Geekbench ML Score

424
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 15 2022 02:08 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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 336
36.0 IPS
 
Image Classification (F16)
100% 333
35.7 IPS
 
Image Classification (I8)
81% 174
18.6 IPS
 
Image Segmentation (F32)
100% 588
3.63 IPS
 
Image Segmentation (F16)
100% 592
3.66 IPS
 
Image Segmentation (I8)
89% 755
4.66 IPS
 
Pose Estimation (F32)
100% 295
1.19 IPS
 
Pose Estimation (F16)
100% 287
1.16 IPS
 
Pose Estimation (I8)
80% 239
0.97 IPS
 
Object Detection (F32)
100% 401
14.1 IPS
 
Object Detection (F16)
100% 411
14.4 IPS
 
Object Detection (I8)
52% 266
9.32 IPS
 
Face Detection (F32)
100% 633
7.28 IPS
 
Face Detection (F16)
100% 629
7.23 IPS
 
Face Detection (I8)
75% 477
5.49 IPS
 
Text Classification (F32)
100% 363
143.5 IPS
 
Text Classification (F16)
100% 287
113.5 IPS
 
Machine Translation (F32)
100% 970
149.5 IPS
 
Machine Translation (F16)
100% 968
149.3 IPS
 

Compare

Set Baseline Geekbench 6 now available