Geekbench ML Score

439
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 15 2022 12:09 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-S908B
Model IDsamsung SM-S908B
Motherboard s5e9925
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.82 GHz
Cluster 14 Cores @ 1.82 GHz
Cluster 23 Cores @ 2.52 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 203
21.8 IPS
 
Image Classification (F16)
100% 145
15.5 IPS
 
Image Classification (I8)
81% 451
48.3 IPS
 
Image Segmentation (F32)
100% 559
3.45 IPS
 
Image Segmentation (F16)
100% 553
3.41 IPS
 
Image Segmentation (I8)
89% 816
5.04 IPS
 
Pose Estimation (F32)
100% 298
1.21 IPS
 
Pose Estimation (F16)
100% 289
1.17 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 321
11.3 IPS
 
Object Detection (F16)
100% 216
7.58 IPS
 
Object Detection (I8)
52% 502
17.6 IPS
 
Face Detection (F32)
100% 427
4.91 IPS
 
Face Detection (F16)
100% 375
4.30 IPS
 
Face Detection (I8)
75% 609
6.99 IPS
 
Text Classification (F32)
100% 1126
445.2 IPS
 
Text Classification (F16)
100% 1131
447.5 IPS
 
Machine Translation (F32)
100% 960
147.9 IPS
 
Machine Translation (F16)
100% 982
151.4 IPS
 

Compare

Set Baseline