Geekbench ML Score

401
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 05 2022 05:32 PM
Views 2

System Information

System Information
Operating System Android 12
Model samsung SM-S908B
Model IDsamsung SM-S908B
Motherboard s5e9925
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.82 GHz
Cluster 14 Cores @ 1.82 GHz
Cluster 23 Cores @ 2.52 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 7.13 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 121
13.0 IPS
 
Image Classification (F16)
100% 100
10.7 IPS
 
Image Classification (I8)
81% 451
48.3 IPS
 
Image Segmentation (F32)
100% 533
3.29 IPS
 
Image Segmentation (F16)
100% 553
3.42 IPS
 
Image Segmentation (I8)
89% 822
5.08 IPS
 
Pose Estimation (F32)
100% 298
1.20 IPS
 
Pose Estimation (F16)
100% 292
1.18 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 175
6.15 IPS
 
Object Detection (F16)
100% 175
6.15 IPS
 
Object Detection (I8)
52% 501
17.6 IPS
 
Face Detection (F32)
100% 378
4.34 IPS
 
Face Detection (F16)
100% 390
4.48 IPS
 
Face Detection (I8)
75% 614
7.05 IPS
 
Text Classification (F32)
100% 1156
457.1 IPS
 
Text Classification (F16)
100% 1157
457.5 IPS
 
Machine Translation (F32)
100% 1011
155.7 IPS
 
Machine Translation (F16)
100% 997
153.6 IPS
 

Compare

Set Baseline Geekbench 6 now available