iPad Pro (12.9-inch 2nd Generation)
Geekbench ML Score
1072
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| Upload Date | September 17 2021 12:39 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.8 |
| Model | iPad Pro (12.9-inch 2nd Generation) |
| Model ID | iPad7,2 |
| Motherboard | J121AP |
| CPU Information | |
|---|---|
| Name | Apple A10X Fusion |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 2.34 GHz |
| L1 Instruction Cache | 64.0 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 8.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 3.88 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1120
120.0 IPS |
|
|
Image Classification (F16)
|
100% |
1989
213.1 IPS |
|
|
Image Classification (I8)
|
81% |
336
36.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
2919
18.0 IPS |
|
|
Image Segmentation (F16)
|
100% |
5088
31.4 IPS |
|
|
Image Segmentation (I8)
|
89% |
612
3.78 IPS |
|
|
Pose Estimation (F32)
|
100% |
847
3.43 IPS |
|
|
Pose Estimation (F16)
|
100% |
2265
9.16 IPS |
|
|
Pose Estimation (I8)
|
80% |
132
0.53 IPS |
|
|
Object Detection (F32)
|
100% |
1465
51.4 IPS |
|
|
Object Detection (F16)
|
100% |
2287
80.2 IPS |
|
|
Object Detection (I8)
|
52% |
478
16.8 IPS |
|
|
Face Detection (F32)
|
100% |
2579
29.6 IPS |
|
|
Face Detection (F16)
|
97% |
4674
53.7 IPS |
|
|
Face Detection (I8)
|
75% |
443
5.09 IPS |
|
|
Text Classification (F32)
|
100% |
604
238.8 IPS |
|
|
Text Classification (F16)
|
98% |
755
298.6 IPS |
|
|
Machine Translation (F32)
|
100% |
749
115.5 IPS |
|
|
Machine Translation (F16)
|
100% |
748
115.2 IPS |
