Geekbench ML Score

302
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 01 2022 07:38 AM
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 244
26.1 IPS
 
Image Classification (F16)
100% 129
13.8 IPS
 
Image Classification (I8)
81% 158
17.0 IPS
 
Image Segmentation (F32)
100% 397
2.45 IPS
 
Image Segmentation (F16)
100% 411
2.54 IPS
 
Image Segmentation (I8)
89% 697
4.31 IPS
 
Pose Estimation (F32)
100% 250
1.01 IPS
 
Pose Estimation (F16)
100% 251
1.02 IPS
 
Pose Estimation (I8)
80% 183
0.74 IPS
 
Object Detection (F32)
100% 176
6.17 IPS
 
Object Detection (F16)
100% 179
6.29 IPS
 
Object Detection (I8)
52% 202
7.09 IPS
 
Face Detection (F32)
100% 413
4.75 IPS
 
Face Detection (F16)
100% 446
5.12 IPS
 
Face Detection (I8)
75% 377
4.33 IPS
 
Text Classification (F32)
100% 255
100.8 IPS
 
Text Classification (F16)
100% 350
138.3 IPS
 
Machine Translation (F32)
100% 717
110.6 IPS
 
Machine Translation (F16)
100% 718
110.6 IPS
 

Compare

Set Baseline