Geekbench ML Score

286
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 05 2022 10:43 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 7.13 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 131
14.0 IPS
 
Image Classification (F16)
100% 120
12.8 IPS
 
Image Classification (I8)
81% 110
11.8 IPS
 
Image Segmentation (F32)
100% 453
2.80 IPS
 
Image Segmentation (F16)
100% 442
2.73 IPS
 
Image Segmentation (I8)
89% 737
4.55 IPS
 
Pose Estimation (F32)
100% 290
1.17 IPS
 
Pose Estimation (F16)
100% 289
1.17 IPS
 
Pose Estimation (I8)
80% 214
0.87 IPS
 
Object Detection (F32)
100% 169
5.94 IPS
 
Object Detection (F16)
100% 181
6.35 IPS
 
Object Detection (I8)
52% 189
6.63 IPS
 
Face Detection (F32)
100% 352
4.04 IPS
 
Face Detection (F16)
100% 338
3.89 IPS
 
Face Detection (I8)
75% 339
3.89 IPS
 
Text Classification (F32)
100% 338
133.8 IPS
 
Text Classification (F16)
100% 256
101.2 IPS
 
Machine Translation (F32)
100% 713
109.8 IPS
 
Machine Translation (F16)
100% 714
110.0 IPS
 

Compare

Set Baseline