Geekbench ML Score

2077
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 22 2023 11:40 AM
Views 1

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 7.09 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1699
182.1 IPS
 
Image Classification (F16)
100% 2558
274.1 IPS
 
Image Classification (I8)
80% 2694
288.6 IPS
 
Image Segmentation (F32)
100% 4459
27.5 IPS
 
Image Segmentation (F16)
100% 7696
47.5 IPS
 
Image Segmentation (I8)
89% 7349
45.4 IPS
 
Pose Estimation (F32)
100% 1989
8.05 IPS
 
Pose Estimation (F16)
100% 3825
15.5 IPS
 
Pose Estimation (I8)
80% 3819
15.5 IPS
 
Object Detection (F32)
100% 626
22.0 IPS
 
Object Detection (F16)
99% 779
27.3 IPS
 
Object Detection (I8)
53% 797
28.0 IPS
 
Face Detection (F32)
100% 2834
32.6 IPS
 
Face Detection (F16)
97% 5215
59.9 IPS
 
Face Detection (I8)
75% 4313
49.6 IPS
 
Text Classification (F32)
100% 842
333.2 IPS
 
Text Classification (F16)
98% 973
385.0 IPS
 
Machine Translation (F32)
100% 765
117.9 IPS
 
Machine Translation (F16)
100% 814
125.4 IPS
 

Compare

Set Baseline Geekbench 6 now available