Upload Date | August 15 2024 05:13 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad16,3 |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.39 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% |
4097
766.6 IPS |
|
Image Classification (F16)
|
100% |
14095
2.64 KIPS |
|
Image Classification (I8)
|
99% |
15929
2.98 KIPS |
|
Image Segmentation (F32)
|
100% |
1876
31.3 IPS |
|
Image Segmentation (F16)
|
100% |
2905
48.5 IPS |
|
Image Segmentation (I8)
|
100% |
2948
49.2 IPS |
|
Pose Estimation (F32)
|
100% |
26850
32.5 IPS |
|
Pose Estimation (F16)
|
100% |
109235
132.3 IPS |
|
Pose Estimation (I8)
|
100% |
110045
133.3 IPS |
|
Object Detection (F32)
|
100% |
3629
270.9 IPS |
|
Object Detection (F16)
|
100% |
7088
529.1 IPS |
|
Object Detection (I8)
|
97% |
3341
249.4 IPS |
|
Face Detection (F32)
|
100% |
11080
131.7 IPS |
|
Face Detection (F16)
|
97% |
22647
269.3 IPS |
|
Face Detection (I8)
|
96% |
23051
274.1 IPS |
|
Depth Estimation (F32)
|
100% |
19754
153.2 IPS |
|
Depth Estimation (F16)
|
100% |
59262
459.6 IPS |
|
Depth Estimation (I8)
|
37% |
62066
481.3 IPS |
|
Style Transfer (F32)
|
100% |
54750
72.0 IPS |
|
Style Transfer (F16)
|
100% |
159781
210.2 IPS |
|
Style Transfer (I8)
|
100% |
160668
211.3 IPS |
|
Image Super-Resolution (F32)
|
100% |
8907
318.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
39151
1.40 KIPS |
|
Image Super-Resolution (I8)
|
100% |
40464
1.45 KIPS |
|
Text Classification (F32)
|
100% |
2732
3.93 KIPS |
|
Text Classification (F16)
|
100% |
4677
6.72 KIPS |
|
Text Classification (I8)
|
96% |
4717
6.78 KIPS |
|
Machine Translation (F32)
|
100% |
1078
19.8 IPS |
|
Machine Translation (F16)
|
100% |
2294
42.2 IPS |
|
Machine Translation (I8)
|
99% |
1019
18.7 IPS |