Geekbench ML Score

159
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2021 03:26 AM
Views 2

System Information

System Information
Operating System Android 11
Model samsung SM-N976N
Model IDsamsung SM-N976N
Motherboard exynos9825
Governorschedutil
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 3 revision 0
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 22 Cores @ 2.40 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 11.02 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 229
24.6 IPS
 
Image Classification (F16)
100% 225
24.1 IPS
 
Image Classification (I8)
81% 149
15.9 IPS
 
Image Segmentation (F32)
100% 214
1.32 IPS
 
Image Segmentation (F16)
100% 198
1.23 IPS
 
Image Segmentation (I8)
89% 352
2.17 IPS
 
Pose Estimation (F32)
100% 114
0.46 IPS
 
Pose Estimation (F16)
100% 111
0.45 IPS
 
Pose Estimation (I8)
80% 119
0.48 IPS
 
Object Detection (F32)
100% 140
4.92 IPS
 
Object Detection (F16)
100% 117
4.10 IPS
 
Object Detection (I8)
52% 134
4.70 IPS
 
Face Detection (F32)
100% 182
2.09 IPS
 
Face Detection (F16)
100% 178
2.04 IPS
 
Face Detection (I8)
75% 227
2.61 IPS
 
Text Classification (F32)
100% 209
82.7 IPS
 
Text Classification (F16)
100% 110
43.4 IPS
 
Machine Translation (F32)
100% 105
16.2 IPS
 
Machine Translation (F16)
100% 105
16.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download