Geekbench ML Score

341
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 19 2022 03:19 AM
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 202
21.7 IPS
 
Image Classification (F16)
100% 144
15.5 IPS
 
Image Classification (I8)
81% 140
14.9 IPS
 
Image Segmentation (F32)
100% 498
3.08 IPS
 
Image Segmentation (F16)
100% 500
3.09 IPS
 
Image Segmentation (I8)
89% 663
4.09 IPS
 
Pose Estimation (F32)
100% 323
1.31 IPS
 
Pose Estimation (F16)
100% 305
1.23 IPS
 
Pose Estimation (I8)
80% 248
1.00 IPS
 
Object Detection (F32)
100% 228
8.01 IPS
 
Object Detection (F16)
100% 222
7.80 IPS
 
Object Detection (I8)
52% 214
7.49 IPS
 
Face Detection (F32)
100% 443
5.09 IPS
 
Face Detection (F16)
100% 457
5.25 IPS
 
Face Detection (I8)
75% 428
4.92 IPS
 
Text Classification (F32)
100% 304
120.4 IPS
 
Text Classification (F16)
100% 297
117.4 IPS
 
Machine Translation (F32)
100% 979
150.9 IPS
 
Machine Translation (F16)
100% 986
152.0 IPS
 

Compare

Set Baseline Geekbench 6 now available