Geekbench ML Score

1335
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:52 AM
Views 2

System Information

System Information
Operating System Android 11
Model samsung SM-T875N
Model IDsamsung SM-T875N
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 3.09 GHz
Memory Information
Size 5.45 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1016
108.8 IPS
 
Image Classification (F16)
100% 1609
172.4 IPS
 
Image Classification (I8)
80% 1416
151.7 IPS
 
Image Segmentation (F32)
100% 2532
15.6 IPS
 
Image Segmentation (F16)
100% 4098
25.3 IPS
 
Image Segmentation (I8)
89% 3964
24.5 IPS
 
Pose Estimation (F32)
100% 1322
5.35 IPS
 
Pose Estimation (F16)
100% 2276
9.21 IPS
 
Pose Estimation (I8)
80% 2259
9.14 IPS
 
Object Detection (F32)
100% 493
17.3 IPS
 
Object Detection (F16)
99% 715
25.1 IPS
 
Object Detection (I8)
53% 715
25.1 IPS
 
Face Detection (F32)
100% 1906
21.9 IPS
 
Face Detection (F16)
97% 3122
35.9 IPS
 
Face Detection (I8)
76% 2801
32.2 IPS
 
Text Classification (F32)
100% 511
202.3 IPS
 
Text Classification (F16)
98% 533
210.9 IPS
 
Machine Translation (F32)
100% 570
87.8 IPS
 
Machine Translation (F16)
100% 579
89.2 IPS
 

Compare

Set Baseline