Geekbench ML Score

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

Result Information

Upload Date August 13 2022 06:12 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 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 368
39.4 IPS
 
Image Classification (F16)
100% 138
14.8 IPS
 
Image Classification (I8)
81% 438
46.9 IPS
 
Image Segmentation (F32)
100% 551
3.40 IPS
 
Image Segmentation (F16)
100% 561
3.46 IPS
 
Image Segmentation (I8)
89% 779
4.81 IPS
 
Pose Estimation (F32)
100% 280
1.13 IPS
 
Pose Estimation (F16)
100% 276
1.12 IPS
 
Pose Estimation (I8)
80% 130
0.53 IPS
 
Object Detection (F32)
100% 216
7.58 IPS
 
Object Detection (F16)
100% 218
7.63 IPS
 
Object Detection (I8)
52% 485
17.0 IPS
 
Face Detection (F32)
100% 437
5.02 IPS
 
Face Detection (F16)
100% 416
4.78 IPS
 
Face Detection (I8)
75% 592
6.80 IPS
 
Text Classification (F32)
100% 1110
439.0 IPS
 
Text Classification (F16)
100% 1125
444.8 IPS
 
Machine Translation (F32)
100% 962
148.2 IPS
 
Machine Translation (F16)
100% 978
150.7 IPS
 

Compare

Set Baseline