Geekbench ML Score

692
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:20 AM
Views 1

System Information

System Information
Operating System Android 13
Model Samsung Galaxy S21+ 5G
Model IDsamsung SM-G996N
Motherboard exynos2100
Governorenergy_step
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 2.21 GHz
Cluster 14 Cores @ 2.21 GHz
Cluster 23 Cores @ 2.81 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 7.03 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 378
40.5 IPS
 
Image Classification (F16)
100% 367
39.4 IPS
 
Image Classification (I8)
81% 384
41.2 IPS
 
Image Segmentation (F32)
100% 618
3.82 IPS
 
Image Segmentation (F16)
100% 596
3.68 IPS
 
Image Segmentation (I8)
89% 1730
10.7 IPS
 
Pose Estimation (F32)
100% 532
2.15 IPS
 
Pose Estimation (F16)
100% 1802
7.29 IPS
 
Pose Estimation (I8)
80% 1991
8.06 IPS
 
Object Detection (F32)
100% 562
19.7 IPS
 
Object Detection (F16)
99% 916
32.1 IPS
 
Object Detection (I8)
52% 432
15.1 IPS
 
Face Detection (F32)
100% 529
6.08 IPS
 
Face Detection (F16)
100% 529
6.08 IPS
 
Face Detection (I8)
75% 520
5.97 IPS
 
Text Classification (F32)
100% 953
377.0 IPS
 
Text Classification (F16)
100% 978
386.7 IPS
 
Machine Translation (F32)
100% 687
105.9 IPS
 
Machine Translation (F16)
100% 686
105.7 IPS
 

Compare

Set Baseline