Geekbench ML Score

826
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 15 2022 12:00 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-S908B
Model IDsamsung SM-S908B
Motherboard s5e9925
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.82 GHz
Cluster 14 Cores @ 1.82 GHz
Cluster 23 Cores @ 2.52 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 280
30.1 IPS
 
Image Classification (F16)
100% 671
71.9 IPS
 
Image Classification (I8)
80% 591
63.3 IPS
 
Image Segmentation (F32)
100% 1295
8.00 IPS
 
Image Segmentation (F16)
100% 3058
18.9 IPS
 
Image Segmentation (I8)
89% 2806
17.3 IPS
 
Pose Estimation (F32)
100% 495
2.00 IPS
 
Pose Estimation (F16)
100% 1105
4.47 IPS
 
Pose Estimation (I8)
80% 1107
4.48 IPS
 
Object Detection (F32)
100% 243
8.52 IPS
 
Object Detection (F16)
100% 496
17.4 IPS
 
Object Detection (I8)
54% 468
16.4 IPS
 
Face Detection (F32)
100% 1107
12.7 IPS
 
Face Detection (F16)
97% 2153
24.7 IPS
 
Face Detection (I8)
76% 2043
23.5 IPS
 
Text Classification (F32)
100% 279
110.3 IPS
 
Text Classification (F16)
98% 497
196.6 IPS
 
Machine Translation (F32)
100% 989
152.5 IPS
 
Machine Translation (F16)
100% 955
147.2 IPS
 

Compare

Set Baseline