Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
698
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 12 2021 09:15 PM |
| Views | 2 |
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 | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
485
52.0 IPS |
|
|
Image Classification (F16)
|
100% |
439
47.1 IPS |
|
|
Image Classification (I8)
|
81% |
347
37.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
659
4.07 IPS |
|
|
Image Segmentation (F16)
|
100% |
637
3.93 IPS |
|
|
Image Segmentation (I8)
|
89% |
2106
13.0 IPS |
|
|
Pose Estimation (F32)
|
100% |
548
2.22 IPS |
|
|
Pose Estimation (F16)
|
100% |
1822
7.37 IPS |
|
|
Pose Estimation (I8)
|
80% |
1664
6.73 IPS |
|
|
Object Detection (F32)
|
100% |
546
19.1 IPS |
|
|
Object Detection (F16)
|
99% |
902
31.6 IPS |
|
|
Object Detection (I8)
|
52% |
403
14.1 IPS |
|
|
Face Detection (F32)
|
100% |
568
6.53 IPS |
|
|
Face Detection (F16)
|
100% |
549
6.31 IPS |
|
|
Face Detection (I8)
|
75% |
475
5.46 IPS |
|
|
Text Classification (F32)
|
100% |
872
344.7 IPS |
|
|
Text Classification (F16)
|
100% |
881
348.5 IPS |
|
|
Machine Translation (F32)
|
100% |
665
102.5 IPS |
|
|
Machine Translation (F16)
|
100% |
667
102.8 IPS |
