Geekbench ML Score

1502
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User ZeroMaximusCool2010
Upload Date November 24 2022 06:46 PM
Views 2

System Information

System Information
Operating System Android 12
Model Samsung Galaxy S21 Ultra 5G
Model IDsamsung SM-G998U
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM SM8350
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 13.96 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 568
60.8 IPS
 
Image Classification (F16)
100% 1171
125.5 IPS
 
Image Classification (I8)
79% 4226
452.8 IPS
 
Image Segmentation (F32)
100% 1620
10.0 IPS
 
Image Segmentation (F16)
100% 3012
18.6 IPS
 
Image Segmentation (I8)
89% 8632
53.3 IPS
 
Pose Estimation (F32)
100% 581
2.35 IPS
 
Pose Estimation (F16)
100% 2061
8.34 IPS
 
Pose Estimation (I8)
80% 25127
101.7 IPS
 
Object Detection (F32)
100% 916
32.1 IPS
 
Object Detection (F16)
100% 1230
43.2 IPS
 
Object Detection (I8)
56% 1793
62.9 IPS
 
Face Detection (F32)
100% 1733
19.9 IPS
 
Face Detection (F16)
97% 2771
31.8 IPS
 
Face Detection (I8)
76% 22872
262.8 IPS
 
Text Classification (F32)
100% 16
6.48 IPS
 
Text Classification (F16)
100% 332
131.4 IPS
 
Machine Translation (F32)
100% 729
112.3 IPS
 
Machine Translation (F16)
100% 743
114.5 IPS
 

Compare

Set Baseline Geekbench 6 now available