Geekbench ML Score

673
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 09:52 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-A536W
Model IDsamsung SM-A536W
Motherboard s5e8825
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 5.26 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 428
45.9 IPS
 
Image Classification (F16)
100% 666
71.4 IPS
 
Image Classification (I8)
80% 593
63.5 IPS
 
Image Segmentation (F32)
100% 867
5.36 IPS
 
Image Segmentation (F16)
100% 1629
10.1 IPS
 
Image Segmentation (I8)
89% 1786
11.0 IPS
 
Pose Estimation (F32)
100% 325
1.31 IPS
 
Pose Estimation (F16)
100% 841
3.40 IPS
 
Pose Estimation (I8)
80% 866
3.50 IPS
 
Object Detection (F32)
100% 381
13.4 IPS
 
Object Detection (F16)
100% 620
21.8 IPS
 
Object Detection (I8)
54% 609
21.4 IPS
 
Face Detection (F32)
100% 772
8.87 IPS
 
Face Detection (F16)
97% 1282
14.7 IPS
 
Face Detection (I8)
75% 1127
13.0 IPS
 
Text Classification (F32)
100% 394
155.8 IPS
 
Text Classification (F16)
98% 646
255.6 IPS
 
Machine Translation (F32)
100% 361
55.6 IPS
 
Machine Translation (F16)
100% 363
55.9 IPS
 

Compare

Set Baseline