Geekbench ML Score

157
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 06 2022 05:28 AM
Views 1

System Information

System Information
Operating System Android 12
Model Khadas rk3588_s
Model IDKhadas rk3588_s
Motherboard rk30sdk
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.26 GHz
Cluster 32 Cores @ 2.30 GHz
Memory Information
Size 7.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 47
5.04 IPS
 
Image Classification (F16)
100% 47
5.02 IPS
 
Image Classification (I8)
81% 157
16.8 IPS
 
Image Segmentation (F32)
100% 182
1.13 IPS
 
Image Segmentation (F16)
100% 175
1.08 IPS
 
Image Segmentation (I8)
89% 564
3.48 IPS
 
Pose Estimation (F32)
100% 138
0.56 IPS
 
Pose Estimation (F16)
100% 103
0.42 IPS
 
Pose Estimation (I8)
80% 127
0.51 IPS
 
Object Detection (F32)
100% 78
2.74 IPS
 
Object Detection (F16)
100% 75
2.64 IPS
 
Object Detection (I8)
52% 265
9.28 IPS
 
Face Detection (F32)
100% 184
2.11 IPS
 
Face Detection (F16)
100% 163
1.87 IPS
 
Face Detection (I8)
75% 350
4.02 IPS
 
Text Classification (F32)
100% 291
115.0 IPS
 
Text Classification (F16)
100% 452
178.8 IPS
 
Machine Translation (F32)
100% 157
24.1 IPS
 
Machine Translation (F16)
100% 154
23.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download