Geekbench ML Score

364
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 08:59 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 NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 116
12.4 IPS
 
Image Classification (F16)
100% 110
11.8 IPS
 
Image Classification (I8)
81% 292
31.2 IPS
 
Image Segmentation (F32)
100% 309
1.91 IPS
 
Image Segmentation (F16)
100% 322
1.99 IPS
 
Image Segmentation (I8)
89% 930
5.74 IPS
 
Pose Estimation (F32)
100% 312
1.26 IPS
 
Pose Estimation (F16)
100% 1263
5.11 IPS
 
Pose Estimation (I8)
80% 246
0.99 IPS
 
Object Detection (F32)
100% 359
12.6 IPS
 
Object Detection (F16)
99% 553
19.4 IPS
 
Object Detection (I8)
52% 317
11.1 IPS
 
Face Detection (F32)
100% 213
2.45 IPS
 
Face Detection (F16)
100% 195
2.24 IPS
 
Face Detection (I8)
75% 401
4.60 IPS
 
Text Classification (F32)
100% 665
262.9 IPS
 
Text Classification (F16)
100% 684
270.6 IPS
 
Machine Translation (F32)
100% 537
82.8 IPS
 
Machine Translation (F16)
100% 537
82.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download