iPad Air 2
Geekbench ML Score
385
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | September 07 2024 12:51 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.2 |
| Model | iPad Air 2 |
| Model ID | iPad5,4 |
| Motherboard | J82AP |
| CPU Information | |
|---|---|
| Name | Apple A8X |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 1.50 GHz |
| L1 Instruction Cache | 64.0 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 2.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 1.94 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
508
54.4 IPS |
|
|
Image Classification (F16)
|
100% |
535
57.3 IPS |
|
|
Image Classification (I8)
|
81% |
149
16.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
887
5.48 IPS |
|
|
Image Segmentation (F16)
|
100% |
1136
7.02 IPS |
|
|
Image Segmentation (I8)
|
89% |
278
1.72 IPS |
|
|
Pose Estimation (F32)
|
100% |
310
1.25 IPS |
|
|
Pose Estimation (F16)
|
100% |
543
2.20 IPS |
|
|
Pose Estimation (I8)
|
80% |
52
0.21 IPS |
|
|
Object Detection (F32)
|
100% |
623
21.9 IPS |
|
|
Object Detection (F16)
|
100% |
809
28.4 IPS |
|
|
Object Detection (I8)
|
52% |
212
7.43 IPS |
|
|
Face Detection (F32)
|
100% |
852
9.79 IPS |
|
|
Face Detection (F16)
|
97% |
1212
13.9 IPS |
|
|
Face Detection (I8)
|
75% |
206
2.37 IPS |
|
|
Text Classification (F32)
|
100% |
330
130.6 IPS |
|
|
Text Classification (F16)
|
98% |
391
154.7 IPS |
|
|
Machine Translation (F32)
|
100% |
215
33.1 IPS |
|
|
Machine Translation (F16)
|
100% |
218
33.5 IPS |
