成测试的全部内容。

GPU: PanVK-G77 MC9
驱动: mali-panvk-27.0.0-devel-r10 Mesa 27.0.0-devel (git-58f2c55854)
设备: Infinix ZERO 30 5G
芯片: MT6891
CPU: 4 x 2.00 GHz + 4 x 2.60 GHz, arm64-v8a
内存: 11.2 GB
上报为: INFINIX / Infinix X6731
收到时间: 2026-11-06 14:20 UTC
Android: 14
库文件 SHA-256: 80acd461bdf07f5fb99af5c7f516e272103340b6775c22dcd347a6d418c7ac0d

无效 oit_linked_lists round 0: timed frame 4 ran past 1000 ms (1010 ms), so the scene was stopped; oit_linked_lists round 1: timed frame 3673 ran past 1000 ms (1004 ms), so the scene was stopped; oit_linked_lists round 2: timed frame 2375 ran past 1000 ms (1009 ms), so the scene was stopped; oit_linked_lists reported in 0 of 3 rounds; subpasses round 0: timed frame 120 ran past 1000 ms (1016 ms), so the scene was stopped; subpasses round 1: timed frame 176 ran past 1000 ms (1017 ms), so the scene was stopped; subpasses round 2: timed frame 113 ran past 1000 ms (1010 ms), so the scene was stopped; subpasses reported in 0 of 3 rounds; compute_nbody round 0: timed frame 16 ran past 1000 ms (1001 ms), so the scene was stopped; compute_nbody round 1: timed frame 10 ran past 1000 ms (1018 ms), so the scene was stopped; compute_nbody round 2: timed frame 31 ran past 1000 ms (1018 ms), so the scene was stopped; compute_nbody reported in 0 of 3 rounds; pipeline_barriers round 0: timed frame 189 ran past 1000 ms (1008 ms), so the scene was stopped; pipeline_barriers round 1: timed frame 320 ran past 1000 ms (1010 ms), so the scene was stopped; pipeline_barriers round 2: timed frame 304 ran past 1000 ms (1004 ms), so the scene was stopped; pipeline_barriers reported in 0 of 3 rounds

原始 JSON

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
cooling_pauses: 0
cooling_s: 0
cooling_capped: 0
test_budget_s: 180
test_s: 102
system_log_unreadable: True
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.

场景

场景	中位数 ms	平均 ms	p95 ms	GPU 频率
oit_linked_lists	n/a	n/a	n/a	未记录
subpasses	n/a	n/a	n/a	未记录
compute_nbody	n/a	n/a	n/a	未记录
pipeline_barriers	n/a	n/a	n/a	未记录
hdr_2160p	n/a	n/a	n/a	未记录

单次运行（15）

场景	轮	状态	中位数 ms
oit_linked_lists	0	hung	n/a
subpasses	0	hung	n/a
compute_nbody	0	hung	n/a
pipeline_barriers	0	hung	n/a
oit_linked_lists	1	hung	n/a
subpasses	1	hung	n/a
compute_nbody	1	hung	n/a
pipeline_barriers	1	hung	n/a
oit_linked_lists	2	hung	n/a
subpasses	2	hung	n/a
compute_nbody	2	hung	n/a
pipeline_barriers	2	hung	n/a
hdr_2160p	0	hung	n/a
hdr_2160p	1	hung	n/a
hdr_2160p	2	hung	n/a