Samsung Galaxy S20 5G
Geekbench ML Score
1329
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | November 05 2022 03:44 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy S20 5G |
| Model ID | samsung SM-G981N |
| Motherboard | kona |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 10.35 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
956
102.4 IPS |
|
|
Image Classification (F16)
|
100% |
1524
163.3 IPS |
|
|
Image Classification (I8)
|
80% |
1375
147.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
2394
14.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
4022
24.8 IPS |
|
|
Image Segmentation (I8)
|
89% |
4026
24.9 IPS |
|
|
Pose Estimation (F32)
|
100% |
1192
4.82 IPS |
|
|
Pose Estimation (F16)
|
100% |
2049
8.29 IPS |
|
|
Pose Estimation (I8)
|
80% |
2037
8.24 IPS |
|
|
Object Detection (F32)
|
100% |
665
23.3 IPS |
|
|
Object Detection (F16)
|
99% |
813
28.5 IPS |
|
|
Object Detection (I8)
|
53% |
799
28.0 IPS |
|
|
Face Detection (F32)
|
100% |
1785
20.5 IPS |
|
|
Face Detection (F16)
|
97% |
3045
35.0 IPS |
|
|
Face Detection (I8)
|
76% |
2749
31.6 IPS |
|
|
Text Classification (F32)
|
100% |
523
206.9 IPS |
|
|
Text Classification (F16)
|
98% |
563
222.6 IPS |
|
|
Machine Translation (F32)
|
100% |
552
85.1 IPS |
|
|
Machine Translation (F16)
|
100% |
553
85.3 IPS |
