Geekbench ML Score

831
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 25 2022 05:17 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 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 289
31.0 IPS
 
Image Classification (F16)
100% 737
79.0 IPS
 
Image Classification (I8)
80% 658
70.5 IPS
 
Image Segmentation (F32)
100% 1104
6.82 IPS
 
Image Segmentation (F16)
100% 3017
18.6 IPS
 
Image Segmentation (I8)
89% 2785
17.2 IPS
 
Pose Estimation (F32)
100% 483
1.96 IPS
 
Pose Estimation (F16)
100% 1093
4.42 IPS
 
Pose Estimation (I8)
80% 1103
4.46 IPS
 
Object Detection (F32)
100% 255
8.95 IPS
 
Object Detection (F16)
100% 485
17.0 IPS
 
Object Detection (I8)
54% 458
16.1 IPS
 
Face Detection (F32)
100% 1132
13.0 IPS
 
Face Detection (F16)
97% 2128
24.4 IPS
 
Face Detection (I8)
76% 2019
23.2 IPS
 
Text Classification (F32)
100% 309
122.4 IPS
 
Text Classification (F16)
98% 505
199.6 IPS
 
Machine Translation (F32)
100% 960
147.9 IPS
 
Machine Translation (F16)
100% 960
147.9 IPS
 

Compare

Set Baseline Geekbench 6 now available