Geekbench ML Score

657
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:19 AM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-M536B
Model IDsamsung SM-M536B
Motherboard m53x
CPU Information
Name ARM MT6877V/ZA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 7.36 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 391
41.9 IPS
 
Image Classification (F16)
100% 937
100.3 IPS
 
Image Classification (I8)
80% 504
54.0 IPS
 
Image Segmentation (F32)
100% 1034
6.39 IPS
 
Image Segmentation (F16)
100% 1902
11.7 IPS
 
Image Segmentation (I8)
89% 1856
11.5 IPS
 
Pose Estimation (F32)
100% 353
1.43 IPS
 
Pose Estimation (F16)
100% 901
3.65 IPS
 
Pose Estimation (I8)
80% 875
3.54 IPS
 
Object Detection (F32)
100% 334
11.7 IPS
 
Object Detection (F16)
100% 427
15.0 IPS
 
Object Detection (I8)
54% 345
12.1 IPS
 
Face Detection (F32)
100% 1020
11.7 IPS
 
Face Detection (F16)
97% 1818
20.9 IPS
 
Face Detection (I8)
75% 1635
18.8 IPS
 
Text Classification (F32)
100% 391
154.6 IPS
 
Text Classification (F16)
98% 444
175.6 IPS
 
Machine Translation (F32)
100% 229
35.4 IPS
 
Machine Translation (F16)
100% 309
47.7 IPS
 

Compare

Set Baseline