Geekbench ML Score

2769
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 10 2022 12:35 AM
Views 1

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% 588
63.0 IPS
 
Image Classification (F16)
100% 8542
915.2 IPS
 
Image Classification (I8)
80% 19275
2.07 KIPS
 
Image Segmentation (F32)
100% 1211
7.48 IPS
 
Image Segmentation (F16)
100% 7853
48.5 IPS
 
Image Segmentation (I8)
89% 35644
220.2 IPS
 
Pose Estimation (F32)
100% 594
2.40 IPS
 
Pose Estimation (F16)
100% 10681
43.2 IPS
 
Pose Estimation (I8)
80% 55704
225.4 IPS
 
Object Detection (F32)
100% 1036
36.3 IPS
 
Object Detection (F16)
100% 1799
63.1 IPS
 
Object Detection (I8)
53% 2002
70.2 IPS
 
Face Detection (F32)
100% 1999
23.0 IPS
 
Face Detection (F16)
97% 7180
82.5 IPS
 
Face Detection (I8)
76% 49538
569.1 IPS
 
Text Classification (F32)
100% 16
6.42 IPS
 
Text Classification (F16)
100% 580
229.4 IPS
 
Machine Translation (F32)
100% 927
142.9 IPS
 
Machine Translation (F16)
100% 959
147.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download