Geekbench ML Score

359
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 15 2022 12:04 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% 481
51.6 IPS
 
Image Classification (F16)
100% 151
16.2 IPS
 
Image Classification (I8)
81% 168
18.0 IPS
 
Image Segmentation (F32)
100% 505
3.12 IPS
 
Image Segmentation (F16)
100% 470
2.91 IPS
 
Image Segmentation (I8)
89% 768
4.75 IPS
 
Pose Estimation (F32)
100% 315
1.27 IPS
 
Pose Estimation (F16)
100% 307
1.24 IPS
 
Pose Estimation (I8)
80% 244
0.99 IPS
 
Object Detection (F32)
100% 206
7.24 IPS
 
Object Detection (F16)
100% 207
7.25 IPS
 
Object Detection (I8)
52% 212
7.45 IPS
 
Face Detection (F32)
100% 527
6.06 IPS
 
Face Detection (F16)
100% 479
5.50 IPS
 
Face Detection (I8)
75% 421
4.83 IPS
 
Text Classification (F32)
100% 289
114.2 IPS
 
Text Classification (F16)
100% 255
101.1 IPS
 
Machine Translation (F32)
100% 991
152.8 IPS
 
Machine Translation (F16)
100% 988
152.3 IPS
 

Compare

Set Baseline