Geekbench ML Score

555
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 18 2023 03:52 PM
Views 1

System Information

System Information
Operating System iOS 17.0
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 469
50.3 IPS
 
Image Classification (F16)
100% 448
48.0 IPS
 
Image Classification (I8)
81% 282
30.3 IPS
 
Image Segmentation (F32)
100% 733
4.52 IPS
 
Image Segmentation (F16)
100% 691
4.27 IPS
 
Image Segmentation (I8)
89% 930
5.74 IPS
 
Pose Estimation (F32)
100% 199
0.81 IPS
 
Pose Estimation (F16)
100% 205
0.83 IPS
 
Pose Estimation (I8)
80% 251
1.02 IPS
 
Object Detection (F32)
100% 660
23.1 IPS
 
Object Detection (F16)
100% 663
23.3 IPS
 
Object Detection (I8)
52% 530
18.6 IPS
 
Face Detection (F32)
100% 784
9.01 IPS
 
Face Detection (F16)
100% 806
9.26 IPS
 
Face Detection (I8)
75% 577
6.63 IPS
 
Text Classification (F32)
100% 788
311.5 IPS
 
Text Classification (F16)
100% 757
299.4 IPS
 
Machine Translation (F32)
100% 985
151.7 IPS
 
Machine Translation (F16)
100% 984
151.6 IPS
 

Compare

Set Baseline Geekbench 6 now available