Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
1731
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | January 19 2022 10:21 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| 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 | 9.97 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1384
148.2 IPS |
|
|
Image Classification (F16)
|
100% |
2191
234.7 IPS |
|
|
Image Classification (I8)
|
80% |
1995
213.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
3383
20.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
5409
33.4 IPS |
|
|
Image Segmentation (I8)
|
89% |
6049
37.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
1507
6.10 IPS |
|
|
Pose Estimation (F16)
|
100% |
2775
11.2 IPS |
|
|
Pose Estimation (I8)
|
80% |
2793
11.3 IPS |
|
|
Object Detection (F32)
|
100% |
863
30.3 IPS |
|
|
Object Detection (F16)
|
99% |
963
33.8 IPS |
|
|
Object Detection (I8)
|
53% |
975
34.2 IPS |
|
|
Face Detection (F32)
|
100% |
2439
28.0 IPS |
|
|
Face Detection (F16)
|
97% |
3838
44.1 IPS |
|
|
Face Detection (I8)
|
75% |
3721
42.7 IPS |
|
|
Text Classification (F32)
|
100% |
773
305.7 IPS |
|
|
Text Classification (F16)
|
98% |
745
294.8 IPS |
|
|
Machine Translation (F32)
|
100% |
516
79.5 IPS |
|
|
Machine Translation (F16)
|
100% |
519
80.0 IPS |
