Geekbench ML Score

840
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 13 2022 06:15 PM
Views 2

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 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 277
29.7 IPS
 
Image Classification (F16)
100% 727
77.9 IPS
 
Image Classification (I8)
80% 604
64.7 IPS
 
Image Segmentation (F32)
100% 1139
7.04 IPS
 
Image Segmentation (F16)
100% 3020
18.7 IPS
 
Image Segmentation (I8)
89% 2805
17.3 IPS
 
Pose Estimation (F32)
100% 455
1.84 IPS
 
Pose Estimation (F16)
100% 1084
4.39 IPS
 
Pose Estimation (I8)
80% 1078
4.36 IPS
 
Object Detection (F32)
100% 258
9.05 IPS
 
Object Detection (F16)
100% 517
18.1 IPS
 
Object Detection (I8)
54% 492
17.3 IPS
 
Face Detection (F32)
100% 1138
13.1 IPS
 
Face Detection (F16)
97% 2325
26.7 IPS
 
Face Detection (I8)
76% 2280
26.2 IPS
 
Text Classification (F32)
100% 288
114.0 IPS
 
Text Classification (F16)
98% 557
220.4 IPS
 
Machine Translation (F32)
100% 973
149.9 IPS
 
Machine Translation (F16)
100% 957
147.5 IPS
 

Compare

Set Baseline Geekbench 6 now available