iPad Pro (12.9-inch 5th generation)
Geekbench ML Score
2737
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| User | davidblue |
| Upload Date | August 23 2022 08:22 PM |
| Views | 8 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 16.1 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,9 |
| Motherboard | J522xAP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| L1 Instruction Cache | 128 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 4.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 15.34 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
4171
446.9 IPS |
|
|
Image Classification (F16)
|
100% |
5861
628.0 IPS |
|
|
Image Classification (I8)
|
81% |
676
72.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
7972
49.2 IPS |
|
|
Image Segmentation (F16)
|
100% |
11529
71.2 IPS |
|
|
Image Segmentation (I8)
|
89% |
1232
7.61 IPS |
|
|
Pose Estimation (F32)
|
100% |
2844
11.5 IPS |
|
|
Pose Estimation (F16)
|
100% |
6773
27.4 IPS |
|
|
Pose Estimation (I8)
|
80% |
236
0.95 IPS |
|
|
Object Detection (F32)
|
100% |
3549
124.6 IPS |
|
|
Object Detection (F16)
|
100% |
3626
127.2 IPS |
|
|
Object Detection (I8)
|
52% |
955
33.5 IPS |
|
|
Face Detection (F32)
|
100% |
6997
80.4 IPS |
|
|
Face Detection (F16)
|
97% |
12374
142.2 IPS |
|
|
Face Detection (I8)
|
75% |
949
10.9 IPS |
|
|
Text Classification (F32)
|
100% |
2384
942.7 IPS |
|
|
Text Classification (F16)
|
100% |
3031
1.20 KIPS |
|
|
Machine Translation (F32)
|
100% |
1806
278.4 IPS |
|
|
Machine Translation (F16)
|
100% |
1823
281.0 IPS |
