samsung SM-S908E
Geekbench ML Score
2881
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | laidbackdev |
| Upload Date | May 31 2023 01:57 PM |
| Views | 4 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | samsung SM-S908E |
| Model ID | samsung SM-S908E |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.50 GHz |
| Cluster 3 | 1 Core @ 3.00 GHz |
| Memory Information | |
|---|---|
| Size | 10.95 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1249
133.9 IPS |
|
|
Image Classification (F16)
|
100% |
9185
984.2 IPS |
|
|
Image Classification (I8)
|
80% |
22138
2.37 KIPS |
|
|
Image Segmentation (F32)
|
100% |
2727
16.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
8041
49.7 IPS |
|
|
Image Segmentation (I8)
|
89% |
36729
226.9 IPS |
|
|
Pose Estimation (F32)
|
100% |
583
2.36 IPS |
|
|
Pose Estimation (F16)
|
100% |
10543
42.7 IPS |
|
|
Pose Estimation (I8)
|
80% |
54920
222.2 IPS |
|
|
Object Detection (F32)
|
100% |
987
34.7 IPS |
|
|
Object Detection (F16)
|
100% |
1756
61.6 IPS |
|
|
Object Detection (I8)
|
53% |
1897
66.6 IPS |
|
|
Face Detection (F32)
|
100% |
1878
21.6 IPS |
|
|
Face Detection (F16)
|
97% |
6993
80.3 IPS |
|
|
Face Detection (I8)
|
76% |
47459
545.2 IPS |
|
|
Text Classification (F32)
|
100% |
14
5.52 IPS |
|
|
Text Classification (F16)
|
100% |
530
209.5 IPS |
|
|
Machine Translation (F32)
|
100% |
717
110.6 IPS |
|
|
Machine Translation (F16)
|
100% |
717
110.5 IPS |
