Geekbench ML Score

909
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 25 2022 02:10 AM
Views 3

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% 314
33.7 IPS
 
Image Classification (F16)
100% 942
100.9 IPS
 
Image Classification (I8)
80% 808
86.5 IPS
 
Image Segmentation (F32)
100% 1301
8.04 IPS
 
Image Segmentation (F16)
100% 3067
18.9 IPS
 
Image Segmentation (I8)
89% 2811
17.4 IPS
 
Pose Estimation (F32)
100% 520
2.11 IPS
 
Pose Estimation (F16)
100% 1121
4.54 IPS
 
Pose Estimation (I8)
80% 1116
4.52 IPS
 
Object Detection (F32)
100% 285
9.99 IPS
 
Object Detection (F16)
100% 571
20.0 IPS
 
Object Detection (I8)
54% 532
18.7 IPS
 
Face Detection (F32)
100% 1230
14.1 IPS
 
Face Detection (F16)
97% 2495
28.7 IPS
 
Face Detection (I8)
76% 2200
25.3 IPS
 
Text Classification (F32)
100% 316
125.0 IPS
 
Text Classification (F16)
98% 549
217.0 IPS
 
Machine Translation (F32)
100% 974
150.1 IPS
 
Machine Translation (F16)
100% 961
148.1 IPS
 

Compare

Set Baseline Geekbench 6 now available