Geekbench ML Score

3125
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 08:29 PM
Views 3

System Information

System Information
Operating System Android 12
Model samsung SM-S908U1
Model IDsamsung SM-S908U1
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.05 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1349
144.5 IPS
 
Image Classification (F16)
100% 9424
1.01 KIPS
 
Image Classification (I8)
80% 22940
2.46 KIPS
 
Image Segmentation (F32)
100% 2915
18.0 IPS
 
Image Segmentation (F16)
100% 8429
52.1 IPS
 
Image Segmentation (I8)
89% 41790
258.1 IPS
 
Pose Estimation (F32)
100% 599
2.42 IPS
 
Pose Estimation (F16)
100% 10414
42.1 IPS
 
Pose Estimation (I8)
80% 55501
224.6 IPS
 
Object Detection (F32)
100% 1034
36.3 IPS
 
Object Detection (F16)
100% 1796
63.0 IPS
 
Object Detection (I8)
53% 1990
69.8 IPS
 
Face Detection (F32)
100% 1999
23.0 IPS
 
Face Detection (F16)
97% 7050
81.0 IPS
 
Face Detection (I8)
76% 49780
571.9 IPS
 
Text Classification (F32)
100% 16
6.25 IPS
 
Text Classification (F16)
100% 580
229.4 IPS
 
Machine Translation (F32)
100% 1000
154.1 IPS
 
Machine Translation (F16)
100% 1016
156.6 IPS
 

Compare

Set Baseline