samsung SM-S908E
Geekbench ML Score
323
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | August 19 2024 12:22 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | samsung SM-S908E |
| Model ID | samsung SM-S908E |
| Motherboard | taro |
| CPU Information | |
|---|---|
| Name | Qualcomm Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 81 architecture 8 variant 1 part 529 revision 2 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 8 Cores @ 2.00 GHz |
| Memory Information | |
|---|---|
| Size | 7.78 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
390
41.8 IPS |
|
|
Image Classification (F16)
|
100% |
406
43.5 IPS |
|
|
Image Classification (I8)
|
81% |
108
11.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
438
2.71 IPS |
|
|
Image Segmentation (F16)
|
100% |
443
2.74 IPS |
|
|
Image Segmentation (I8)
|
89% |
197
1.21 IPS |
|
|
Pose Estimation (F32)
|
100% |
244
0.99 IPS |
|
|
Pose Estimation (F16)
|
100% |
243
0.98 IPS |
|
|
Pose Estimation (I8)
|
80% |
44
0.18 IPS |
|
|
Object Detection (F32)
|
100% |
554
19.5 IPS |
|
|
Object Detection (F16)
|
100% |
569
20.0 IPS |
|
|
Object Detection (I8)
|
52% |
160
5.60 IPS |
|
|
Face Detection (F32)
|
100% |
600
6.89 IPS |
|
|
Face Detection (F16)
|
100% |
591
6.79 IPS |
|
|
Face Detection (I8)
|
75% |
126
1.45 IPS |
|
|
Text Classification (F32)
|
100% |
455
179.8 IPS |
|
|
Text Classification (F16)
|
100% |
455
180.1 IPS |
|
|
Machine Translation (F32)
|
100% |
782
120.5 IPS |
|
|
Machine Translation (F16)
|
100% |
789
121.5 IPS |
