Geekbench ML Score

2249
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 02:19 AM
Views 6

System Information

System Information
Operating System Android 12
Model samsung SM-F936N
Model IDsamsung SM-F936N
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 2.02 GHz
Cluster 14 Cores @ 2.02 GHz
Cluster 23 Cores @ 2.75 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 10.99 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1809
193.9 IPS
 
Image Classification (F16)
100% 2491
266.9 IPS
 
Image Classification (I8)
80% 2326
249.2 IPS
 
Image Segmentation (F32)
100% 4491
27.7 IPS
 
Image Segmentation (F16)
100% 7720
47.7 IPS
 
Image Segmentation (I8)
89% 6742
41.6 IPS
 
Pose Estimation (F32)
100% 2160
8.74 IPS
 
Pose Estimation (F16)
100% 4135
16.7 IPS
 
Pose Estimation (I8)
80% 4112
16.6 IPS
 
Object Detection (F32)
100% 665
23.3 IPS
 
Object Detection (F16)
99% 1159
40.7 IPS
 
Object Detection (I8)
53% 945
33.2 IPS
 
Face Detection (F32)
100% 2971
34.1 IPS
 
Face Detection (F16)
97% 5424
62.3 IPS
 
Face Detection (I8)
75% 4474
51.4 IPS
 
Text Classification (F32)
100% 784
310.0 IPS
 
Text Classification (F16)
98% 1066
421.8 IPS
 
Machine Translation (F32)
100% 1111
171.3 IPS
 
Machine Translation (F16)
100% 1114
171.7 IPS
 

Compare

Set Baseline