Geekbench ML Score

369
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 25 2022 05:15 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% 356
38.1 IPS
 
Image Classification (F16)
100% 324
34.8 IPS
 
Image Classification (I8)
81% 182
19.5 IPS
 
Image Segmentation (F32)
100% 501
3.09 IPS
 
Image Segmentation (F16)
100% 514
3.18 IPS
 
Image Segmentation (I8)
89% 709
4.38 IPS
 
Pose Estimation (F32)
100% 310
1.25 IPS
 
Pose Estimation (F16)
100% 315
1.27 IPS
 
Pose Estimation (I8)
80% 243
0.98 IPS
 
Object Detection (F32)
100% 224
7.85 IPS
 
Object Detection (F16)
100% 191
6.69 IPS
 
Object Detection (I8)
52% 217
7.61 IPS
 
Face Detection (F32)
100% 470
5.39 IPS
 
Face Detection (F16)
100% 437
5.02 IPS
 
Face Detection (I8)
75% 423
4.86 IPS
 
Text Classification (F32)
100% 282
111.5 IPS
 
Text Classification (F16)
100% 300
118.8 IPS
 
Machine Translation (F32)
100% 986
151.9 IPS
 
Machine Translation (F16)
100% 974
150.0 IPS
 

Compare

Set Baseline Geekbench 6 now available