Geekbench ML Score

925
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 25 2022 11:22 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% 334
35.8 IPS
 
Image Classification (F16)
100% 837
89.7 IPS
 
Image Classification (I8)
80% 711
76.1 IPS
 
Image Segmentation (F32)
100% 1309
8.09 IPS
 
Image Segmentation (F16)
100% 3155
19.5 IPS
 
Image Segmentation (I8)
89% 2927
18.1 IPS
 
Pose Estimation (F32)
100% 517
2.09 IPS
 
Pose Estimation (F16)
100% 1129
4.57 IPS
 
Pose Estimation (I8)
80% 1128
4.56 IPS
 
Object Detection (F32)
100% 298
10.5 IPS
 
Object Detection (F16)
100% 576
20.2 IPS
 
Object Detection (I8)
54% 561
19.7 IPS
 
Face Detection (F32)
100% 1282
14.7 IPS
 
Face Detection (F16)
97% 2798
32.1 IPS
 
Face Detection (I8)
76% 2385
27.4 IPS
 
Text Classification (F32)
100% 324
128.3 IPS
 
Text Classification (F16)
98% 594
235.1 IPS
 
Machine Translation (F32)
100% 959
147.8 IPS
 
Machine Translation (F16)
100% 958
147.6 IPS
 

Compare

Set Baseline Geekbench 6 now available