Geekbench ML Score

308
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 19 2022 10:34 AM
Views 2

System Information

System Information
Operating System iOS 15.2.1
Model iPad (5th generation)
Model IDiPad6,11
Motherboard J71sAP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.80 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 207
22.1 IPS
 
Image Classification (F16)
100% 203
21.7 IPS
 
Image Classification (I8)
81% 345
36.9 IPS
 
Image Segmentation (F32)
100% 382
2.36 IPS
 
Image Segmentation (F16)
100% 382
2.36 IPS
 
Image Segmentation (I8)
89% 620
3.83 IPS
 
Pose Estimation (F32)
100% 111
0.45 IPS
 
Pose Estimation (F16)
100% 112
0.45 IPS
 
Pose Estimation (I8)
80% 113
0.46 IPS
 
Object Detection (F32)
100% 322
11.3 IPS
 
Object Detection (F16)
100% 336
11.8 IPS
 
Object Detection (I8)
52% 432
15.2 IPS
 
Face Detection (F32)
100% 411
4.72 IPS
 
Face Detection (F16)
100% 399
4.58 IPS
 
Face Detection (I8)
75% 434
4.99 IPS
 
Text Classification (F32)
100% 441
174.4 IPS
 
Text Classification (F16)
100% 451
178.2 IPS
 
Machine Translation (F32)
100% 402
62.0 IPS
 
Machine Translation (F16)
100% 408
62.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download