Geekbench ML Score

3162
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 27 2022 04:35 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% 1317
141.1 IPS
 
Image Classification (F16)
100% 9085
973.5 IPS
 
Image Classification (I8)
80% 21071
2.26 KIPS
 
Image Segmentation (F32)
100% 2851
17.6 IPS
 
Image Segmentation (F16)
100% 8354
51.6 IPS
 
Image Segmentation (I8)
89% 41504
256.4 IPS
 
Pose Estimation (F32)
100% 620
2.51 IPS
 
Pose Estimation (F16)
100% 10387
42.0 IPS
 
Pose Estimation (I8)
80% 54845
221.9 IPS
 
Object Detection (F32)
100% 1031
36.2 IPS
 
Object Detection (F16)
100% 1794
63.0 IPS
 
Object Detection (I8)
53% 2007
70.4 IPS
 
Face Detection (F32)
100% 2028
23.3 IPS
 
Face Detection (F16)
97% 7046
80.9 IPS
 
Face Detection (I8)
76% 47287
543.3 IPS
 
Text Classification (F32)
100% 17
6.62 IPS
 
Text Classification (F16)
100% 807
319.2 IPS
 
Machine Translation (F32)
100% 1023
157.7 IPS
 
Machine Translation (F16)
100% 1020
157.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download