Geekbench ML Score

387
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 10 2022 10:41 AM
Views 5

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 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 174
18.7 IPS
 
Image Classification (F16)
100% 116
12.4 IPS
 
Image Classification (I8)
81% 294
31.5 IPS
 
Image Segmentation (F32)
100% 444
2.74 IPS
 
Image Segmentation (F16)
100% 431
2.66 IPS
 
Image Segmentation (I8)
89% 562
3.47 IPS
 
Pose Estimation (F32)
100% 301
1.22 IPS
 
Pose Estimation (F16)
100% 295
1.19 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 176
6.17 IPS
 
Object Detection (F16)
100% 177
6.21 IPS
 
Object Detection (I8)
52% 498
17.5 IPS
 
Face Detection (F32)
100% 458
5.26 IPS
 
Face Detection (F16)
100% 382
4.39 IPS
 
Face Detection (I8)
75% 610
7.01 IPS
 
Text Classification (F32)
100% 1119
442.7 IPS
 
Text Classification (F16)
100% 1136
449.2 IPS
 
Machine Translation (F32)
100% 953
146.9 IPS
 
Machine Translation (F16)
100% 948
146.2 IPS
 

Compare

Set Baseline Geekbench 6 now available