Upload Date | October 15 2024 06:56 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
Model | iPad16,3 |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.30 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% |
4263
797.8 IPS |
|
Image Classification (F16)
|
100% |
14561
2.72 KIPS |
|
Image Classification (I8)
|
99% |
16485
3.08 KIPS |
|
Image Segmentation (F32)
|
100% |
1953
32.6 IPS |
|
Image Segmentation (F16)
|
100% |
2792
46.6 IPS |
|
Image Segmentation (I8)
|
100% |
2905
48.5 IPS |
|
Pose Estimation (F32)
|
100% |
27040
32.7 IPS |
|
Pose Estimation (F16)
|
100% |
108807
131.8 IPS |
|
Pose Estimation (I8)
|
100% |
108889
131.9 IPS |
|
Object Detection (F32)
|
100% |
3719
277.7 IPS |
|
Object Detection (F16)
|
100% |
7663
572.1 IPS |
|
Object Detection (I8)
|
97% |
3456
258.0 IPS |
|
Face Detection (F32)
|
100% |
11294
134.3 IPS |
|
Face Detection (F16)
|
97% |
24166
287.3 IPS |
|
Face Detection (I8)
|
96% |
23725
282.1 IPS |
|
Depth Estimation (F32)
|
100% |
20422
158.4 IPS |
|
Depth Estimation (F16)
|
100% |
76008
589.4 IPS |
|
Depth Estimation (I8)
|
37% |
67305
522.0 IPS |
|
Style Transfer (F32)
|
100% |
55538
73.1 IPS |
|
Style Transfer (F16)
|
100% |
159636
210.0 IPS |
|
Style Transfer (I8)
|
100% |
162041
213.2 IPS |
|
Image Super-Resolution (F32)
|
100% |
8704
310.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
41852
1.49 KIPS |
|
Image Super-Resolution (I8)
|
100% |
46240
1.65 KIPS |
|
Text Classification (F32)
|
100% |
2753
3.96 KIPS |
|
Text Classification (F16)
|
100% |
4838
6.95 KIPS |
|
Text Classification (I8)
|
96% |
4895
7.03 KIPS |
|
Machine Translation (F32)
|
100% |
1066
19.6 IPS |
|
Machine Translation (F16)
|
100% |
2404
44.2 IPS |
|
Machine Translation (I8)
|
99% |
1008
18.6 IPS |