Geekbench ML Score

2701
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 03:23 AM
Views 2

System Information

System Information
Operating System iOS 15.1
Model iPad13,8
Model IDiPad13,8
Motherboard J522AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.20 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3940
422.1 IPS
 
Image Classification (F16)
100% 5660
606.5 IPS
 
Image Classification (I8)
81% 680
72.8 IPS
 
Image Segmentation (F32)
100% 7971
49.2 IPS
 
Image Segmentation (F16)
100% 11198
69.2 IPS
 
Image Segmentation (I8)
89% 1246
7.70 IPS
 
Pose Estimation (F32)
100% 2852
11.5 IPS
 
Pose Estimation (F16)
100% 6740
27.3 IPS
 
Pose Estimation (I8)
80% 236
0.95 IPS
 
Object Detection (F32)
100% 3586
125.8 IPS
 
Object Detection (F16)
100% 3602
126.4 IPS
 
Object Detection (I8)
52% 965
33.9 IPS
 
Face Detection (F32)
100% 6948
79.8 IPS
 
Face Detection (F16)
97% 12041
138.3 IPS
 
Face Detection (I8)
75% 948
10.9 IPS
 
Text Classification (F32)
100% 2464
974.5 IPS
 
Text Classification (F16)
100% 2535
1.00 KIPS
 
Machine Translation (F32)
100% 1834
282.6 IPS
 
Machine Translation (F16)
100% 1825
281.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download