Geekbench ML Score

450
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 05 2022 10:20 AM
Views 3

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% 422
45.2 IPS
 
Image Classification (F16)
100% 434
46.5 IPS
 
Image Classification (I8)
81% 434
46.5 IPS
 
Image Segmentation (F32)
100% 661
4.08 IPS
 
Image Segmentation (F16)
100% 625
3.86 IPS
 
Image Segmentation (I8)
89% 704
4.35 IPS
 
Pose Estimation (F32)
100% 294
1.19 IPS
 
Pose Estimation (F16)
100% 282
1.14 IPS
 
Pose Estimation (I8)
80% 109
0.44 IPS
 
Object Detection (F32)
100% 333
11.7 IPS
 
Object Detection (F16)
100% 335
11.8 IPS
 
Object Detection (I8)
52% 378
13.3 IPS
 
Face Detection (F32)
100% 493
5.66 IPS
 
Face Detection (F16)
100% 454
5.21 IPS
 
Face Detection (I8)
75% 423
4.86 IPS
 
Text Classification (F32)
100% 796
314.9 IPS
 
Text Classification (F16)
100% 795
314.5 IPS
 
Machine Translation (F32)
100% 704
108.6 IPS
 
Machine Translation (F16)
100% 703
108.4 IPS
 

Compare

Set Baseline Geekbench 6 now available