Geekbench ML Score

496
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 07:41 AM
Views 3

System Information

System Information
Operating System Android 10
Model samsung SM-T835N
Model IDsamsung SM-T835N
Motherboard msm8998
Governorinteractive
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 10 part 2048 revision 1
Base Frequency 1.90 GHz
Cluster 14 Cores @ 1.90 GHz
Cluster 24 Cores @ 2.36 GHz
Memory Information
Size 5.46 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 227
24.3 IPS
 
Image Classification (F16)
100% 557
59.7 IPS
 
Image Classification (I8)
80% 512
54.9 IPS
 
Image Segmentation (F32)
100% 703
4.34 IPS
 
Image Segmentation (F16)
100% 1757
10.9 IPS
 
Image Segmentation (I8)
89% 1919
11.9 IPS
 
Pose Estimation (F32)
100% 341
1.38 IPS
 
Pose Estimation (F16)
100% 993
4.02 IPS
 
Pose Estimation (I8)
80% 991
4.01 IPS
 
Object Detection (F32)
100% 181
6.34 IPS
 
Object Detection (F16)
99% 305
10.7 IPS
 
Object Detection (I8)
53% 303
10.6 IPS
 
Face Detection (F32)
100% 716
8.22 IPS
 
Face Detection (F16)
97% 1474
16.9 IPS
 
Face Detection (I8)
75% 1343
15.4 IPS
 
Text Classification (F32)
100% 209
82.6 IPS
 
Text Classification (F16)
98% 352
139.2 IPS
 
Machine Translation (F32)
100% 135
20.8 IPS
 
Machine Translation (F16)
100% 136
21.0 IPS
 

Compare

Set Baseline