Geekbench ML Score

695
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2021 10:23 PM
Views 5

System Information

System Information
Operating System Android 11
Model Samsung Galaxy S21 Ultra 5G
Model IDsamsung SM-G998B
Motherboard exynos2100
Governorenergy_step
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 2.21 GHz
Cluster 14 Cores @ 2.21 GHz
Cluster 23 Cores @ 2.81 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 10.31 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 451
48.3 IPS
 
Image Classification (F16)
100% 436
46.7 IPS
 
Image Classification (I8)
81% 374
40.1 IPS
 
Image Segmentation (F32)
100% 667
4.12 IPS
 
Image Segmentation (F16)
100% 657
4.06 IPS
 
Image Segmentation (I8)
89% 1595
9.85 IPS
 
Pose Estimation (F32)
100% 531
2.15 IPS
 
Pose Estimation (F16)
100% 1783
7.21 IPS
 
Pose Estimation (I8)
80% 1675
6.78 IPS
 
Object Detection (F32)
100% 554
19.4 IPS
 
Object Detection (F16)
99% 822
28.9 IPS
 
Object Detection (I8)
52% 433
15.2 IPS
 
Face Detection (F32)
100% 600
6.89 IPS
 
Face Detection (F16)
100% 575
6.61 IPS
 
Face Detection (I8)
75% 482
5.54 IPS
 
Text Classification (F32)
100% 902
356.8 IPS
 
Text Classification (F16)
100% 919
363.6 IPS
 
Machine Translation (F32)
100% 676
104.2 IPS
 
Machine Translation (F16)
100% 678
104.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download