Geekbench ML Score

829
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 15 2022 12:17 PM
Views 5

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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 293
31.4 IPS
 
Image Classification (F16)
100% 713
76.4 IPS
 
Image Classification (I8)
80% 611
65.4 IPS
 
Image Segmentation (F32)
100% 1220
7.53 IPS
 
Image Segmentation (F16)
100% 3001
18.5 IPS
 
Image Segmentation (I8)
89% 2802
17.3 IPS
 
Pose Estimation (F32)
100% 466
1.89 IPS
 
Pose Estimation (F16)
100% 1136
4.60 IPS
 
Pose Estimation (I8)
80% 1096
4.44 IPS
 
Object Detection (F32)
100% 234
8.20 IPS
 
Object Detection (F16)
100% 490
17.2 IPS
 
Object Detection (I8)
54% 461
16.2 IPS
 
Face Detection (F32)
100% 1166
13.4 IPS
 
Face Detection (F16)
97% 2339
26.9 IPS
 
Face Detection (I8)
76% 1973
22.7 IPS
 
Text Classification (F32)
100% 286
113.2 IPS
 
Text Classification (F16)
98% 496
196.2 IPS
 
Machine Translation (F32)
100% 958
147.7 IPS
 
Machine Translation (F16)
100% 981
151.2 IPS
 

Compare

Set Baseline Geekbench 6 now available