Geekbench ML Score

365
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 06:38 AM
Views 1

System Information

System Information
Operating System iOS 15.6
Model iPad Pro (9.7-inch)
Model IDiPad6,3
Motherboard J127AP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.92 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 231
24.7 IPS
 
Image Classification (F16)
100% 232
24.9 IPS
 
Image Classification (I8)
81% 413
44.2 IPS
 
Image Segmentation (F32)
100% 452
2.79 IPS
 
Image Segmentation (F16)
100% 453
2.80 IPS
 
Image Segmentation (I8)
89% 772
4.77 IPS
 
Pose Estimation (F32)
100% 153
0.62 IPS
 
Pose Estimation (F16)
100% 146
0.59 IPS
 
Pose Estimation (I8)
80% 135
0.55 IPS
 
Object Detection (F32)
100% 354
12.4 IPS
 
Object Detection (F16)
100% 353
12.4 IPS
 
Object Detection (I8)
52% 526
18.5 IPS
 
Face Detection (F32)
100% 457
5.25 IPS
 
Face Detection (F16)
100% 453
5.20 IPS
 
Face Detection (I8)
75% 537
6.17 IPS
 
Text Classification (F32)
100% 544
215.3 IPS
 
Text Classification (F16)
100% 545
215.5 IPS
 
Machine Translation (F32)
100% 454
69.9 IPS
 
Machine Translation (F16)
100% 475
73.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download