Geekbench ML Score

2110
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 21 2022 06:26 PM
Views 4

System Information

System Information
Operating System Android 12
Model motorola motorola edge 30 pro
Model IDmotorola motorola edge 30 pro
Motherboard hiphi
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 10.98 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1749
187.4 IPS
 
Image Classification (F16)
100% 2588
277.3 IPS
 
Image Classification (I8)
80% 2355
252.3 IPS
 
Image Segmentation (F32)
100% 4250
26.3 IPS
 
Image Segmentation (F16)
100% 7117
44.0 IPS
 
Image Segmentation (I8)
89% 6562
40.5 IPS
 
Pose Estimation (F32)
100% 2004
8.11 IPS
 
Pose Estimation (F16)
100% 3847
15.6 IPS
 
Pose Estimation (I8)
80% 3869
15.7 IPS
 
Object Detection (F32)
100% 707
24.8 IPS
 
Object Detection (F16)
99% 898
31.5 IPS
 
Object Detection (I8)
53% 830
29.1 IPS
 
Face Detection (F32)
100% 2880
33.1 IPS
 
Face Detection (F16)
97% 5293
60.8 IPS
 
Face Detection (I8)
75% 4391
50.5 IPS
 
Text Classification (F32)
100% 752
297.6 IPS
 
Text Classification (F16)
98% 863
341.3 IPS
 
Machine Translation (F32)
100% 1004
154.7 IPS
 
Machine Translation (F16)
100% 1003
154.6 IPS
 

Compare

Set Baseline Geekbench 6 now available