Upload Date | May 11 2024 11:47 AM |
Views | 9 |
System Information | |
---|---|
Operating System | iOS 17.5 |
Model | iPad16,4 |
Model ID | iPad16,4 |
Motherboard | J718AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.40 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 | 15.13 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4185
783.2 IPS |
|
Image Classification (F16)
|
100% |
5810
1.09 KIPS |
|
Image Classification (I8)
|
99% |
7790
1.46 KIPS |
|
Image Segmentation (F32)
|
100% |
1987
33.2 IPS |
|
Image Segmentation (F16)
|
100% |
2302
38.5 IPS |
|
Image Segmentation (I8)
|
100% |
2276
38.0 IPS |
|
Pose Estimation (F32)
|
100% |
27013
32.7 IPS |
|
Pose Estimation (F16)
|
100% |
89514
108.4 IPS |
|
Pose Estimation (I8)
|
100% |
93955
113.8 IPS |
|
Object Detection (F32)
|
100% |
3661
273.3 IPS |
|
Object Detection (F16)
|
100% |
4764
355.7 IPS |
|
Object Detection (I8)
|
97% |
3395
253.4 IPS |
|
Face Detection (F32)
|
100% |
11386
135.4 IPS |
|
Face Detection (F16)
|
97% |
12851
152.8 IPS |
|
Face Detection (I8)
|
96% |
13304
158.2 IPS |
|
Depth Estimation (F32)
|
100% |
19794
153.5 IPS |
|
Depth Estimation (F16)
|
100% |
40114
311.1 IPS |
|
Depth Estimation (I8)
|
37% |
40747
316.0 IPS |
|
Style Transfer (F32)
|
100% |
55414
72.9 IPS |
|
Style Transfer (F16)
|
100% |
104698
137.7 IPS |
|
Style Transfer (I8)
|
100% |
103891
136.7 IPS |
|
Image Super-Resolution (F32)
|
100% |
8630
308.2 IPS |
|
Image Super-Resolution (F16)
|
100% |
20868
745.3 IPS |
|
Image Super-Resolution (I8)
|
100% |
18785
670.9 IPS |
|
Text Classification (F32)
|
100% |
1372
1.97 KIPS |
|
Text Classification (F16)
|
100% |
1398
2.01 KIPS |
|
Text Classification (I8)
|
96% |
1033
1.49 KIPS |
|
Machine Translation (F32)
|
100% |
1055
19.4 IPS |
|
Machine Translation (F16)
|
100% |
1755
32.3 IPS |
|
Machine Translation (I8)
|
99% |
902
16.6 IPS |