Geekbench ML Score

348
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 22 2022 08:47 PM
Views 1

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 CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 373
40.0 IPS
 
Image Classification (F16)
100% 128
13.7 IPS
 
Image Classification (I8)
81% 166
17.8 IPS
 
Image Segmentation (F32)
100% 509
3.14 IPS
 
Image Segmentation (F16)
100% 481
2.97 IPS
 
Image Segmentation (I8)
89% 760
4.69 IPS
 
Pose Estimation (F32)
100% 329
1.33 IPS
 
Pose Estimation (F16)
100% 317
1.28 IPS
 
Pose Estimation (I8)
80% 247
1.00 IPS
 
Object Detection (F32)
100% 205
7.18 IPS
 
Object Detection (F16)
100% 178
6.26 IPS
 
Object Detection (I8)
52% 217
7.60 IPS
 
Face Detection (F32)
100% 445
5.12 IPS
 
Face Detection (F16)
100% 479
5.50 IPS
 
Face Detection (I8)
75% 443
5.09 IPS
 
Text Classification (F32)
100% 274
108.3 IPS
 
Text Classification (F16)
100% 259
102.5 IPS
 
Machine Translation (F32)
100% 998
153.8 IPS
 
Machine Translation (F16)
100% 1000
154.2 IPS
 

Compare

Set Baseline Geekbench 6 now available