Geekbench ML Score

1488
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 15 2022 01:17 AM
Views 1

System Information

System Information
Operating System Android 12
Model OPPO CPH2207
Model IDOPPO CPH2207
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 11.24 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1066
114.3 IPS
 
Image Classification (F16)
100% 1877
201.1 IPS
 
Image Classification (I8)
80% 1555
166.6 IPS
 
Image Segmentation (F32)
100% 2985
18.4 IPS
 
Image Segmentation (F16)
100% 5267
32.5 IPS
 
Image Segmentation (I8)
89% 4794
29.6 IPS
 
Pose Estimation (F32)
100% 1541
6.24 IPS
 
Pose Estimation (F16)
100% 2713
11.0 IPS
 
Pose Estimation (I8)
80% 2685
10.9 IPS
 
Object Detection (F32)
100% 587
20.6 IPS
 
Object Detection (F16)
99% 824
28.9 IPS
 
Object Detection (I8)
53% 693
24.3 IPS
 
Face Detection (F32)
100% 2126
24.4 IPS
 
Face Detection (F16)
97% 3665
42.1 IPS
 
Face Detection (I8)
76% 3150
36.2 IPS
 
Text Classification (F32)
100% 493
194.9 IPS
 
Text Classification (F16)
98% 554
219.3 IPS
 
Machine Translation (F32)
100% 568
87.5 IPS
 
Machine Translation (F16)
100% 569
87.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download