iPad14,5
Geekbench ML Score
3343
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | November 05 2022 03:33 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 16.0 |
| Model | iPad14,5 |
| Model ID | iPad14,5 |
| Motherboard | J620AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 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 | 7.33 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
4706
504.3 IPS |
|
|
Image Classification (F16)
|
100% |
6725
720.6 IPS |
|
|
Image Classification (I8)
|
81% |
733
78.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
11303
69.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
16059
99.2 IPS |
|
|
Image Segmentation (I8)
|
89% |
1344
8.30 IPS |
|
|
Pose Estimation (F32)
|
100% |
3823
15.5 IPS |
|
|
Pose Estimation (F16)
|
100% |
9320
37.7 IPS |
|
|
Pose Estimation (I8)
|
80% |
255
1.03 IPS |
|
|
Object Detection (F32)
|
100% |
3928
137.9 IPS |
|
|
Object Detection (F16)
|
100% |
5232
183.6 IPS |
|
|
Object Detection (I8)
|
52% |
1047
36.7 IPS |
|
|
Face Detection (F32)
|
100% |
9460
108.7 IPS |
|
|
Face Detection (F16)
|
97% |
15896
182.6 IPS |
|
|
Face Detection (I8)
|
75% |
1027
11.8 IPS |
|
|
Text Classification (F32)
|
100% |
3600
1.42 KIPS |
|
|
Text Classification (F16)
|
100% |
4048
1.60 KIPS |
|
|
Machine Translation (F32)
|
100% |
1916
295.3 IPS |
|
|
Machine Translation (F16)
|
100% |
1913
294.8 IPS |
