Geekbench ML Score

382
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 05:58 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
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% 226
24.2 IPS
 
Image Classification (F16)
100% 229
24.5 IPS
 
Image Classification (I8)
81% 407
43.6 IPS
 
Image Segmentation (F32)
100% 448
2.77 IPS
 
Image Segmentation (F16)
100% 449
2.78 IPS
 
Image Segmentation (I8)
89% 762
4.71 IPS
 
Pose Estimation (F32)
100% 152
0.61 IPS
 
Pose Estimation (F16)
100% 152
0.61 IPS
 
Pose Estimation (I8)
80% 148
0.60 IPS
 
Object Detection (F32)
100% 392
13.8 IPS
 
Object Detection (F16)
100% 390
13.7 IPS
 
Object Detection (I8)
52% 576
20.2 IPS
 
Face Detection (F32)
100% 473
5.44 IPS
 
Face Detection (F16)
100% 475
5.45 IPS
 
Face Detection (I8)
75% 570
6.55 IPS
 
Text Classification (F32)
100% 606
239.8 IPS
 
Text Classification (F16)
100% 605
239.2 IPS
 
Machine Translation (F32)
100% 502
77.3 IPS
 
Machine Translation (F16)
100% 520
80.1 IPS
 

Compare

Set Baseline