Geekbench ML Score

835
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 28 2022 06:33 PM
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% 289
30.9 IPS
 
Image Classification (F16)
100% 681
73.0 IPS
 
Image Classification (I8)
80% 628
67.3 IPS
 
Image Segmentation (F32)
100% 1307
8.08 IPS
 
Image Segmentation (F16)
100% 3075
19.0 IPS
 
Image Segmentation (I8)
89% 2757
17.0 IPS
 
Pose Estimation (F32)
100% 438
1.77 IPS
 
Pose Estimation (F16)
100% 1088
4.40 IPS
 
Pose Estimation (I8)
80% 1077
4.36 IPS
 
Object Detection (F32)
100% 243
8.52 IPS
 
Object Detection (F16)
100% 514
18.1 IPS
 
Object Detection (I8)
54% 512
18.0 IPS
 
Face Detection (F32)
100% 1186
13.6 IPS
 
Face Detection (F16)
97% 2399
27.6 IPS
 
Face Detection (I8)
76% 2033
23.4 IPS
 
Text Classification (F32)
100% 270
106.9 IPS
 
Text Classification (F16)
98% 510
201.6 IPS
 
Machine Translation (F32)
100% 965
148.7 IPS
 
Machine Translation (F16)
100% 958
147.7 IPS
 

Compare

Set Baseline Geekbench 6 now available