iPad Pro (12.9-inch 3rd Generation)
Geekbench ML Score
1393
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| Upload Date | June 11 2021 04:11 AM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.4.1 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,5 |
| Motherboard | J320AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| L1 Instruction Cache | 128 KB x 1 |
| L1 Data Cache | 128 KB x 1 |
| L2 Cache | 8.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 3.67 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | Core ML |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
3392
363.4 IPS |
|
|
Image Classification (F16)
|
100% |
3317
355.5 IPS |
|
|
Image Classification (I8)
|
81% |
406
43.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
1455
8.99 IPS |
|
|
Image Segmentation (F16)
|
100% |
1463
9.04 IPS |
|
|
Image Segmentation (I8)
|
89% |
752
4.65 IPS |
|
|
Pose Estimation (F32)
|
100% |
8115
32.8 IPS |
|
|
Pose Estimation (F16)
|
100% |
8168
33.1 IPS |
|
|
Pose Estimation (I8)
|
80% |
143
0.58 IPS |
|
|
Object Detection (F32)
|
94% |
4306
151.1 IPS |
|
|
Object Detection (F16)
|
94% |
4326
151.8 IPS |
|
|
Object Detection (I8)
|
52% |
575
20.2 IPS |
|
|
Face Detection (F32)
|
67% |
4210
48.4 IPS |
|
|
Face Detection (F16)
|
67% |
4066
46.7 IPS |
|
|
Face Detection (I8)
|
75% |
557
6.40 IPS |
|
|
Text Classification (F32)
|
100% |
262
103.7 IPS |
|
|
Text Classification (F16)
|
100% |
287
113.6 IPS |
|
|
Machine Translation (F32)
|
100% |
1017
156.7 IPS |
|
|
Machine Translation (F16)
|
100% |
1016
156.5 IPS |
