Allwinner T527
Geekbench ML Score
88
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | November 01 2024 10:41 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Allwinner T527 |
| Model ID | Allwinner T527 |
| Motherboard | exdroid |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3333 revision 0 |
| Base Frequency | 1.42 GHz |
| Cluster 1 | 4 Cores @ 1.42 GHz |
| Cluster 2 | 4 Cores @ 1.80 GHz |
| Memory Information | |
|---|---|
| Size | 3.79 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
50
5.39 IPS |
|
|
Image Classification (F16)
|
100% |
52
5.60 IPS |
|
|
Image Classification (I8)
|
81% |
131
14.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
121
0.75 IPS |
|
|
Image Segmentation (F16)
|
100% |
118
0.73 IPS |
|
|
Image Segmentation (I8)
|
89% |
334
2.07 IPS |
|
|
Pose Estimation (F32)
|
100% |
66
0.27 IPS |
|
|
Pose Estimation (F16)
|
100% |
66
0.27 IPS |
|
|
Pose Estimation (I8)
|
80% |
79
0.32 IPS |
|
|
Object Detection (F32)
|
100% |
88
3.09 IPS |
|
|
Object Detection (F16)
|
100% |
87
3.07 IPS |
|
|
Object Detection (I8)
|
52% |
249
8.75 IPS |
|
|
Face Detection (F32)
|
100% |
120
1.38 IPS |
|
|
Face Detection (F16)
|
100% |
120
1.38 IPS |
|
|
Face Detection (I8)
|
75% |
237
2.72 IPS |
|
|
Text Classification (F32)
|
100% |
92
36.5 IPS |
|
|
Text Classification (F16)
|
100% |
94
37.2 IPS |
|
|
Machine Translation (F32)
|
100% |
17
2.62 IPS |
|
|
Machine Translation (F16)
|
100% |
17
2.63 IPS |
