User | gbenchgs |
Upload Date | August 15 2024 06:09 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad16,6 |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 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 | 15.07 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4195
785.0 IPS |
|
Image Classification (F16)
|
100% |
4483
838.9 IPS |
|
Image Classification (I8)
|
99% |
4080
763.4 IPS |
|
Image Segmentation (F32)
|
100% |
1990
33.2 IPS |
|
Image Segmentation (F16)
|
100% |
2181
36.4 IPS |
|
Image Segmentation (I8)
|
100% |
2214
37.0 IPS |
|
Pose Estimation (F32)
|
100% |
26596
32.2 IPS |
|
Pose Estimation (F16)
|
100% |
28350
34.3 IPS |
|
Pose Estimation (I8)
|
100% |
27308
33.1 IPS |
|
Object Detection (F32)
|
100% |
3381
252.4 IPS |
|
Object Detection (F16)
|
100% |
3829
285.9 IPS |
|
Object Detection (I8)
|
97% |
3242
242.1 IPS |
|
Face Detection (F32)
|
100% |
10982
130.6 IPS |
|
Face Detection (F16)
|
98% |
13741
163.4 IPS |
|
Face Detection (I8)
|
97% |
13423
159.6 IPS |
|
Depth Estimation (F32)
|
100% |
19623
152.2 IPS |
|
Depth Estimation (F16)
|
100% |
21751
168.7 IPS |
|
Depth Estimation (I8)
|
99% |
19938
154.6 IPS |
|
Style Transfer (F32)
|
100% |
55710
73.3 IPS |
|
Style Transfer (F16)
|
100% |
65067
85.6 IPS |
|
Style Transfer (I8)
|
100% |
64777
85.2 IPS |
|
Image Super-Resolution (F32)
|
100% |
9478
338.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
8684
310.1 IPS |
|
Image Super-Resolution (I8)
|
100% |
9616
343.4 IPS |
|
Text Classification (F32)
|
100% |
2720
3.91 KIPS |
|
Text Classification (F16)
|
100% |
4935
7.09 KIPS |
|
Text Classification (I8)
|
96% |
5075
7.29 KIPS |
|
Machine Translation (F32)
|
100% |
1067
19.6 IPS |
|
Machine Translation (F16)
|
100% |
1123
20.7 IPS |
|
Machine Translation (I8)
|
99% |
1004
18.5 IPS |