Geekbench ML Score

417
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 01 2022 05:54 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 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 433
46.4 IPS
 
Image Classification (F16)
100% 426
45.7 IPS
 
Image Classification (I8)
81% 195
20.9 IPS
 
Image Segmentation (F32)
100% 696
4.30 IPS
 
Image Segmentation (F16)
100% 703
4.34 IPS
 
Image Segmentation (I8)
89% 909
5.61 IPS
 
Pose Estimation (F32)
100% 302
1.22 IPS
 
Pose Estimation (F16)
100% 291
1.18 IPS
 
Pose Estimation (I8)
80% 182
0.74 IPS
 
Object Detection (F32)
100% 311
10.9 IPS
 
Object Detection (F16)
100% 323
11.4 IPS
 
Object Detection (I8)
52% 234
8.21 IPS
 
Face Detection (F32)
100% 581
6.67 IPS
 
Face Detection (F16)
100% 564
6.48 IPS
 
Face Detection (I8)
75% 596
6.85 IPS
 
Text Classification (F32)
100% 294
116.1 IPS
 
Text Classification (F16)
100% 370
146.2 IPS
 
Machine Translation (F32)
100% 705
108.7 IPS
 
Machine Translation (F16)
100% 703
108.4 IPS
 

Compare

Set Baseline