Geekbench ML Score

338
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 05 2022 11:16 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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 238
25.5 IPS
 
Image Classification (F16)
100% 240
25.8 IPS
 
Image Classification (I8)
81% 166
17.8 IPS
 
Image Segmentation (F32)
100% 557
3.44 IPS
 
Image Segmentation (F16)
100% 480
2.96 IPS
 
Image Segmentation (I8)
89% 770
4.76 IPS
 
Pose Estimation (F32)
100% 315
1.27 IPS
 
Pose Estimation (F16)
100% 302
1.22 IPS
 
Pose Estimation (I8)
80% 244
0.99 IPS
 
Object Detection (F32)
100% 198
6.95 IPS
 
Object Detection (F16)
100% 187
6.56 IPS
 
Object Detection (I8)
52% 217
7.63 IPS
 
Face Detection (F32)
100% 412
4.73 IPS
 
Face Detection (F16)
100% 430
4.94 IPS
 
Face Detection (I8)
75% 431
4.96 IPS
 
Text Classification (F32)
100% 261
103.3 IPS
 
Text Classification (F16)
100% 377
149.0 IPS
 
Machine Translation (F32)
100% 606
93.3 IPS
 
Machine Translation (F16)
100% 704
108.6 IPS
 

Compare

Set Baseline Geekbench 6 now available