Geekbench ML Score

413
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User ett11
Upload Date June 27 2022 10:42 PM
Views 3

System Information

System Information
Operating System Android 12
Model samsung SM-S901U
Model IDsamsung SM-S901U
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 403
43.2 IPS
 
Image Classification (F16)
100% 398
42.6 IPS
 
Image Classification (I8)
81% 184
19.7 IPS
 
Image Segmentation (F32)
100% 631
3.89 IPS
 
Image Segmentation (F16)
100% 627
3.87 IPS
 
Image Segmentation (I8)
89% 752
4.65 IPS
 
Pose Estimation (F32)
100% 272
1.10 IPS
 
Pose Estimation (F16)
100% 265
1.07 IPS
 
Pose Estimation (I8)
80% 198
0.80 IPS
 
Object Detection (F32)
100% 408
14.3 IPS
 
Object Detection (F16)
100% 393
13.8 IPS
 
Object Detection (I8)
52% 277
9.71 IPS
 
Face Detection (F32)
100% 669
7.68 IPS
 
Face Detection (F16)
100% 655
7.53 IPS
 
Face Detection (I8)
75% 428
4.92 IPS
 
Text Classification (F32)
100% 307
121.4 IPS
 
Text Classification (F16)
100% 307
121.4 IPS
 
Machine Translation (F32)
100% 732
112.8 IPS
 
Machine Translation (F16)
100% 730
112.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download