Upload Date | August 15 2024 07:27 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad16,4 |
Model ID | iPad16,4 |
Motherboard | J718AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 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 | 7.29 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4043
756.5 IPS |
|
Image Classification (F16)
|
100% |
14445
2.70 KIPS |
|
Image Classification (I8)
|
99% |
15832
2.96 KIPS |
|
Image Segmentation (F32)
|
100% |
1958
32.7 IPS |
|
Image Segmentation (F16)
|
100% |
2890
48.3 IPS |
|
Image Segmentation (I8)
|
100% |
2963
49.5 IPS |
|
Pose Estimation (F32)
|
100% |
26886
32.6 IPS |
|
Pose Estimation (F16)
|
100% |
109685
132.8 IPS |
|
Pose Estimation (I8)
|
100% |
111871
135.5 IPS |
|
Object Detection (F32)
|
100% |
3658
273.1 IPS |
|
Object Detection (F16)
|
100% |
7197
537.3 IPS |
|
Object Detection (I8)
|
97% |
3326
248.3 IPS |
|
Face Detection (F32)
|
100% |
11352
135.0 IPS |
|
Face Detection (F16)
|
97% |
22859
271.8 IPS |
|
Face Detection (I8)
|
96% |
23093
274.6 IPS |
|
Depth Estimation (F32)
|
100% |
19836
153.8 IPS |
|
Depth Estimation (F16)
|
100% |
59951
464.9 IPS |
|
Depth Estimation (I8)
|
37% |
64671
501.5 IPS |
|
Style Transfer (F32)
|
100% |
55263
72.7 IPS |
|
Style Transfer (F16)
|
100% |
160195
210.7 IPS |
|
Style Transfer (I8)
|
100% |
159663
210.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
8986
320.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
43371
1.55 KIPS |
|
Image Super-Resolution (I8)
|
100% |
39259
1.40 KIPS |
|
Text Classification (F32)
|
100% |
2733
3.93 KIPS |
|
Text Classification (F16)
|
100% |
4619
6.64 KIPS |
|
Text Classification (I8)
|
96% |
4617
6.63 KIPS |
|
Machine Translation (F32)
|
100% |
1081
19.9 IPS |
|
Machine Translation (F16)
|
100% |
2295
42.2 IPS |
|
Machine Translation (I8)
|
99% |
1022
18.8 IPS |