Geekbench ML Score

560
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 09:09 PM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad (8th generation)
Model IDiPad11,6
Motherboard J171aAP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.88 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 469
50.3 IPS
 
Image Classification (F16)
100% 453
48.6 IPS
 
Image Classification (I8)
81% 282
30.3 IPS
 
Image Segmentation (F32)
100% 740
4.57 IPS
 
Image Segmentation (F16)
100% 722
4.46 IPS
 
Image Segmentation (I8)
89% 935
5.78 IPS
 
Pose Estimation (F32)
100% 224
0.91 IPS
 
Pose Estimation (F16)
100% 221
0.89 IPS
 
Pose Estimation (I8)
80% 252
1.02 IPS
 
Object Detection (F32)
100% 648
22.7 IPS
 
Object Detection (F16)
100% 651
22.8 IPS
 
Object Detection (I8)
52% 539
18.9 IPS
 
Face Detection (F32)
100% 819
9.41 IPS
 
Face Detection (F16)
100% 786
9.03 IPS
 
Face Detection (I8)
75% 603
6.92 IPS
 
Text Classification (F32)
100% 755
298.7 IPS
 
Text Classification (F16)
100% 737
291.7 IPS
 
Machine Translation (F32)
100% 952
146.8 IPS
 
Machine Translation (F16)
100% 958
147.6 IPS
 

Compare

Set Baseline