Geekbench ML Score

411
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 05:23 PM
Views 2

System Information

System Information
Operating System Android 12
Model samsung SM-S908E
Model IDsamsung SM-S908E
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 9.94 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 403
43.2 IPS
 
Image Classification (F16)
100% 380
40.7 IPS
 
Image Classification (I8)
81% 183
19.6 IPS
 
Image Segmentation (F32)
100% 617
3.81 IPS
 
Image Segmentation (F16)
100% 615
3.80 IPS
 
Image Segmentation (I8)
89% 651
4.02 IPS
 
Pose Estimation (F32)
100% 265
1.07 IPS
 
Pose Estimation (F16)
100% 252
1.02 IPS
 
Pose Estimation (I8)
80% 182
0.74 IPS
 
Object Detection (F32)
100% 391
13.7 IPS
 
Object Detection (F16)
100% 407
14.3 IPS
 
Object Detection (I8)
52% 271
9.52 IPS
 
Face Detection (F32)
100% 647
7.43 IPS
 
Face Detection (F16)
100% 648
7.44 IPS
 
Face Detection (I8)
75% 438
5.03 IPS
 
Text Classification (F32)
100% 311
122.9 IPS
 
Text Classification (F16)
100% 322
127.3 IPS
 
Machine Translation (F32)
100% 832
128.3 IPS
 
Machine Translation (F16)
100% 833
128.4 IPS
 

Compare

Set Baseline