iPad Air (4th generation)
Geekbench ML Score
1918
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | May 15 2022 08:48 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.4.1 |
| Model | iPad Air (4th generation) |
| Model ID | iPad13,1 |
| Motherboard | J307AP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 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 | 3.78 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
2219
237.8 IPS |
|
|
Image Classification (F16)
|
100% |
3623
388.2 IPS |
|
|
Image Classification (I8)
|
81% |
605
64.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
4360
26.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
7422
45.8 IPS |
|
|
Image Segmentation (I8)
|
89% |
933
5.76 IPS |
|
|
Pose Estimation (F32)
|
100% |
1414
5.72 IPS |
|
|
Pose Estimation (F16)
|
100% |
4681
18.9 IPS |
|
|
Pose Estimation (I8)
|
80% |
205
0.83 IPS |
|
|
Object Detection (F32)
|
100% |
2912
102.2 IPS |
|
|
Object Detection (F16)
|
99% |
3267
114.6 IPS |
|
|
Object Detection (I8)
|
52% |
707
24.8 IPS |
|
|
Face Detection (F32)
|
100% |
3892
44.7 IPS |
|
|
Face Detection (F16)
|
97% |
7880
90.5 IPS |
|
|
Face Detection (I8)
|
75% |
847
9.73 IPS |
|
|
Text Classification (F32)
|
100% |
1789
707.4 IPS |
|
|
Text Classification (F16)
|
98% |
1361
538.3 IPS |
|
|
Machine Translation (F32)
|
100% |
1668
257.0 IPS |
|
|
Machine Translation (F16)
|
100% |
1675
258.2 IPS |
