Geekbench ML Score

443
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 26 2022 03:25 PM
Views 3

System Information

System Information
Operating System Android 13
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% 270
28.9 IPS
 
Image Classification (F16)
100% 266
28.5 IPS
 
Image Classification (I8)
81% 247
26.5 IPS
 
Image Segmentation (F32)
100% 399
2.47 IPS
 
Image Segmentation (F16)
100% 401
2.48 IPS
 
Image Segmentation (I8)
89% 451
2.78 IPS
 
Pose Estimation (F32)
100% 314
1.27 IPS
 
Pose Estimation (F16)
100% 302
1.22 IPS
 
Pose Estimation (I8)
80% 144
0.58 IPS
 
Object Detection (F32)
100% 310
10.9 IPS
 
Object Detection (F16)
100% 314
11.0 IPS
 
Object Detection (I8)
52% 504
17.7 IPS
 
Face Detection (F32)
100% 524
6.02 IPS
 
Face Detection (F16)
100% 522
5.99 IPS
 
Face Detection (I8)
75% 614
7.06 IPS
 
Text Classification (F32)
100% 1163
459.9 IPS
 
Text Classification (F16)
100% 1163
460.1 IPS
 
Machine Translation (F32)
100% 1007
155.1 IPS
 
Machine Translation (F16)
100% 997
153.7 IPS
 

Compare

Set Baseline Geekbench 6 now available