Geekbench ML Score

232
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 08:29 PM
Views 1

System Information

System Information
Operating System iOS 15.4.1
Model iPad Air 2
Model IDiPad5,4
Motherboard J82AP
CPU Information
Name Apple A8X
Topology 1 Processor, 3 Cores
Identifier ARM
Base Frequency 1.50 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 166
17.8 IPS
 
Image Classification (F16)
100% 166
17.8 IPS
 
Image Classification (I8)
81% 348
37.3 IPS
 
Image Segmentation (F32)
100% 301
1.86 IPS
 
Image Segmentation (F16)
100% 300
1.85 IPS
 
Image Segmentation (I8)
89% 681
4.20 IPS
 
Pose Estimation (F32)
100% 112
0.45 IPS
 
Pose Estimation (F16)
100% 107
0.43 IPS
 
Pose Estimation (I8)
80% 122
0.49 IPS
 
Object Detection (F32)
100% 244
8.56 IPS
 
Object Detection (F16)
100% 244
8.56 IPS
 
Object Detection (I8)
52% 421
14.8 IPS
 
Face Detection (F32)
100% 305
3.50 IPS
 
Face Detection (F16)
100% 299
3.44 IPS
 
Face Detection (I8)
75% 402
4.62 IPS
 
Text Classification (F32)
100% 181
71.6 IPS
 
Text Classification (F16)
100% 185
73.1 IPS
 
Machine Translation (F32)
100% 187
28.8 IPS
 
Machine Translation (F16)
100% 192
29.5 IPS
 

Compare

Set Baseline Geekbench 6 now available