samsung SM-S908U1
Geekbench ML Score
2223
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | July 16 2022 08:27 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | samsung SM-S908U1 |
| Model ID | samsung SM-S908U1 |
| 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 | 7.05 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1760
188.6 IPS |
|
|
Image Classification (F16)
|
100% |
2676
286.7 IPS |
|
|
Image Classification (I8)
|
80% |
2435
260.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
4308
26.6 IPS |
|
|
Image Segmentation (F16)
|
100% |
7234
44.7 IPS |
|
|
Image Segmentation (I8)
|
89% |
7185
44.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
2025
8.19 IPS |
|
|
Pose Estimation (F16)
|
100% |
3845
15.6 IPS |
|
|
Pose Estimation (I8)
|
80% |
3863
15.6 IPS |
|
|
Object Detection (F32)
|
100% |
862
30.3 IPS |
|
|
Object Detection (F16)
|
99% |
928
32.6 IPS |
|
|
Object Detection (I8)
|
53% |
946
33.2 IPS |
|
|
Face Detection (F32)
|
100% |
2924
33.6 IPS |
|
|
Face Detection (F16)
|
97% |
5276
60.6 IPS |
|
|
Face Detection (I8)
|
75% |
4671
53.7 IPS |
|
|
Text Classification (F32)
|
100% |
851
336.7 IPS |
|
|
Text Classification (F16)
|
98% |
993
392.7 IPS |
|
|
Machine Translation (F32)
|
100% |
1054
162.4 IPS |
|
|
Machine Translation (F16)
|
100% |
1049
161.7 IPS |
