Geekbench ML Score

3096
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User ett11
Upload Date June 27 2022 10:47 PM
Views 4

System Information

System Information
Operating System Android 12
Model samsung SM-S901U
Model IDsamsung SM-S901U
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% 1315
140.9 IPS
 
Image Classification (F16)
100% 8604
921.9 IPS
 
Image Classification (I8)
80% 18792
2.01 KIPS
 
Image Segmentation (F32)
100% 2813
17.4 IPS
 
Image Segmentation (F16)
100% 7811
48.2 IPS
 
Image Segmentation (I8)
89% 40327
249.1 IPS
 
Pose Estimation (F32)
100% 593
2.40 IPS
 
Pose Estimation (F16)
100% 10191
41.2 IPS
 
Pose Estimation (I8)
80% 54552
220.7 IPS
 
Object Detection (F32)
100% 1033
36.3 IPS
 
Object Detection (F16)
100% 1782
62.5 IPS
 
Object Detection (I8)
53% 1993
69.9 IPS
 
Face Detection (F32)
100% 1989
22.9 IPS
 
Face Detection (F16)
97% 7132
81.9 IPS
 
Face Detection (I8)
76% 47595
546.8 IPS
 
Text Classification (F32)
100% 17
6.68 IPS
 
Text Classification (F16)
100% 802
317.3 IPS
 
Machine Translation (F32)
100% 1004
154.7 IPS
 
Machine Translation (F16)
100% 1009
155.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download