Geekbench ML Score

374
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 03 2022 12:48 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 CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 372
39.9 IPS
 
Image Classification (F16)
100% 372
39.8 IPS
 
Image Classification (I8)
81% 210
22.5 IPS
 
Image Segmentation (F32)
100% 732
4.52 IPS
 
Image Segmentation (F16)
100% 687
4.24 IPS
 
Image Segmentation (I8)
89% 793
4.90 IPS
 
Pose Estimation (F32)
100% 279
1.13 IPS
 
Pose Estimation (F16)
100% 281
1.14 IPS
 
Pose Estimation (I8)
80% 207
0.84 IPS
 
Object Detection (F32)
100% 243
8.52 IPS
 
Object Detection (F16)
100% 234
8.21 IPS
 
Object Detection (I8)
52% 225
7.90 IPS
 
Face Detection (F32)
100% 508
5.84 IPS
 
Face Detection (F16)
100% 492
5.65 IPS
 
Face Detection (I8)
75% 447
5.14 IPS
 
Text Classification (F32)
100% 301
119.1 IPS
 
Text Classification (F16)
100% 290
114.6 IPS
 
Machine Translation (F32)
100% 573
88.4 IPS
 
Machine Translation (F16)
100% 574
88.5 IPS
 

Compare

Set Baseline Geekbench 6 now available