iPad Air 2
Geekbench ML Score
385
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | July 06 2024 07:30 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.8.2 |
| 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% |
514
55.1 IPS |
|
|
Image Classification (F16)
|
100% |
544
58.3 IPS |
|
|
Image Classification (I8)
|
81% |
149
15.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
884
5.46 IPS |
|
|
Image Segmentation (F16)
|
100% |
1136
7.02 IPS |
|
|
Image Segmentation (I8)
|
89% |
277
1.71 IPS |
|
|
Pose Estimation (F32)
|
100% |
315
1.27 IPS |
|
|
Pose Estimation (F16)
|
100% |
545
2.21 IPS |
|
|
Pose Estimation (I8)
|
80% |
52
0.21 IPS |
|
|
Object Detection (F32)
|
100% |
624
21.9 IPS |
|
|
Object Detection (F16)
|
100% |
817
28.7 IPS |
|
|
Object Detection (I8)
|
52% |
211
7.42 IPS |
|
|
Face Detection (F32)
|
100% |
851
9.78 IPS |
|
|
Face Detection (F16)
|
97% |
1211
13.9 IPS |
|
|
Face Detection (I8)
|
75% |
206
2.37 IPS |
|
|
Text Classification (F32)
|
100% |
331
130.9 IPS |
|
|
Text Classification (F16)
|
98% |
391
154.6 IPS |
|
|
Machine Translation (F32)
|
100% |
210
32.3 IPS |
|
|
Machine Translation (F16)
|
100% |
208
32.1 IPS |
