Geekbench ML Score

411
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 13 2022 09:07 PM
Views 2

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% 352
37.7 IPS
 
Image Classification (F16)
100% 339
36.3 IPS
 
Image Classification (I8)
81% 174
18.6 IPS
 
Image Segmentation (F32)
100% 605
3.74 IPS
 
Image Segmentation (F16)
100% 634
3.92 IPS
 
Image Segmentation (I8)
89% 718
4.44 IPS
 
Pose Estimation (F32)
100% 306
1.24 IPS
 
Pose Estimation (F16)
100% 300
1.21 IPS
 
Pose Estimation (I8)
80% 226
0.91 IPS
 
Object Detection (F32)
100% 418
14.7 IPS
 
Object Detection (F16)
100% 427
15.0 IPS
 
Object Detection (I8)
52% 243
8.52 IPS
 
Face Detection (F32)
100% 643
7.39 IPS
 
Face Detection (F16)
100% 638
7.32 IPS
 
Face Detection (I8)
75% 449
5.16 IPS
 
Text Classification (F32)
100% 248
98.2 IPS
 
Text Classification (F16)
100% 320
126.4 IPS
 
Machine Translation (F32)
100% 797
122.9 IPS
 
Machine Translation (F16)
100% 797
122.8 IPS
 

Compare

Set Baseline