Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
671
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | July 11 2021 11:47 AM |
| Views | 42 |
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 | 14.24 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
369
39.6 IPS |
|
|
Image Classification (F16)
|
100% |
367
39.3 IPS |
|
|
Image Classification (I8)
|
81% |
319
34.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
604
3.73 IPS |
|
|
Image Segmentation (F16)
|
100% |
601
3.71 IPS |
|
|
Image Segmentation (I8)
|
89% |
1966
12.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
530
2.14 IPS |
|
|
Pose Estimation (F16)
|
100% |
1875
7.59 IPS |
|
|
Pose Estimation (I8)
|
80% |
1787
7.23 IPS |
|
|
Object Detection (F32)
|
100% |
586
20.6 IPS |
|
|
Object Detection (F16)
|
99% |
821
28.8 IPS |
|
|
Object Detection (I8)
|
52% |
412
14.5 IPS |
|
|
Face Detection (F32)
|
100% |
601
6.90 IPS |
|
|
Face Detection (F16)
|
100% |
510
5.85 IPS |
|
|
Face Detection (I8)
|
75% |
458
5.26 IPS |
|
|
Text Classification (F32)
|
100% |
850
336.4 IPS |
|
|
Text Classification (F16)
|
100% |
903
357.3 IPS |
|
|
Machine Translation (F32)
|
100% |
664
102.4 IPS |
|
|
Machine Translation (F16)
|
100% |
660
101.8 IPS |
