iPad Air (4th generation)
Geekbench ML Score
1990
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| User | danielmcfarland |
| Upload Date | July 22 2021 08:56 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.7 |
| 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% |
2389
256.0 IPS |
|
|
Image Classification (F16)
|
100% |
3962
424.5 IPS |
|
|
Image Classification (I8)
|
81% |
647
69.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
4496
27.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
7490
46.3 IPS |
|
|
Image Segmentation (I8)
|
89% |
1186
7.33 IPS |
|
|
Pose Estimation (F32)
|
100% |
1417
5.73 IPS |
|
|
Pose Estimation (F16)
|
100% |
4656
18.8 IPS |
|
|
Pose Estimation (I8)
|
80% |
223
0.90 IPS |
|
|
Object Detection (F32)
|
100% |
3028
106.3 IPS |
|
|
Object Detection (F16)
|
99% |
3559
124.9 IPS |
|
|
Object Detection (I8)
|
52% |
919
32.2 IPS |
|
|
Face Detection (F32)
|
100% |
3872
44.5 IPS |
|
|
Face Detection (F16)
|
97% |
7838
90.0 IPS |
|
|
Face Detection (I8)
|
75% |
900
10.3 IPS |
|
|
Text Classification (F32)
|
100% |
1268
501.6 IPS |
|
|
Text Classification (F16)
|
98% |
1340
530.0 IPS |
|
|
Machine Translation (F32)
|
100% |
1708
263.2 IPS |
|
|
Machine Translation (F16)
|
100% |
1702
262.3 IPS |
