Geekbench ML Score

291
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 24 2022 08:29 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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 229
24.6 IPS
 
Image Classification (F16)
100% 185
19.8 IPS
 
Image Classification (I8)
81% 173
18.5 IPS
 
Image Segmentation (F32)
100% 368
2.27 IPS
 
Image Segmentation (F16)
100% 361
2.23 IPS
 
Image Segmentation (I8)
89% 614
3.79 IPS
 
Pose Estimation (F32)
100% 214
0.87 IPS
 
Pose Estimation (F16)
100% 215
0.87 IPS
 
Pose Estimation (I8)
80% 149
0.60 IPS
 
Object Detection (F32)
100% 201
7.04 IPS
 
Object Detection (F16)
100% 190
6.67 IPS
 
Object Detection (I8)
52% 217
7.62 IPS
 
Face Detection (F32)
100% 358
4.11 IPS
 
Face Detection (F16)
100% 355
4.08 IPS
 
Face Detection (I8)
75% 399
4.58 IPS
 
Text Classification (F32)
100% 351
138.8 IPS
 
Text Classification (F16)
100% 344
136.0 IPS
 
Machine Translation (F32)
100% 571
87.9 IPS
 
Machine Translation (F16)
100% 570
87.8 IPS
 

Compare

Set Baseline