Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
1495
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 12 2021 08:00 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998B |
| Motherboard | exynos2100 |
| Governor | energy_step |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 2.21 GHz |
| Cluster 1 | 4 Cores @ 2.21 GHz |
| Cluster 2 | 3 Cores @ 2.81 GHz |
| Cluster 3 | 1 Core @ 2.91 GHz |
| Memory Information | |
|---|---|
| Size | 10.31 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1076
115.3 IPS |
|
|
Image Classification (F16)
|
100% |
1921
205.8 IPS |
|
|
Image Classification (I8)
|
80% |
1638
175.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
2209
13.6 IPS |
|
|
Image Segmentation (F16)
|
100% |
4039
25.0 IPS |
|
|
Image Segmentation (I8)
|
89% |
4068
25.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
657
2.66 IPS |
|
|
Pose Estimation (F16)
|
100% |
2595
10.5 IPS |
|
|
Pose Estimation (I8)
|
80% |
2584
10.5 IPS |
|
|
Object Detection (F32)
|
100% |
583
20.5 IPS |
|
|
Object Detection (F16)
|
100% |
858
30.1 IPS |
|
|
Object Detection (I8)
|
54% |
872
30.6 IPS |
|
|
Face Detection (F32)
|
100% |
1760
20.2 IPS |
|
|
Face Detection (F16)
|
97% |
3394
39.0 IPS |
|
|
Face Detection (I8)
|
75% |
2939
33.8 IPS |
|
|
Text Classification (F32)
|
100% |
940
372.0 IPS |
|
|
Text Classification (F16)
|
98% |
1185
468.6 IPS |
|
|
Machine Translation (F32)
|
100% |
681
104.9 IPS |
|
|
Machine Translation (F16)
|
100% |
665
102.5 IPS |
