Upload Date | August 15 2024 06:06 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad16,6 |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
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 | 15.07 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4322
808.8 IPS |
|
Image Classification (F16)
|
100% |
14252
2.67 KIPS |
|
Image Classification (I8)
|
99% |
16480
3.08 KIPS |
|
Image Segmentation (F32)
|
100% |
1906
31.8 IPS |
|
Image Segmentation (F16)
|
100% |
2840
47.4 IPS |
|
Image Segmentation (I8)
|
100% |
2793
46.7 IPS |
|
Pose Estimation (F32)
|
100% |
27110
32.8 IPS |
|
Pose Estimation (F16)
|
100% |
109329
132.4 IPS |
|
Pose Estimation (I8)
|
100% |
111286
134.8 IPS |
|
Object Detection (F32)
|
100% |
3728
278.3 IPS |
|
Object Detection (F16)
|
100% |
7261
542.1 IPS |
|
Object Detection (I8)
|
97% |
3428
255.9 IPS |
|
Face Detection (F32)
|
100% |
11348
134.9 IPS |
|
Face Detection (F16)
|
97% |
22372
266.0 IPS |
|
Face Detection (I8)
|
96% |
22865
271.9 IPS |
|
Depth Estimation (F32)
|
100% |
20190
156.6 IPS |
|
Depth Estimation (F16)
|
100% |
76876
596.2 IPS |
|
Depth Estimation (I8)
|
37% |
53914
418.1 IPS |
|
Style Transfer (F32)
|
100% |
55540
73.1 IPS |
|
Style Transfer (F16)
|
100% |
160831
211.6 IPS |
|
Style Transfer (I8)
|
100% |
160626
211.3 IPS |
|
Image Super-Resolution (F32)
|
100% |
9714
346.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
41376
1.48 KIPS |
|
Image Super-Resolution (I8)
|
100% |
40189
1.44 KIPS |
|
Text Classification (F32)
|
100% |
2791
4.01 KIPS |
|
Text Classification (F16)
|
100% |
5113
7.35 KIPS |
|
Text Classification (I8)
|
96% |
5004
7.19 KIPS |
|
Machine Translation (F32)
|
100% |
1071
19.7 IPS |
|
Machine Translation (F16)
|
100% |
2274
41.8 IPS |
|
Machine Translation (I8)
|
99% |
1016
18.7 IPS |