Geekbench ML Score

408
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 16 2022 03:21 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% 138
14.8 IPS
 
Image Classification (F16)
100% 110
11.8 IPS
 
Image Classification (I8)
81% 450
48.3 IPS
 
Image Segmentation (F32)
100% 565
3.49 IPS
 
Image Segmentation (F16)
100% 546
3.38 IPS
 
Image Segmentation (I8)
89% 821
5.07 IPS
 
Pose Estimation (F32)
100% 300
1.22 IPS
 
Pose Estimation (F16)
100% 290
1.17 IPS
 
Pose Estimation (I8)
80% 140
0.56 IPS
 
Object Detection (F32)
100% 194
6.82 IPS
 
Object Detection (F16)
100% 174
6.10 IPS
 
Object Detection (I8)
52% 502
17.6 IPS
 
Face Detection (F32)
100% 386
4.43 IPS
 
Face Detection (F16)
100% 378
4.34 IPS
 
Face Detection (I8)
75% 612
7.03 IPS
 
Text Classification (F32)
100% 1149
454.5 IPS
 
Text Classification (F16)
100% 1153
455.9 IPS
 
Machine Translation (F32)
100% 981
151.2 IPS
 
Machine Translation (F16)
100% 989
152.3 IPS
 

Compare

Set Baseline