Geekbench ML Score

316
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 15 2022 12:13 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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 347
37.2 IPS
 
Image Classification (F16)
100% 212
22.7 IPS
 
Image Classification (I8)
81% 166
17.8 IPS
 
Image Segmentation (F32)
100% 382
2.36 IPS
 
Image Segmentation (F16)
100% 400
2.47 IPS
 
Image Segmentation (I8)
89% 742
4.59 IPS
 
Pose Estimation (F32)
100% 235
0.95 IPS
 
Pose Estimation (F16)
100% 234
0.95 IPS
 
Pose Estimation (I8)
80% 183
0.74 IPS
 
Object Detection (F32)
100% 183
6.41 IPS
 
Object Detection (F16)
100% 178
6.25 IPS
 
Object Detection (I8)
52% 223
7.84 IPS
 
Face Detection (F32)
100% 344
3.95 IPS
 
Face Detection (F16)
100% 395
4.54 IPS
 
Face Detection (I8)
75% 397
4.56 IPS
 
Text Classification (F32)
100% 342
135.1 IPS
 
Text Classification (F16)
100% 349
138.0 IPS
 
Machine Translation (F32)
100% 702
108.2 IPS
 
Machine Translation (F16)
100% 703
108.3 IPS
 

Compare

Set Baseline