Geekbench ML Score

278
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 09:07 PM
Views 1

System Information

System Information
Operating System Android 12
Model Samsung Galaxy Tab S6
Model IDsamsung SM-T865
Motherboard msmnile
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 5.32 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 188
20.2 IPS
 
Image Classification (F16)
100% 192
20.6 IPS
 
Image Classification (I8)
81% 211
22.7 IPS
 
Image Segmentation (F32)
100% 378
2.34 IPS
 
Image Segmentation (F16)
100% 368
2.28 IPS
 
Image Segmentation (I8)
89% 601
3.71 IPS
 
Pose Estimation (F32)
100% 219
0.88 IPS
 
Pose Estimation (F16)
100% 212
0.86 IPS
 
Pose Estimation (I8)
80% 163
0.66 IPS
 
Object Detection (F32)
100% 219
7.70 IPS
 
Object Detection (F16)
100% 234
8.21 IPS
 
Object Detection (I8)
52% 251
8.83 IPS
 
Face Detection (F32)
100% 435
5.00 IPS
 
Face Detection (F16)
100% 431
4.95 IPS
 
Face Detection (I8)
75% 408
4.69 IPS
 
Text Classification (F32)
100% 248
98.2 IPS
 
Text Classification (F16)
100% 252
99.6 IPS
 
Machine Translation (F32)
100% 307
47.3 IPS
 
Machine Translation (F16)
100% 309
47.6 IPS
 

Compare

Set Baseline