Geekbench ML Score

474
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 01:39 PM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-S906E
Model IDsamsung SM-S906E
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 7.06 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 482
51.7 IPS
 
Image Classification (F16)
100% 474
50.8 IPS
 
Image Classification (I8)
81% 175
18.7 IPS
 
Image Segmentation (F32)
100% 710
4.39 IPS
 
Image Segmentation (F16)
100% 723
4.47 IPS
 
Image Segmentation (I8)
89% 942
5.82 IPS
 
Pose Estimation (F32)
100% 284
1.15 IPS
 
Pose Estimation (F16)
100% 277
1.12 IPS
 
Pose Estimation (I8)
80% 243
0.98 IPS
 
Object Detection (F32)
100% 444
15.6 IPS
 
Object Detection (F16)
100% 444
15.6 IPS
 
Object Detection (I8)
52% 276
9.67 IPS
 
Face Detection (F32)
100% 734
8.43 IPS
 
Face Detection (F16)
100% 717
8.23 IPS
 
Face Detection (I8)
75% 528
6.07 IPS
 
Text Classification (F32)
100% 341
134.7 IPS
 
Text Classification (F16)
100% 339
134.2 IPS
 
Machine Translation (F32)
100% 1057
163.0 IPS
 
Machine Translation (F16)
100% 1048
161.5 IPS
 

Compare

Set Baseline