iPad Pro (11-inch)
Geekbench ML Score
1287
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64
Result Information
| User | Jelke |
| Upload Date | May 08 2024 09:43 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 17.4.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,3 |
| Motherboard | J318AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| L1 Instruction Cache | 48.0 KB x 1 |
| L1 Data Cache | 32.0 KB x 1 |
| L2 Cache | 2.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Inference Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
786
147.0 IPS |
|
|
Image Classification (F16)
|
100% |
779
145.7 IPS |
|
|
Image Classification (I8)
|
99% |
1034
193.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
243
4.06 IPS |
|
|
Image Segmentation (F16)
|
100% |
261
4.36 IPS |
|
|
Image Segmentation (I8)
|
100% |
261
4.36 IPS |
|
|
Pose Estimation (F32)
|
100% |
2696
3.26 IPS |
|
|
Pose Estimation (F16)
|
100% |
3756
4.55 IPS |
|
|
Pose Estimation (I8)
|
100% |
3844
4.66 IPS |
|
|
Object Detection (F32)
|
100% |
856
63.9 IPS |
|
|
Object Detection (F16)
|
100% |
1090
81.3 IPS |
|
|
Object Detection (I8)
|
97% |
871
65.0 IPS |
|
|
Face Detection (F32)
|
100% |
3184
37.9 IPS |
|
|
Face Detection (F16)
|
98% |
3628
43.1 IPS |
|
|
Face Detection (I8)
|
97% |
3708
44.1 IPS |
|
|
Depth Estimation (F32)
|
100% |
2997
23.2 IPS |
|
|
Depth Estimation (F16)
|
100% |
4158
32.2 IPS |
|
|
Depth Estimation (I8)
|
99% |
4305
33.4 IPS |
|
|
Style Transfer (F32)
|
100% |
7692
10.1 IPS |
|
|
Style Transfer (F16)
|
100% |
9245
12.2 IPS |
|
|
Style Transfer (I8)
|
100% |
9278
12.2 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1579
56.4 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
2130
76.1 IPS |
|
|
Image Super-Resolution (I8)
|
100% |
2023
72.2 IPS |
|
|
Text Classification (F32)
|
100% |
207
297.6 IPS |
|
|
Text Classification (F16)
|
100% |
245
352.6 IPS |
|
|
Text Classification (I8)
|
96% |
247
355.7 IPS |
|
|
Machine Translation (F32)
|
100% |
361
6.64 IPS |
|
|
Machine Translation (F16)
|
100% |
354
6.51 IPS |
|
|
Machine Translation (I8)
|
99% |
361
6.65 IPS |
