Geekbench ML Score

2223
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 08:27 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-S908U1
Model IDsamsung SM-S908U1
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.05 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1760
188.6 IPS
 
Image Classification (F16)
100% 2676
286.7 IPS
 
Image Classification (I8)
80% 2435
260.9 IPS
 
Image Segmentation (F32)
100% 4308
26.6 IPS
 
Image Segmentation (F16)
100% 7234
44.7 IPS
 
Image Segmentation (I8)
89% 7185
44.4 IPS
 
Pose Estimation (F32)
100% 2025
8.19 IPS
 
Pose Estimation (F16)
100% 3845
15.6 IPS
 
Pose Estimation (I8)
80% 3863
15.6 IPS
 
Object Detection (F32)
100% 862
30.3 IPS
 
Object Detection (F16)
99% 928
32.6 IPS
 
Object Detection (I8)
53% 946
33.2 IPS
 
Face Detection (F32)
100% 2924
33.6 IPS
 
Face Detection (F16)
97% 5276
60.6 IPS
 
Face Detection (I8)
75% 4671
53.7 IPS
 
Text Classification (F32)
100% 851
336.7 IPS
 
Text Classification (F16)
98% 993
392.7 IPS
 
Machine Translation (F32)
100% 1054
162.4 IPS
 
Machine Translation (F16)
100% 1049
161.7 IPS
 

Compare

Set Baseline