Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
370
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | January 19 2022 06:42 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998N |
| 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 | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
404
43.3 IPS |
|
|
Image Classification (F16)
|
100% |
374
40.0 IPS |
|
|
Image Classification (I8)
|
81% |
204
21.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
551
3.40 IPS |
|
|
Image Segmentation (F16)
|
100% |
551
3.41 IPS |
|
|
Image Segmentation (I8)
|
89% |
906
5.59 IPS |
|
|
Pose Estimation (F32)
|
100% |
269
1.09 IPS |
|
|
Pose Estimation (F16)
|
100% |
187
0.75 IPS |
|
|
Pose Estimation (I8)
|
80% |
150
0.61 IPS |
|
|
Object Detection (F32)
|
100% |
242
8.49 IPS |
|
|
Object Detection (F16)
|
100% |
275
9.64 IPS |
|
|
Object Detection (I8)
|
52% |
193
6.79 IPS |
|
|
Face Detection (F32)
|
100% |
492
5.65 IPS |
|
|
Face Detection (F16)
|
100% |
575
6.61 IPS |
|
|
Face Detection (I8)
|
75% |
470
5.40 IPS |
|
|
Text Classification (F32)
|
100% |
360
142.5 IPS |
|
|
Text Classification (F16)
|
100% |
391
154.8 IPS |
|
|
Machine Translation (F32)
|
100% |
626
96.5 IPS |
|
|
Machine Translation (F16)
|
100% |
654
100.9 IPS |
