Samsung Galaxy S21 5G
Geekbench ML Score
709
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | January 19 2022 05:43 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy S21 5G |
| Model ID | samsung SM-G991N |
| 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 | 7.03 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
381
40.9 IPS |
|
|
Image Classification (F16)
|
100% |
372
39.9 IPS |
|
|
Image Classification (I8)
|
81% |
407
43.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
632
3.90 IPS |
|
|
Image Segmentation (F16)
|
100% |
630
3.89 IPS |
|
|
Image Segmentation (I8)
|
89% |
1785
11.0 IPS |
|
|
Pose Estimation (F32)
|
100% |
518
2.10 IPS |
|
|
Pose Estimation (F16)
|
100% |
1923
7.78 IPS |
|
|
Pose Estimation (I8)
|
80% |
1843
7.46 IPS |
|
|
Object Detection (F32)
|
100% |
602
21.1 IPS |
|
|
Object Detection (F16)
|
99% |
913
32.0 IPS |
|
|
Object Detection (I8)
|
52% |
464
16.3 IPS |
|
|
Face Detection (F32)
|
100% |
524
6.02 IPS |
|
|
Face Detection (F16)
|
100% |
528
6.07 IPS |
|
|
Face Detection (I8)
|
75% |
547
6.29 IPS |
|
|
Text Classification (F32)
|
100% |
989
391.2 IPS |
|
|
Text Classification (F16)
|
100% |
992
392.2 IPS |
|
|
Machine Translation (F32)
|
100% |
718
110.7 IPS |
|
|
Machine Translation (F16)
|
100% |
712
109.7 IPS |
