Geekbench ML Score

234
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 09:22 AM
Views 2

System Information

System Information
Operating System Android 12
Model samsung SM-G970N
Model IDsamsung SM-G970N
Motherboard exynos9820
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 @ 2.31 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 5.29 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 152
16.3 IPS
 
Image Classification (F16)
100% 109
11.7 IPS
 
Image Classification (I8)
81% 156
16.7 IPS
 
Image Segmentation (F32)
100% 314
1.94 IPS
 
Image Segmentation (F16)
100% 312
1.93 IPS
 
Image Segmentation (I8)
89% 617
3.81 IPS
 
Pose Estimation (F32)
100% 161
0.65 IPS
 
Pose Estimation (F16)
100% 148
0.60 IPS
 
Pose Estimation (I8)
80% 182
0.73 IPS
 
Object Detection (F32)
100% 134
4.72 IPS
 
Object Detection (F16)
100% 139
4.88 IPS
 
Object Detection (I8)
52% 225
7.90 IPS
 
Face Detection (F32)
100% 232
2.66 IPS
 
Face Detection (F16)
100% 251
2.88 IPS
 
Face Detection (I8)
75% 390
4.48 IPS
 
Text Classification (F32)
100% 271
107.2 IPS
 
Text Classification (F16)
100% 214
84.5 IPS
 
Machine Translation (F32)
100% 546
84.1 IPS
 
Machine Translation (F16)
100% 524
80.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download