Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
666
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | January 19 2022 07:22 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998N |
| 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 | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
455
48.7 IPS |
|
|
Image Classification (F16)
|
100% |
431
46.1 IPS |
|
|
Image Classification (I8)
|
81% |
379
40.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
652
4.02 IPS |
|
|
Image Segmentation (F16)
|
100% |
654
4.04 IPS |
|
|
Image Segmentation (I8)
|
89% |
2009
12.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
531
2.15 IPS |
|
|
Pose Estimation (F16)
|
100% |
1808
7.32 IPS |
|
|
Pose Estimation (I8)
|
80% |
1767
7.15 IPS |
|
|
Object Detection (F32)
|
100% |
541
19.0 IPS |
|
|
Object Detection (F16)
|
99% |
802
28.2 IPS |
|
|
Object Detection (I8)
|
52% |
350
12.3 IPS |
|
|
Face Detection (F32)
|
100% |
551
6.33 IPS |
|
|
Face Detection (F16)
|
100% |
502
5.77 IPS |
|
|
Face Detection (I8)
|
75% |
435
5.00 IPS |
|
|
Text Classification (F32)
|
100% |
807
319.3 IPS |
|
|
Text Classification (F16)
|
100% |
813
321.6 IPS |
|
|
Machine Translation (F32)
|
100% |
590
91.0 IPS |
|
|
Machine Translation (F16)
|
100% |
589
90.7 IPS |
