Geekbench ML Score

482
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 08 2022 10:46 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 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 431
46.2 IPS
 
Image Classification (F16)
100% 396
42.4 IPS
 
Image Classification (I8)
81% 197
21.1 IPS
 
Image Segmentation (F32)
100% 718
4.44 IPS
 
Image Segmentation (F16)
100% 716
4.42 IPS
 
Image Segmentation (I8)
89% 964
5.95 IPS
 
Pose Estimation (F32)
100% 309
1.25 IPS
 
Pose Estimation (F16)
100% 302
1.22 IPS
 
Pose Estimation (I8)
80% 260
1.05 IPS
 
Object Detection (F32)
100% 482
16.9 IPS
 
Object Detection (F16)
100% 495
17.4 IPS
 
Object Detection (I8)
52% 285
10.0 IPS
 
Face Detection (F32)
100% 762
8.76 IPS
 
Face Detection (F16)
100% 759
8.72 IPS
 
Face Detection (I8)
75% 637
7.31 IPS
 
Text Classification (F32)
100% 315
124.6 IPS
 
Text Classification (F16)
100% 317
125.6 IPS
 
Machine Translation (F32)
100% 988
152.3 IPS
 
Machine Translation (F16)
100% 966
148.9 IPS
 

Compare

Set Baseline Geekbench 6 now available