Geekbench ML Score

792
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 22 2022 06:11 PM
Views 1

System Information

System Information
Operating System Android 13
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 290
31.1 IPS
 
Image Classification (F16)
100% 675
72.3 IPS
 
Image Classification (I8)
80% 570
61.1 IPS
 
Image Segmentation (F32)
100% 1207
7.45 IPS
 
Image Segmentation (F16)
100% 3099
19.1 IPS
 
Image Segmentation (I8)
89% 1275
7.87 IPS
 
Pose Estimation (F32)
100% 458
1.85 IPS
 
Pose Estimation (F16)
100% 1075
4.35 IPS
 
Pose Estimation (I8)
80% 1102
4.46 IPS
 
Object Detection (F32)
100% 268
9.42 IPS
 
Object Detection (F16)
100% 551
19.3 IPS
 
Object Detection (I8)
54% 486
17.1 IPS
 
Face Detection (F32)
100% 1146
13.2 IPS
 
Face Detection (F16)
97% 2117
24.3 IPS
 
Face Detection (I8)
76% 1903
21.9 IPS
 
Text Classification (F32)
100% 266
105.3 IPS
 
Text Classification (F16)
98% 545
215.5 IPS
 
Machine Translation (F32)
100% 932
143.6 IPS
 
Machine Translation (F16)
100% 922
142.2 IPS
 

Compare

Set Baseline Geekbench 6 now available