samsung SM-S921B
Geekbench ML Score
2171
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | acuesta |
| Upload Date | March 13 2025 05:07 PM |
| Views | 6 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | samsung SM-S921B |
| Model ID | samsung SM-S921B |
| Motherboard | s5e9945 |
| Governor | energy_aware |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 10 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
| Base Frequency | 1.96 GHz |
| Cluster 1 | 4 Cores @ 1.96 GHz |
| Cluster 2 | 3 Cores @ 2.59 GHz |
| Cluster 3 | 2 Cores @ 2.90 GHz |
| Cluster 4 | 1 Core @ 3.21 GHz |
| Memory Information | |
|---|---|
| Size | 7.06 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1647
176.4 IPS |
|
|
Image Classification (F16)
|
100% |
2659
284.9 IPS |
|
|
Image Classification (I8)
|
80% |
2329
249.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
4820
29.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
7283
45.0 IPS |
|
|
Image Segmentation (I8)
|
89% |
7384
45.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
2564
10.4 IPS |
|
|
Pose Estimation (F16)
|
100% |
5104
20.7 IPS |
|
|
Pose Estimation (I8)
|
80% |
5018
20.3 IPS |
|
|
Object Detection (F32)
|
100% |
757
26.5 IPS |
|
|
Object Detection (F16)
|
100% |
916
32.1 IPS |
|
|
Object Detection (I8)
|
54% |
873
30.6 IPS |
|
|
Face Detection (F32)
|
100% |
2873
33.0 IPS |
|
|
Face Detection (F16)
|
97% |
4353
50.0 IPS |
|
|
Face Detection (I8)
|
75% |
3584
41.2 IPS |
|
|
Text Classification (F32)
|
100% |
1333
527.1 IPS |
|
|
Text Classification (F16)
|
98% |
1335
528.2 IPS |
|
|
Machine Translation (F32)
|
100% |
546
84.2 IPS |
|
|
Machine Translation (F16)
|
100% |
547
84.3 IPS |
