Geekbench ML Score

398
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 05:38 PM
Views 2

System Information

System Information
Operating System iOS 15.5
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% 466
49.9 IPS
 
Image Classification (F16)
100% 449
48.1 IPS
 
Image Classification (I8)
81% 283
30.3 IPS
 
Image Segmentation (F32)
100% 725
4.48 IPS
 
Image Segmentation (F16)
100% 535
3.30 IPS
 
Image Segmentation (I8)
89% 635
3.92 IPS
 
Pose Estimation (F32)
100% 173
0.70 IPS
 
Pose Estimation (F16)
100% 139
0.56 IPS
 
Pose Estimation (I8)
80% 176
0.71 IPS
 
Object Detection (F32)
100% 592
20.8 IPS
 
Object Detection (F16)
100% 362
12.7 IPS
 
Object Detection (I8)
52% 426
15.0 IPS
 
Face Detection (F32)
100% 484
5.56 IPS
 
Face Detection (F16)
100% 525
6.03 IPS
 
Face Detection (I8)
75% 297
3.42 IPS
 
Text Classification (F32)
100% 561
221.9 IPS
 
Text Classification (F16)
100% 223
88.3 IPS
 
Machine Translation (F32)
100% 665
102.5 IPS
 
Machine Translation (F16)
100% 728
112.2 IPS
 

Compare

Set Baseline