Geekbench ML Score

448
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 15 2022 12:20 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 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 300
32.1 IPS
 
Image Classification (F16)
100% 505
54.1 IPS
 
Image Classification (I8)
81% 309
33.1 IPS
 
Image Segmentation (F32)
100% 423
2.61 IPS
 
Image Segmentation (F16)
100% 420
2.60 IPS
 
Image Segmentation (I8)
89% 563
3.47 IPS
 
Pose Estimation (F32)
100% 303
1.23 IPS
 
Pose Estimation (F16)
100% 287
1.16 IPS
 
Pose Estimation (I8)
80% 138
0.56 IPS
 
Object Detection (F32)
100% 377
13.2 IPS
 
Object Detection (F16)
100% 218
7.67 IPS
 
Object Detection (I8)
52% 497
17.4 IPS
 
Face Detection (F32)
100% 392
4.51 IPS
 
Face Detection (F16)
100% 380
4.36 IPS
 
Face Detection (I8)
75% 606
6.96 IPS
 
Text Classification (F32)
100% 1122
443.8 IPS
 
Text Classification (F16)
100% 1127
445.6 IPS
 
Machine Translation (F32)
100% 963
148.4 IPS
 
Machine Translation (F16)
100% 958
147.6 IPS
 

Compare

Set Baseline