iPad Pro (9.7-inch)
Geekbench ML Score
694
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | August 06 2022 06:20 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.6 |
| Model | iPad Pro (9.7-inch) |
| Model ID | iPad6,3 |
| Motherboard | J127AP |
| CPU Information | |
|---|---|
| Name | Apple A9X |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM |
| Base Frequency | 2.26 GHz |
| L1 Instruction Cache | 64.0 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 3.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 1.92 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
655
70.2 IPS |
|
|
Image Classification (F16)
|
100% |
1103
118.1 IPS |
|
|
Image Classification (I8)
|
81% |
223
23.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
1825
11.3 IPS |
|
|
Image Segmentation (F16)
|
100% |
3090
19.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
428
2.64 IPS |
|
|
Pose Estimation (F32)
|
100% |
448
1.81 IPS |
|
|
Pose Estimation (F16)
|
100% |
1441
5.83 IPS |
|
|
Pose Estimation (I8)
|
80% |
78
0.32 IPS |
|
|
Object Detection (F32)
|
100% |
1001
35.1 IPS |
|
|
Object Detection (F16)
|
100% |
1363
47.8 IPS |
|
|
Object Detection (I8)
|
52% |
318
11.2 IPS |
|
|
Face Detection (F32)
|
100% |
1615
18.6 IPS |
|
|
Face Detection (F16)
|
97% |
3124
35.9 IPS |
|
|
Face Detection (I8)
|
75% |
319
3.67 IPS |
|
|
Text Classification (F32)
|
100% |
468
185.2 IPS |
|
|
Text Classification (F16)
|
98% |
591
233.7 IPS |
|
|
Machine Translation (F32)
|
100% |
496
76.5 IPS |
|
|
Machine Translation (F16)
|
100% |
517
79.7 IPS |
