Geekbench ML Score

523
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 21 2023 06:55 AM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-S918U
Model IDsamsung SM-S918U
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 6.91 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 471
50.5 IPS
 
Image Classification (F16)
100% 477
51.1 IPS
 
Image Classification (I8)
81% 445
47.7 IPS
 
Image Segmentation (F32)
100% 712
4.40 IPS
 
Image Segmentation (F16)
100% 700
4.32 IPS
 
Image Segmentation (I8)
89% 743
4.59 IPS
 
Pose Estimation (F32)
100% 308
1.25 IPS
 
Pose Estimation (F16)
100% 273
1.10 IPS
 
Pose Estimation (I8)
80% 142
0.57 IPS
 
Object Detection (F32)
100% 447
15.7 IPS
 
Object Detection (F16)
100% 442
15.5 IPS
 
Object Detection (I8)
52% 415
14.6 IPS
 
Face Detection (F32)
100% 591
6.79 IPS
 
Face Detection (F16)
100% 598
6.87 IPS
 
Face Detection (I8)
75% 507
5.83 IPS
 
Text Classification (F32)
100% 950
375.6 IPS
 
Text Classification (F16)
100% 949
375.5 IPS
 
Machine Translation (F32)
100% 875
134.9 IPS
 
Machine Translation (F16)
100% 880
135.6 IPS
 

Compare

Set Baseline Geekbench 6 now available