Geekbench ML Score

240
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 06:33 AM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-A536U
Model IDsamsung SM-A536U
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 130
14.0 IPS
 
Image Classification (F16)
100% 66
7.12 IPS
 
Image Classification (I8)
81% 168
18.0 IPS
 
Image Segmentation (F32)
100% 368
2.27 IPS
 
Image Segmentation (F16)
100% 376
2.32 IPS
 
Image Segmentation (I8)
89% 527
3.25 IPS
 
Pose Estimation (F32)
100% 137
0.55 IPS
 
Pose Estimation (F16)
100% 135
0.54 IPS
 
Pose Estimation (I8)
80% 131
0.53 IPS
 
Object Detection (F32)
100% 215
7.56 IPS
 
Object Detection (F16)
100% 219
7.69 IPS
 
Object Detection (I8)
52% 241
8.44 IPS
 
Face Detection (F32)
100% 338
3.88 IPS
 
Face Detection (F16)
100% 333
3.82 IPS
 
Face Detection (I8)
75% 362
4.16 IPS
 
Text Classification (F32)
100% 332
131.2 IPS
 
Text Classification (F16)
100% 333
131.8 IPS
 
Machine Translation (F32)
100% 367
56.5 IPS
 
Machine Translation (F16)
100% 369
56.8 IPS
 

Compare

Set Baseline