samsung SM-S918B
Geekbench ML Score
2437
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 10 2023 08:53 PM |
| Views | 4 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | samsung SM-S918B |
| Model ID | samsung SM-S918B |
| Motherboard | kalama |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
| Base Frequency | 2.02 GHz |
| Cluster 1 | 3 Cores @ 2.02 GHz |
| Cluster 2 | 4 Cores @ 2.80 GHz |
| Cluster 3 | 1 Core @ 3.36 GHz |
| Memory Information | |
|---|---|
| Size | 6.91 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1849
198.1 IPS |
|
|
Image Classification (F16)
|
100% |
2665
285.5 IPS |
|
|
Image Classification (I8)
|
80% |
2407
257.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
5109
31.6 IPS |
|
|
Image Segmentation (F16)
|
100% |
8913
55.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
8232
50.8 IPS |
|
|
Pose Estimation (F32)
|
100% |
2624
10.6 IPS |
|
|
Pose Estimation (F16)
|
100% |
4888
19.8 IPS |
|
|
Pose Estimation (I8)
|
80% |
4842
19.6 IPS |
|
|
Object Detection (F32)
|
100% |
825
29.0 IPS |
|
|
Object Detection (F16)
|
99% |
1016
35.7 IPS |
|
|
Object Detection (I8)
|
53% |
986
34.6 IPS |
|
|
Face Detection (F32)
|
100% |
3754
43.1 IPS |
|
|
Face Detection (F16)
|
97% |
5907
67.9 IPS |
|
|
Face Detection (I8)
|
75% |
5117
58.8 IPS |
|
|
Text Classification (F32)
|
100% |
751
296.9 IPS |
|
|
Text Classification (F16)
|
98% |
864
341.7 IPS |
|
|
Machine Translation (F32)
|
100% |
1159
178.6 IPS |
|
|
Machine Translation (F16)
|
100% |
1157
178.3 IPS |
