Geekbench ML Score

834
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 24 2021 01:21 AM
Views 1

System Information

System Information
Operating System iOS 14.6
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 7.22 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 596
63.9 IPS
 
Image Classification (F16)
100% 613
65.7 IPS
 
Image Classification (I8)
81% 251
26.9 IPS
 
Image Segmentation (F32)
100% 1006
6.21 IPS
 
Image Segmentation (F16)
100% 1153
7.12 IPS
 
Image Segmentation (I8)
89% 1477
9.12 IPS
 
Pose Estimation (F32)
100% 433
1.75 IPS
 
Pose Estimation (F16)
100% 358
1.45 IPS
 
Pose Estimation (I8)
80% 633
2.56 IPS
 
Object Detection (F32)
100% 975
34.2 IPS
 
Object Detection (F16)
100% 1015
35.6 IPS
 
Object Detection (I8)
52% 597
20.9 IPS
 
Face Detection (F32)
100% 1466
16.8 IPS
 
Face Detection (F16)
100% 1455
16.7 IPS
 
Face Detection (I8)
75% 853
9.80 IPS
 
Text Classification (F32)
100% 813
321.4 IPS
 
Text Classification (F16)
100% 704
278.3 IPS
 
Machine Translation (F32)
100% 1812
279.3 IPS
 
Machine Translation (F16)
100% 1860
286.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download