Geekbench ML Score

266
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:24 AM
Views 1

System Information

System Information
Operating System Android 11
Model Samsung Galaxy A30s
Model IDsamsung SM-A307FN
Motherboard exynos7904
Governorinteractive
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3337 revision 2
Base Frequency 1.59 GHz
Cluster 16 Cores @ 1.59 GHz
Cluster 22 Cores @ 1.77 GHz
Memory Information
Size 3.64 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 158
16.9 IPS
 
Image Classification (F16)
100% 323
34.6 IPS
 
Image Classification (I8)
81% 299
32.1 IPS
 
Image Segmentation (F32)
100% 285
1.76 IPS
 
Image Segmentation (F16)
100% 728
4.49 IPS
 
Image Segmentation (I8)
89% 699
4.32 IPS
 
Pose Estimation (F32)
100% 85
0.34 IPS
 
Pose Estimation (F16)
0% 285
1.15 IPS
 
Pose Estimation (I8)
0% 285
1.15 IPS
 
Object Detection (F32)
100% 149
5.23 IPS
 
Object Detection (F16)
99% 245
8.61 IPS
 
Object Detection (I8)
54% 241
8.44 IPS
 
Face Detection (F32)
100% 298
3.43 IPS
 
Face Detection (F16)
97% 670
7.70 IPS
 
Face Detection (I8)
75% 587
6.74 IPS
 
Text Classification (F32)
100% 250
98.7 IPS
 
Text Classification (F16)
46% 375
148.5 IPS
 
Machine Translation (F32)
100% 89
13.7 IPS
 
Machine Translation (F16)
100% 90
13.9 IPS
 

Compare

Set Baseline