Geekbench ML Score

400
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 11 2021 12:20 PM
Views 3

System Information

System Information
Operating System Android 10
Model LG G8 ThinQ
Model IDLGE LM-G850
Motherboard msmnile
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 5.38 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 384
41.1 IPS
 
Image Classification (F16)
100% 494
52.9 IPS
 
Image Classification (I8)
80% 922
98.8 IPS
 
Image Segmentation (F32)
100% 391
2.41 IPS
 
Image Segmentation (F16)
100% 404
2.50 IPS
 
Image Segmentation (I8)
89% 516
3.19 IPS
 
Pose Estimation (F32)
100% 361
1.46 IPS
 
Pose Estimation (F16)
100% 836
3.38 IPS
 
Pose Estimation (I8)
80% 205
0.83 IPS
 
Object Detection (F32)
100% 453
15.9 IPS
 
Object Detection (F16)
100% 555
19.5 IPS
 
Object Detection (I8)
52% 792
27.8 IPS
 
Face Detection (F32)
100% 808
9.28 IPS
 
Face Detection (F16)
100% 1000
11.5 IPS
 
Face Detection (I8)
75% 2769
31.8 IPS
 
Text Classification (F32)
100% 29
11.4 IPS
 
Text Classification (F16)
100% 29
11.3 IPS
 
Machine Translation (F32)
100% 291
44.9 IPS
 
Machine Translation (F16)
100% 289
44.5 IPS
 

Compare

Set Baseline Geekbench 6 now available