Upload Date | August 17 2024 04:24 AM |
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, 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 | 7.21 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4092
765.7 IPS |
|
Image Classification (F16)
|
100% |
14486
2.71 KIPS |
|
Image Classification (I8)
|
99% |
15762
2.95 KIPS |
|
Image Segmentation (F32)
|
100% |
2002
33.4 IPS |
|
Image Segmentation (F16)
|
100% |
2964
49.5 IPS |
|
Image Segmentation (I8)
|
100% |
2867
47.9 IPS |
|
Pose Estimation (F32)
|
100% |
26501
32.1 IPS |
|
Pose Estimation (F16)
|
100% |
109519
132.6 IPS |
|
Pose Estimation (I8)
|
100% |
110972
134.4 IPS |
|
Object Detection (F32)
|
100% |
3228
241.0 IPS |
|
Object Detection (F16)
|
100% |
7196
537.2 IPS |
|
Object Detection (I8)
|
97% |
3421
255.4 IPS |
|
Face Detection (F32)
|
100% |
11179
132.9 IPS |
|
Face Detection (F16)
|
97% |
23067
274.3 IPS |
|
Face Detection (I8)
|
96% |
23082
274.4 IPS |
|
Depth Estimation (F32)
|
100% |
19875
154.1 IPS |
|
Depth Estimation (F16)
|
100% |
57350
444.7 IPS |
|
Depth Estimation (I8)
|
37% |
65058
504.5 IPS |
|
Style Transfer (F32)
|
100% |
54075
71.1 IPS |
|
Style Transfer (F16)
|
100% |
159642
210.0 IPS |
|
Style Transfer (I8)
|
100% |
160326
210.9 IPS |
|
Image Super-Resolution (F32)
|
100% |
8749
312.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
38837
1.39 KIPS |
|
Image Super-Resolution (I8)
|
100% |
38289
1.37 KIPS |
|
Text Classification (F32)
|
100% |
2780
4.00 KIPS |
|
Text Classification (F16)
|
100% |
4853
6.97 KIPS |
|
Text Classification (I8)
|
96% |
4794
6.89 KIPS |
|
Machine Translation (F32)
|
100% |
1113
20.5 IPS |
|
Machine Translation (F16)
|
100% |
2283
42.0 IPS |
|
Machine Translation (I8)
|
99% |
1027
18.9 IPS |