Samsung Galaxy S21 5G
Geekbench ML Score
1102
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | July 14 2021 03:11 PM |
| Views | 45 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 5G |
| Model ID | samsung SM-G991U1 |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| 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 | 7.13 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
958
102.7 IPS |
|
|
Image Classification (F16)
|
100% |
1675
179.5 IPS |
|
|
Image Classification (I8)
|
79% |
4514
483.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
2349
14.5 IPS |
|
|
Image Segmentation (F16)
|
71% |
3530
21.8 IPS |
|
|
Image Segmentation (I8)
|
89% |
10142
62.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
570
2.31 IPS |
|
|
Pose Estimation (F16)
|
100% |
2010
8.13 IPS |
|
|
Pose Estimation (I8)
|
80% |
24603
99.6 IPS |
|
|
Object Detection (F32)
|
100% |
893
31.4 IPS |
|
|
Object Detection (F16)
|
100% |
1209
42.4 IPS |
|
|
Object Detection (I8)
|
56% |
1809
63.5 IPS |
|
|
Face Detection (F32)
|
100% |
613
7.05 IPS |
|
|
Face Detection (F16)
|
100% |
617
7.09 IPS |
|
|
Face Detection (I8)
|
76% |
22483
258.3 IPS |
|
|
Text Classification (F32)
|
100% |
10
4.05 IPS |
|
|
Text Classification (F16)
|
46% |
10
3.93 IPS |
|
|
Machine Translation (F32)
|
100% |
520
80.1 IPS |
|
|
Machine Translation (F16)
|
100% |
427
65.8 IPS |
