Geekbench ML Score

2059
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 02:30 AM
Views 8

System Information

System Information
Operating System Android 12
Model samsung SM-X706N
Model IDsamsung SM-X706N
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 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1536
164.6 IPS
 
Image Classification (F16)
100% 2418
259.1 IPS
 
Image Classification (I8)
80% 2169
232.4 IPS
 
Image Segmentation (F32)
100% 4038
24.9 IPS
 
Image Segmentation (F16)
100% 6983
43.1 IPS
 
Image Segmentation (I8)
89% 6449
39.8 IPS
 
Pose Estimation (F32)
100% 2041
8.26 IPS
 
Pose Estimation (F16)
100% 3893
15.8 IPS
 
Pose Estimation (I8)
80% 3874
15.7 IPS
 
Object Detection (F32)
100% 582
20.4 IPS
 
Object Detection (F16)
99% 821
28.8 IPS
 
Object Detection (I8)
53% 886
31.1 IPS
 
Face Detection (F32)
100% 2803
32.2 IPS
 
Face Detection (F16)
97% 5206
59.8 IPS
 
Face Detection (I8)
75% 4302
49.4 IPS
 
Text Classification (F32)
100% 812
321.3 IPS
 
Text Classification (F16)
98% 842
332.9 IPS
 
Machine Translation (F32)
100% 1060
163.4 IPS
 
Machine Translation (F16)
100% 1054
162.4 IPS
 

Compare

Set Baseline