Geekbench ML Score

1068
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2021 10:42 PM
Views 4

System Information

System Information
Operating System Android 11
Model Samsung Galaxy S21 Ultra 5G
Model IDsamsung SM-G998U1
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 10.07 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 991
106.2 IPS
 
Image Classification (F16)
100% 1794
192.2 IPS
 
Image Classification (I8)
79% 4945
529.8 IPS
 
Image Segmentation (F32)
100% 2424
15.0 IPS
 
Image Segmentation (F16)
71% 3605
22.3 IPS
 
Image Segmentation (I8)
89% 10451
64.6 IPS
 
Pose Estimation (F32)
100% 574
2.32 IPS
 
Pose Estimation (F16)
100% 2022
8.18 IPS
 
Pose Estimation (I8)
80% 24266
98.2 IPS
 
Object Detection (F32)
100% 841
29.5 IPS
 
Object Detection (F16)
100% 1135
39.8 IPS
 
Object Detection (I8)
56% 1559
54.7 IPS
 
Face Detection (F32)
100% 571
6.56 IPS
 
Face Detection (F16)
100% 590
6.78 IPS
 
Face Detection (I8)
76% 21201
243.6 IPS
 
Text Classification (F32)
100% 9
3.54 IPS
 
Text Classification (F16)
46% 6
2.26 IPS
 
Machine Translation (F32)
100% 584
89.9 IPS
 
Machine Translation (F16)
100% 468
72.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download