Upload Date | December 21 2023 11:14 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.1.2 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
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 | 5.49 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1010
188.9 IPS |
|
Image Classification (F16)
|
100% |
5546
1.04 KIPS |
|
Image Classification (I8)
|
99% |
5675
1.06 KIPS |
|
Image Segmentation (F32)
|
100% |
895
14.9 IPS |
|
Image Segmentation (F16)
|
100% |
1451
24.2 IPS |
|
Image Segmentation (I8)
|
100% |
1482
24.7 IPS |
|
Pose Estimation (F32)
|
100% |
11264
13.6 IPS |
|
Pose Estimation (F16)
|
100% |
80021
96.9 IPS |
|
Pose Estimation (I8)
|
100% |
66518
80.6 IPS |
|
Object Detection (F32)
|
100% |
1460
109.0 IPS |
|
Object Detection (F16)
|
100% |
3675
274.3 IPS |
|
Object Detection (I8)
|
97% |
1702
127.1 IPS |
|
Face Detection (F32)
|
100% |
4869
57.9 IPS |
|
Face Detection (F16)
|
97% |
10334
122.9 IPS |
|
Face Detection (I8)
|
96% |
10084
119.9 IPS |
|
Depth Estimation (F32)
|
100% |
8588
66.6 IPS |
|
Depth Estimation (F16)
|
100% |
34043
264.0 IPS |
|
Depth Estimation (I8)
|
37% |
43529
337.6 IPS |
|
Style Transfer (F32)
|
100% |
20940
27.5 IPS |
|
Style Transfer (F16)
|
100% |
114813
151.0 IPS |
|
Style Transfer (I8)
|
100% |
114963
151.2 IPS |
|
Image Super-Resolution (F32)
|
100% |
4188
149.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
17218
614.9 IPS |
|
Image Super-Resolution (I8)
|
100% |
16746
598.1 IPS |
|
Text Classification (F32)
|
100% |
393
565.2 IPS |
|
Text Classification (F16)
|
100% |
415
597.1 IPS |
|
Text Classification (I8)
|
96% |
230
330.6 IPS |
|
Machine Translation (F32)
|
100% |
620
11.4 IPS |
|
Machine Translation (F16)
|
100% |
1100
20.2 IPS |
|
Machine Translation (I8)
|
99% |
582
10.7 IPS |