iPad Air (3rd generation)
Geekbench ML Score
577
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| Upload Date | June 12 2021 06:46 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.6 |
| Model | iPad Air (3rd generation) |
| Model ID | iPad11,3 |
| Motherboard | J217AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| L1 Instruction Cache | 128 KB x 1 |
| L1 Data Cache | 128 KB x 1 |
| L2 Cache | 8.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 2.84 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
469
50.3 IPS |
|
|
Image Classification (F16)
|
100% |
460
49.3 IPS |
|
|
Image Classification (I8)
|
81% |
279
29.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
767
4.74 IPS |
|
|
Image Segmentation (F16)
|
100% |
764
4.72 IPS |
|
|
Image Segmentation (I8)
|
89% |
980
6.05 IPS |
|
|
Pose Estimation (F32)
|
100% |
253
1.02 IPS |
|
|
Pose Estimation (F16)
|
100% |
251
1.01 IPS |
|
|
Pose Estimation (I8)
|
80% |
271
1.10 IPS |
|
|
Object Detection (F32)
|
100% |
626
22.0 IPS |
|
|
Object Detection (F16)
|
100% |
666
23.4 IPS |
|
|
Object Detection (I8)
|
52% |
520
18.3 IPS |
|
|
Face Detection (F32)
|
100% |
753
8.66 IPS |
|
|
Face Detection (F16)
|
100% |
812
9.33 IPS |
|
|
Face Detection (I8)
|
75% |
617
7.09 IPS |
|
|
Text Classification (F32)
|
100% |
784
309.9 IPS |
|
|
Text Classification (F16)
|
100% |
787
311.2 IPS |
|
|
Machine Translation (F32)
|
100% |
1000
154.2 IPS |
|
|
Machine Translation (F16)
|
100% |
996
153.5 IPS |
