iPad14,5
Geekbench ML Score
3443
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| Upload Date | June 10 2023 07:08 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 17.0 |
| Model | iPad14,5 |
| Model ID | iPad14,5 |
| Motherboard | J620AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.48 GHz |
| 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 | 7.32 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
4795
513.8 IPS |
|
|
Image Classification (F16)
|
100% |
6867
735.7 IPS |
|
|
Image Classification (I8)
|
81% |
734
78.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
11324
69.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
16422
101.4 IPS |
|
|
Image Segmentation (I8)
|
89% |
1343
8.30 IPS |
|
|
Pose Estimation (F32)
|
100% |
4210
17.0 IPS |
|
|
Pose Estimation (F16)
|
100% |
9641
39.0 IPS |
|
|
Pose Estimation (I8)
|
80% |
253
1.03 IPS |
|
|
Object Detection (F32)
|
100% |
5291
185.7 IPS |
|
|
Object Detection (F16)
|
100% |
5106
179.2 IPS |
|
|
Object Detection (I8)
|
52% |
1052
36.9 IPS |
|
|
Face Detection (F32)
|
100% |
9654
110.9 IPS |
|
|
Face Detection (F16)
|
97% |
16217
186.3 IPS |
|
|
Face Detection (I8)
|
75% |
1030
11.8 IPS |
|
|
Text Classification (F32)
|
100% |
3642
1.44 KIPS |
|
|
Text Classification (F16)
|
100% |
4028
1.59 KIPS |
|
|
Machine Translation (F32)
|
100% |
1984
305.8 IPS |
|
|
Machine Translation (F16)
|
100% |
1932
297.8 IPS |
