Geekbench ML Score

910
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 01 2022 05:56 AM
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% 328
35.2 IPS
 
Image Classification (F16)
100% 839
89.9 IPS
 
Image Classification (I8)
80% 712
76.2 IPS
 
Image Segmentation (F32)
100% 1296
8.01 IPS
 
Image Segmentation (F16)
100% 3131
19.3 IPS
 
Image Segmentation (I8)
89% 2889
17.8 IPS
 
Pose Estimation (F32)
100% 455
1.84 IPS
 
Pose Estimation (F16)
100% 1127
4.56 IPS
 
Pose Estimation (I8)
80% 1094
4.43 IPS
 
Object Detection (F32)
100% 294
10.3 IPS
 
Object Detection (F16)
100% 569
20.0 IPS
 
Object Detection (I8)
54% 557
19.6 IPS
 
Face Detection (F32)
100% 1281
14.7 IPS
 
Face Detection (F16)
97% 2688
30.9 IPS
 
Face Detection (I8)
76% 2380
27.3 IPS
 
Text Classification (F32)
100% 313
123.7 IPS
 
Text Classification (F16)
98% 601
237.8 IPS
 
Machine Translation (F32)
100% 958
147.6 IPS
 
Machine Translation (F16)
100% 956
147.3 IPS
 

Compare

Set Baseline