Geekbench ML Score

366
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 03 2022 03:53 AM
Views 2

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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 163
17.4 IPS
 
Image Classification (F16)
100% 135
14.5 IPS
 
Image Classification (I8)
81% 174
18.7 IPS
 
Image Segmentation (F32)
100% 502
3.10 IPS
 
Image Segmentation (F16)
100% 501
3.09 IPS
 
Image Segmentation (I8)
89% 811
5.01 IPS
 
Pose Estimation (F32)
100% 327
1.32 IPS
 
Pose Estimation (F16)
100% 324
1.31 IPS
 
Pose Estimation (I8)
80% 248
1.00 IPS
 
Object Detection (F32)
100% 390
13.7 IPS
 
Object Detection (F16)
100% 280
9.82 IPS
 
Object Detection (I8)
52% 224
7.85 IPS
 
Face Detection (F32)
100% 543
6.24 IPS
 
Face Detection (F16)
100% 509
5.85 IPS
 
Face Detection (I8)
75% 409
4.70 IPS
 
Text Classification (F32)
100% 306
121.2 IPS
 
Text Classification (F16)
100% 298
117.7 IPS
 
Machine Translation (F32)
100% 996
153.5 IPS
 
Machine Translation (F16)
100% 994
153.1 IPS
 

Compare

Set Baseline Geekbench 6 now available