Geekbench ML Score

363
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 30 2022 12:36 AM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-S908U
Model IDsamsung SM-S908U
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 9.95 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 342
36.7 IPS
 
Image Classification (F16)
100% 340
36.5 IPS
 
Image Classification (I8)
81% 182
19.5 IPS
 
Image Segmentation (F32)
100% 531
3.28 IPS
 
Image Segmentation (F16)
100% 531
3.28 IPS
 
Image Segmentation (I8)
89% 610
3.77 IPS
 
Pose Estimation (F32)
100% 238
0.96 IPS
 
Pose Estimation (F16)
100% 234
0.95 IPS
 
Pose Estimation (I8)
80% 159
0.64 IPS
 
Object Detection (F32)
100% 334
11.7 IPS
 
Object Detection (F16)
100% 339
11.9 IPS
 
Object Detection (I8)
52% 247
8.66 IPS
 
Face Detection (F32)
100% 585
6.72 IPS
 
Face Detection (F16)
100% 589
6.76 IPS
 
Face Detection (I8)
75% 419
4.81 IPS
 
Text Classification (F32)
100% 278
110.1 IPS
 
Text Classification (F16)
100% 274
108.4 IPS
 
Machine Translation (F32)
100% 670
103.2 IPS
 
Machine Translation (F16)
100% 670
103.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download