Geekbench ML Score

438
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 27 2022 06:07 PM
Views 4

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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 143
15.3 IPS
 
Image Classification (F16)
100% 266
28.5 IPS
 
Image Classification (I8)
81% 450
48.2 IPS
 
Image Segmentation (F32)
100% 556
3.43 IPS
 
Image Segmentation (F16)
100% 576
3.56 IPS
 
Image Segmentation (I8)
89% 819
5.06 IPS
 
Pose Estimation (F32)
100% 298
1.20 IPS
 
Pose Estimation (F16)
100% 294
1.19 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 217
7.60 IPS
 
Object Detection (F16)
100% 210
7.39 IPS
 
Object Detection (I8)
52% 500
17.6 IPS
 
Face Detection (F32)
100% 395
4.53 IPS
 
Face Detection (F16)
100% 405
4.65 IPS
 
Face Detection (I8)
75% 604
6.94 IPS
 
Text Classification (F32)
100% 1130
447.1 IPS
 
Text Classification (F16)
100% 1140
450.8 IPS
 
Machine Translation (F32)
100% 1005
155.0 IPS
 
Machine Translation (F16)
100% 1001
154.2 IPS
 

Compare

Set Baseline Geekbench 6 now available