Geekbench ML Score

859
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 11 2022 03:24 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% 318
34.1 IPS
 
Image Classification (F16)
100% 761
81.6 IPS
 
Image Classification (I8)
80% 639
68.4 IPS
 
Image Segmentation (F32)
100% 1276
7.88 IPS
 
Image Segmentation (F16)
100% 3110
19.2 IPS
 
Image Segmentation (I8)
89% 2792
17.2 IPS
 
Pose Estimation (F32)
100% 496
2.01 IPS
 
Pose Estimation (F16)
100% 1107
4.48 IPS
 
Pose Estimation (I8)
80% 1104
4.47 IPS
 
Object Detection (F32)
100% 261
9.15 IPS
 
Object Detection (F16)
100% 512
18.0 IPS
 
Object Detection (I8)
54% 508
17.8 IPS
 
Face Detection (F32)
100% 1187
13.6 IPS
 
Face Detection (F16)
97% 2470
28.4 IPS
 
Face Detection (I8)
76% 1903
21.9 IPS
 
Text Classification (F32)
100% 297
117.4 IPS
 
Text Classification (F16)
98% 521
206.2 IPS
 
Machine Translation (F32)
100% 968
149.2 IPS
 
Machine Translation (F16)
100% 958
147.7 IPS
 

Compare

Set Baseline