iPad Air (4th generation)
Geekbench ML Score
1932
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| Upload Date | September 29 2021 01:45 AM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.1 |
| 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% |
2247
240.7 IPS |
|
|
Image Classification (F16)
|
100% |
3454
370.1 IPS |
|
|
Image Classification (I8)
|
81% |
648
69.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
4493
27.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
7520
46.5 IPS |
|
|
Image Segmentation (I8)
|
89% |
1187
7.33 IPS |
|
|
Pose Estimation (F32)
|
100% |
1417
5.74 IPS |
|
|
Pose Estimation (F16)
|
100% |
4632
18.7 IPS |
|
|
Pose Estimation (I8)
|
80% |
224
0.91 IPS |
|
|
Object Detection (F32)
|
100% |
2974
104.4 IPS |
|
|
Object Detection (F16)
|
99% |
3243
113.8 IPS |
|
|
Object Detection (I8)
|
52% |
917
32.2 IPS |
|
|
Face Detection (F32)
|
100% |
3863
44.4 IPS |
|
|
Face Detection (F16)
|
97% |
7706
88.5 IPS |
|
|
Face Detection (I8)
|
75% |
902
10.4 IPS |
|
|
Text Classification (F32)
|
100% |
1164
460.4 IPS |
|
|
Text Classification (F16)
|
98% |
1169
462.5 IPS |
|
|
Machine Translation (F32)
|
100% |
1689
260.4 IPS |
|
|
Machine Translation (F16)
|
100% |
1684
259.6 IPS |
