Upload Date | January 12 2024 06:27 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.3 |
Model | iPhone 15 |
Model ID | iPhone15,4 |
Motherboard | D37AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 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 | 5.54 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
668
125.1 IPS |
|
Image Classification (F16)
|
100% |
5386
1.01 KIPS |
|
Image Classification (I8)
|
99% |
5863
1.10 KIPS |
|
Image Segmentation (F32)
|
100% |
1325
22.1 IPS |
|
Image Segmentation (F16)
|
100% |
1974
33.0 IPS |
|
Image Segmentation (I8)
|
100% |
1996
33.3 IPS |
|
Pose Estimation (F32)
|
100% |
11318
13.7 IPS |
|
Pose Estimation (F16)
|
100% |
80305
97.2 IPS |
|
Pose Estimation (I8)
|
100% |
82838
100.3 IPS |
|
Object Detection (F32)
|
100% |
1164
86.9 IPS |
|
Object Detection (F16)
|
100% |
3707
276.8 IPS |
|
Object Detection (I8)
|
97% |
1114
83.2 IPS |
|
Face Detection (F32)
|
100% |
4147
49.3 IPS |
|
Face Detection (F16)
|
97% |
10570
125.7 IPS |
|
Face Detection (I8)
|
96% |
10552
125.5 IPS |
|
Depth Estimation (F32)
|
100% |
8052
62.4 IPS |
|
Depth Estimation (F16)
|
100% |
35852
278.0 IPS |
|
Depth Estimation (I8)
|
37% |
33311
258.3 IPS |
|
Style Transfer (F32)
|
100% |
21187
27.9 IPS |
|
Style Transfer (F16)
|
100% |
120930
159.1 IPS |
|
Style Transfer (I8)
|
100% |
119286
156.9 IPS |
|
Image Super-Resolution (F32)
|
100% |
2680
95.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
17248
616.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
17690
631.8 IPS |
|
Text Classification (F32)
|
100% |
381
547.6 IPS |
|
Text Classification (F16)
|
100% |
385
553.1 IPS |
|
Text Classification (I8)
|
96% |
229
329.1 IPS |
|
Machine Translation (F32)
|
100% |
479
8.81 IPS |
|
Machine Translation (F16)
|
100% |
1150
21.2 IPS |
|
Machine Translation (I8)
|
99% |
525
9.67 IPS |