Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
1401
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 22 2024 04:22 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 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 | 10.07 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
973
104.3 IPS |
|
|
Image Classification (F16)
|
100% |
977
104.7 IPS |
|
|
Image Classification (I8)
|
79% |
2900
310.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
1967
12.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
2892
17.9 IPS |
|
|
Image Segmentation (I8)
|
89% |
9178
56.7 IPS |
|
|
Pose Estimation (F32)
|
100% |
424
1.71 IPS |
|
|
Pose Estimation (F16)
|
100% |
1919
7.76 IPS |
|
|
Pose Estimation (I8)
|
80% |
25251
102.2 IPS |
|
|
Object Detection (F32)
|
100% |
641
22.5 IPS |
|
|
Object Detection (F16)
|
100% |
926
32.5 IPS |
|
|
Object Detection (I8)
|
56% |
1444
50.7 IPS |
|
|
Face Detection (F32)
|
100% |
1654
19.0 IPS |
|
|
Face Detection (F16)
|
97% |
2697
31.0 IPS |
|
|
Face Detection (I8)
|
76% |
22415
257.5 IPS |
|
|
Text Classification (F32)
|
100% |
15
5.85 IPS |
|
|
Text Classification (F16)
|
100% |
336
133.0 IPS |
|
|
Machine Translation (F32)
|
100% |
685
105.5 IPS |
|
|
Machine Translation (F16)
|
100% |
696
107.3 IPS |
