Geekbench ML Score

491
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 04 2022 05:07 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 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 419
44.9 IPS
 
Image Classification (F16)
100% 431
46.2 IPS
 
Image Classification (I8)
81% 197
21.1 IPS
 
Image Segmentation (F32)
100% 707
4.37 IPS
 
Image Segmentation (F16)
100% 702
4.34 IPS
 
Image Segmentation (I8)
89% 908
5.61 IPS
 
Pose Estimation (F32)
100% 307
1.24 IPS
 
Pose Estimation (F16)
100% 304
1.23 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 511
17.9 IPS
 
Object Detection (F16)
100% 499
17.5 IPS
 
Object Detection (I8)
52% 320
11.2 IPS
 
Face Detection (F32)
100% 755
8.68 IPS
 
Face Detection (F16)
100% 750
8.62 IPS
 
Face Detection (I8)
75% 568
6.53 IPS
 
Text Classification (F32)
100% 411
162.6 IPS
 
Text Classification (F16)
100% 363
143.6 IPS
 
Machine Translation (F32)
100% 959
147.9 IPS
 
Machine Translation (F16)
100% 957
147.5 IPS
 

Compare

Set Baseline Geekbench 6 now available