Geekbench ML Score

728
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 23 2022 06:55 AM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-F916U
Model IDsamsung SM-F916U
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 3.09 GHz
Memory Information
Size 10.35 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 676
72.5 IPS
 
Image Classification (F16)
100% 1076
115.3 IPS
 
Image Classification (I8)
80% 1254
134.4 IPS
 
Image Segmentation (F32)
100% 972
6.00 IPS
 
Image Segmentation (F16)
100% 1308
8.08 IPS
 
Image Segmentation (I8)
89% 3249
20.1 IPS
 
Pose Estimation (F32)
100% 457
1.85 IPS
 
Pose Estimation (F16)
100% 1705
6.90 IPS
 
Pose Estimation (I8)
80% 5636
22.8 IPS
 
Object Detection (F32)
100% 614
21.5 IPS
 
Object Detection (F16)
100% 892
31.3 IPS
 
Object Detection (I8)
52% 1181
41.4 IPS
 
Face Detection (F32)
100% 992
11.4 IPS
 
Face Detection (F16)
97% 1201
13.8 IPS
 
Face Detection (I8)
75% 4112
47.2 IPS
 
Text Classification (F32)
54% 12
4.69 IPS
 
Text Classification (F16)
54% 11
4.45 IPS
 
Machine Translation (F32)
100% 595
91.6 IPS
 
Machine Translation (F16)
100% 594
91.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download