Geekbench ML Score

313
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 29 2022 10:05 PM
Views 1

System Information

System Information
Operating System Android 13
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 CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 327
35.0 IPS
 
Image Classification (F16)
100% 246
26.3 IPS
 
Image Classification (I8)
81% 168
18.0 IPS
 
Image Segmentation (F32)
100% 408
2.52 IPS
 
Image Segmentation (F16)
100% 414
2.56 IPS
 
Image Segmentation (I8)
89% 587
3.62 IPS
 
Pose Estimation (F32)
100% 208
0.84 IPS
 
Pose Estimation (F16)
100% 208
0.84 IPS
 
Pose Estimation (I8)
80% 158
0.64 IPS
 
Object Detection (F32)
100% 260
9.13 IPS
 
Object Detection (F16)
100% 252
8.86 IPS
 
Object Detection (I8)
52% 208
7.29 IPS
 
Face Detection (F32)
100% 422
4.85 IPS
 
Face Detection (F16)
100% 436
5.01 IPS
 
Face Detection (I8)
75% 387
4.44 IPS
 
Text Classification (F32)
100% 288
114.1 IPS
 
Text Classification (F16)
100% 311
122.9 IPS
 
Machine Translation (F32)
100% 573
88.3 IPS
 
Machine Translation (F16)
100% 572
88.2 IPS
 

Compare

Set Baseline Geekbench 6 now available