Geekbench ML Score

372
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 04 2022 07:53 PM
Views 1

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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 469
50.2 IPS
 
Image Classification (F16)
100% 208
22.2 IPS
 
Image Classification (I8)
81% 166
17.7 IPS
 
Image Segmentation (F32)
100% 492
3.04 IPS
 
Image Segmentation (F16)
100% 515
3.18 IPS
 
Image Segmentation (I8)
89% 631
3.90 IPS
 
Pose Estimation (F32)
100% 318
1.29 IPS
 
Pose Estimation (F16)
100% 301
1.22 IPS
 
Pose Estimation (I8)
80% 232
0.94 IPS
 
Object Detection (F32)
100% 231
8.10 IPS
 
Object Detection (F16)
100% 197
6.91 IPS
 
Object Detection (I8)
52% 214
7.53 IPS
 
Face Detection (F32)
100% 671
7.71 IPS
 
Face Detection (F16)
100% 603
6.93 IPS
 
Face Detection (I8)
75% 435
4.99 IPS
 
Text Classification (F32)
100% 303
119.9 IPS
 
Text Classification (F16)
100% 285
112.8 IPS
 
Machine Translation (F32)
100% 907
139.9 IPS
 
Machine Translation (F16)
100% 909
140.1 IPS
 

Compare

Set Baseline