Geekbench ML Score

451
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 04 2022 04:01 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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 405
43.4 IPS
 
Image Classification (F16)
100% 156
16.7 IPS
 
Image Classification (I8)
81% 440
47.1 IPS
 
Image Segmentation (F32)
100% 584
3.61 IPS
 
Image Segmentation (F16)
100% 585
3.61 IPS
 
Image Segmentation (I8)
89% 793
4.90 IPS
 
Pose Estimation (F32)
100% 284
1.15 IPS
 
Pose Estimation (F16)
100% 280
1.13 IPS
 
Pose Estimation (I8)
80% 136
0.55 IPS
 
Object Detection (F32)
100% 225
7.89 IPS
 
Object Detection (F16)
100% 218
7.66 IPS
 
Object Detection (I8)
52% 486
17.0 IPS
 
Face Detection (F32)
100% 450
5.16 IPS
 
Face Detection (F16)
100% 447
5.14 IPS
 
Face Detection (I8)
75% 591
6.79 IPS
 
Text Classification (F32)
100% 1121
443.3 IPS
 
Text Classification (F16)
100% 1123
444.0 IPS
 
Machine Translation (F32)
100% 969
149.4 IPS
 
Machine Translation (F16)
100% 970
149.5 IPS
 

Compare

Set Baseline Geekbench 6 now available