Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
1040
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 31 2023 03:03 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U1 |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| 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 | 13.96 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
748
80.2 IPS |
|
|
Image Classification (F16)
|
100% |
1190
127.5 IPS |
|
|
Image Classification (I8)
|
80% |
1080
115.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
1965
12.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
3249
20.1 IPS |
|
|
Image Segmentation (I8)
|
89% |
3183
19.7 IPS |
|
|
Pose Estimation (F32)
|
100% |
869
3.52 IPS |
|
|
Pose Estimation (F16)
|
100% |
1639
6.63 IPS |
|
|
Pose Estimation (I8)
|
80% |
1631
6.60 IPS |
|
|
Object Detection (F32)
|
100% |
447
15.7 IPS |
|
|
Object Detection (F16)
|
99% |
483
17.0 IPS |
|
|
Object Detection (I8)
|
53% |
472
16.6 IPS |
|
|
Face Detection (F32)
|
100% |
1404
16.1 IPS |
|
|
Face Detection (F16)
|
97% |
2487
28.6 IPS |
|
|
Face Detection (I8)
|
75% |
2235
25.7 IPS |
|
|
Text Classification (F32)
|
100% |
466
184.4 IPS |
|
|
Text Classification (F16)
|
98% |
572
226.3 IPS |
|
|
Machine Translation (F32)
|
100% |
473
72.9 IPS |
|
|
Machine Translation (F16)
|
100% |
470
72.5 IPS |
