Geekbench ML Score

338
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 15 2021 10:07 AM
Views 1

System Information

System Information
Operating System Android 10
Model LG G8 ThinQ
Model IDLGE LM-G820N
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 5.35 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 293
31.4 IPS
 
Image Classification (F16)
100% 289
31.0 IPS
 
Image Classification (I8)
81% 175
18.8 IPS
 
Image Segmentation (F32)
100% 485
2.99 IPS
 
Image Segmentation (F16)
100% 485
3.00 IPS
 
Image Segmentation (I8)
89% 693
4.28 IPS
 
Pose Estimation (F32)
100% 222
0.90 IPS
 
Pose Estimation (F16)
100% 215
0.87 IPS
 
Pose Estimation (I8)
80% 188
0.76 IPS
 
Object Detection (F32)
100% 347
12.2 IPS
 
Object Detection (F16)
100% 345
12.1 IPS
 
Object Detection (I8)
52% 265
9.31 IPS
 
Face Detection (F32)
100% 553
6.36 IPS
 
Face Detection (F16)
100% 545
6.27 IPS
 
Face Detection (I8)
75% 441
5.07 IPS
 
Text Classification (F32)
100% 300
118.5 IPS
 
Text Classification (F16)
100% 289
114.4 IPS
 
Machine Translation (F32)
100% 384
59.1 IPS
 
Machine Translation (F16)
100% 379
58.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download