Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
343
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | May 31 2023 03:01 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 | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
336
36.0 IPS |
|
|
Image Classification (F16)
|
100% |
385
41.3 IPS |
|
|
Image Classification (I8)
|
81% |
207
22.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
528
3.26 IPS |
|
|
Image Segmentation (F16)
|
100% |
523
3.23 IPS |
|
|
Image Segmentation (I8)
|
89% |
650
4.01 IPS |
|
|
Pose Estimation (F32)
|
100% |
277
1.12 IPS |
|
|
Pose Estimation (F16)
|
100% |
277
1.12 IPS |
|
|
Pose Estimation (I8)
|
80% |
158
0.64 IPS |
|
|
Object Detection (F32)
|
100% |
233
8.19 IPS |
|
|
Object Detection (F16)
|
100% |
266
9.33 IPS |
|
|
Object Detection (I8)
|
52% |
245
8.59 IPS |
|
|
Face Detection (F32)
|
100% |
479
5.50 IPS |
|
|
Face Detection (F16)
|
100% |
493
5.66 IPS |
|
|
Face Detection (I8)
|
75% |
433
4.97 IPS |
|
|
Text Classification (F32)
|
100% |
265
104.8 IPS |
|
|
Text Classification (F16)
|
100% |
268
106.0 IPS |
|
|
Machine Translation (F32)
|
100% |
473
72.9 IPS |
|
|
Machine Translation (F16)
|
100% |
488
75.3 IPS |
