Geekbench ML Score

3053
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 01:35 PM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-S906E
Model IDsamsung SM-S906E
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 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.06 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1282
137.3 IPS
 
Image Classification (F16)
100% 9223
988.2 IPS
 
Image Classification (I8)
80% 22327
2.39 KIPS
 
Image Segmentation (F32)
100% 2757
17.0 IPS
 
Image Segmentation (F16)
100% 7758
47.9 IPS
 
Image Segmentation (I8)
89% 38708
239.1 IPS
 
Pose Estimation (F32)
100% 597
2.41 IPS
 
Pose Estimation (F16)
100% 10753
43.5 IPS
 
Pose Estimation (I8)
80% 55074
222.8 IPS
 
Object Detection (F32)
100% 1003
35.2 IPS
 
Object Detection (F16)
100% 1768
62.0 IPS
 
Object Detection (I8)
53% 1975
69.3 IPS
 
Face Detection (F32)
100% 1938
22.3 IPS
 
Face Detection (F16)
97% 6916
79.5 IPS
 
Face Detection (I8)
76% 48258
554.4 IPS
 
Text Classification (F32)
100% 16
6.23 IPS
 
Text Classification (F16)
100% 575
227.6 IPS
 
Machine Translation (F32)
100% 1002
154.4 IPS
 
Machine Translation (F16)
100% 1005
154.9 IPS
 

Compare

Set Baseline