Geekbench ML Score

354
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 18 2022 08:50 PM
Views 4

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% 285
30.5 IPS
 
Image Classification (F16)
100% 236
25.3 IPS
 
Image Classification (I8)
81% 163
17.5 IPS
 
Image Segmentation (F32)
100% 481
2.97 IPS
 
Image Segmentation (F16)
100% 455
2.81 IPS
 
Image Segmentation (I8)
89% 750
4.64 IPS
 
Pose Estimation (F32)
100% 322
1.30 IPS
 
Pose Estimation (F16)
100% 305
1.24 IPS
 
Pose Estimation (I8)
80% 228
0.92 IPS
 
Object Detection (F32)
100% 191
6.69 IPS
 
Object Detection (F16)
100% 200
7.00 IPS
 
Object Detection (I8)
52% 213
7.48 IPS
 
Face Detection (F32)
100% 510
5.86 IPS
 
Face Detection (F16)
100% 448
5.15 IPS
 
Face Detection (I8)
75% 440
5.06 IPS
 
Text Classification (F32)
100% 253
99.9 IPS
 
Text Classification (F16)
100% 332
131.1 IPS
 
Machine Translation (F32)
100% 998
153.8 IPS
 
Machine Translation (F16)
100% 992
152.9 IPS
 

Compare

Set Baseline Geekbench 6 now available