iPad Air (4th generation)
Geekbench ML Score
903
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| Upload Date | September 28 2021 11:20 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.0 |
| 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 | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
638
68.4 IPS |
|
|
Image Classification (F16)
|
100% |
629
67.4 IPS |
|
|
Image Classification (I8)
|
81% |
416
44.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
980
6.05 IPS |
|
|
Image Segmentation (F16)
|
100% |
978
6.04 IPS |
|
|
Image Segmentation (I8)
|
89% |
1398
8.63 IPS |
|
|
Pose Estimation (F32)
|
100% |
380
1.54 IPS |
|
|
Pose Estimation (F16)
|
100% |
379
1.54 IPS |
|
|
Pose Estimation (I8)
|
80% |
464
1.88 IPS |
|
|
Object Detection (F32)
|
100% |
925
32.5 IPS |
|
|
Object Detection (F16)
|
100% |
930
32.6 IPS |
|
|
Object Detection (I8)
|
52% |
739
25.9 IPS |
|
|
Face Detection (F32)
|
100% |
1108
12.7 IPS |
|
|
Face Detection (F16)
|
100% |
1103
12.7 IPS |
|
|
Face Detection (I8)
|
75% |
813
9.34 IPS |
|
|
Text Classification (F32)
|
100% |
2388
944.7 IPS |
|
|
Text Classification (F16)
|
100% |
2316
915.9 IPS |
|
|
Machine Translation (F32)
|
100% |
1676
258.4 IPS |
|
|
Machine Translation (F16)
|
100% |
1679
258.8 IPS |
