iPad Pro 12.9-inch (5th generation) iPad13,10
Geekbench ML Score
2849
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| User | idanbo |
| Upload Date | May 21 2021 05:16 AM |
| Views | 20 |
| Notes | iPad Pro 12.9-inch (5th generation) with Wi-Fi + Cellular/512GB |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.5.1 |
| Model | iPad13,10 |
| Model ID | iPad13,10 |
| Motherboard | J523AP |
| CPU Information | |
|---|---|
| Name | ARM |
| 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 | 7.22 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
4044
433.2 IPS |
|
|
Image Classification (F16)
|
100% |
5899
632.1 IPS |
|
|
Image Classification (I8)
|
81% |
690
73.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
8138
50.3 IPS |
|
|
Image Segmentation (F16)
|
100% |
11835
73.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
1247
7.70 IPS |
|
|
Pose Estimation (F32)
|
100% |
2869
11.6 IPS |
|
|
Pose Estimation (F16)
|
100% |
6813
27.6 IPS |
|
|
Pose Estimation (I8)
|
80% |
236
0.95 IPS |
|
|
Object Detection (F32)
|
100% |
3823
134.2 IPS |
|
|
Object Detection (F16)
|
100% |
3441
120.7 IPS |
|
|
Object Detection (I8)
|
52% |
973
34.1 IPS |
|
|
Face Detection (F32)
|
100% |
7069
81.2 IPS |
|
|
Face Detection (F16)
|
97% |
12658
145.4 IPS |
|
|
Face Detection (I8)
|
75% |
947
10.9 IPS |
|
|
Text Classification (F32)
|
100% |
3390
1.34 KIPS |
|
|
Text Classification (F16)
|
100% |
3836
1.52 KIPS |
|
|
Machine Translation (F32)
|
100% |
1839
283.4 IPS |
|
|
Machine Translation (F16)
|
100% |
1842
283.9 IPS |
