Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
414
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 12 2021 07:58 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998B |
| 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% |
379
40.6 IPS |
|
|
Image Classification (F16)
|
100% |
400
42.8 IPS |
|
|
Image Classification (I8)
|
81% |
234
25.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
609
3.76 IPS |
|
|
Image Segmentation (F16)
|
100% |
611
3.78 IPS |
|
|
Image Segmentation (I8)
|
89% |
926
5.72 IPS |
|
|
Pose Estimation (F32)
|
100% |
273
1.10 IPS |
|
|
Pose Estimation (F16)
|
100% |
260
1.05 IPS |
|
|
Pose Estimation (I8)
|
80% |
228
0.92 IPS |
|
|
Object Detection (F32)
|
100% |
314
11.0 IPS |
|
|
Object Detection (F16)
|
100% |
335
11.8 IPS |
|
|
Object Detection (I8)
|
52% |
288
10.1 IPS |
|
|
Face Detection (F32)
|
100% |
572
6.58 IPS |
|
|
Face Detection (F16)
|
100% |
577
6.63 IPS |
|
|
Face Detection (I8)
|
75% |
574
6.60 IPS |
|
|
Text Classification (F32)
|
100% |
342
135.2 IPS |
|
|
Text Classification (F16)
|
100% |
401
158.7 IPS |
|
|
Machine Translation (F32)
|
100% |
586
90.3 IPS |
|
|
Machine Translation (F16)
|
100% |
590
91.0 IPS |
