Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
436
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | March 19 2023 03:44 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998W |
| 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 |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
411
44.1 IPS |
|
|
Image Classification (F16)
|
100% |
419
44.9 IPS |
|
|
Image Classification (I8)
|
81% |
187
20.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
648
4.00 IPS |
|
|
Image Segmentation (F16)
|
100% |
627
3.87 IPS |
|
|
Image Segmentation (I8)
|
89% |
915
5.65 IPS |
|
|
Pose Estimation (F32)
|
100% |
261
1.06 IPS |
|
|
Pose Estimation (F16)
|
100% |
252
1.02 IPS |
|
|
Pose Estimation (I8)
|
80% |
241
0.98 IPS |
|
|
Object Detection (F32)
|
100% |
415
14.6 IPS |
|
|
Object Detection (F16)
|
100% |
382
13.4 IPS |
|
|
Object Detection (I8)
|
52% |
280
9.82 IPS |
|
|
Face Detection (F32)
|
100% |
631
7.25 IPS |
|
|
Face Detection (F16)
|
100% |
667
7.66 IPS |
|
|
Face Detection (I8)
|
75% |
542
6.22 IPS |
|
|
Text Classification (F32)
|
100% |
362
143.2 IPS |
|
|
Text Classification (F16)
|
100% |
361
142.7 IPS |
|
|
Machine Translation (F32)
|
100% |
761
117.2 IPS |
|
|
Machine Translation (F16)
|
100% |
754
116.2 IPS |
