Geekbench ML Score

418
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 14 2022 07:06 PM
Views 1

System Information

System Information
Operating System Android 13
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 333
35.7 IPS
 
Image Classification (F16)
100% 336
36.0 IPS
 
Image Classification (I8)
81% 173
18.5 IPS
 
Image Segmentation (F32)
100% 613
3.79 IPS
 
Image Segmentation (F16)
100% 598
3.70 IPS
 
Image Segmentation (I8)
89% 765
4.73 IPS
 
Pose Estimation (F32)
100% 293
1.19 IPS
 
Pose Estimation (F16)
100% 286
1.16 IPS
 
Pose Estimation (I8)
80% 231
0.93 IPS
 
Object Detection (F32)
100% 410
14.4 IPS
 
Object Detection (F16)
100% 406
14.2 IPS
 
Object Detection (I8)
52% 238
8.37 IPS
 
Face Detection (F32)
100% 637
7.32 IPS
 
Face Detection (F16)
100% 614
7.05 IPS
 
Face Detection (I8)
75% 462
5.30 IPS
 
Text Classification (F32)
100% 341
135.0 IPS
 
Text Classification (F16)
100% 379
150.0 IPS
 
Machine Translation (F32)
100% 820
126.3 IPS
 
Machine Translation (F16)
100% 819
126.3 IPS
 

Compare

Set Baseline