samsung SM-S908B
Geekbench ML Score
808
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | mihun70 |
| Upload Date | October 10 2022 06:18 PM |
| Views | 4 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | samsung SM-S908B |
| Model ID | samsung SM-S908B |
| Motherboard | s5e9925 |
| Governor | energy_aware |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.82 GHz |
| Cluster 1 | 4 Cores @ 1.82 GHz |
| Cluster 2 | 3 Cores @ 2.52 GHz |
| Cluster 3 | 1 Core @ 2.80 GHz |
| Memory Information | |
|---|---|
| Size | 7.12 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
290
31.1 IPS |
|
|
Image Classification (F16)
|
100% |
764
81.9 IPS |
|
|
Image Classification (I8)
|
80% |
633
67.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
1270
7.84 IPS |
|
|
Image Segmentation (F16)
|
100% |
2983
18.4 IPS |
|
|
Image Segmentation (I8)
|
89% |
2868
17.7 IPS |
|
|
Pose Estimation (F32)
|
100% |
459
1.86 IPS |
|
|
Pose Estimation (F16)
|
100% |
1078
4.36 IPS |
|
|
Pose Estimation (I8)
|
80% |
1069
4.33 IPS |
|
|
Object Detection (F32)
|
100% |
223
7.81 IPS |
|
|
Object Detection (F16)
|
100% |
480
16.8 IPS |
|
|
Object Detection (I8)
|
54% |
490
17.2 IPS |
|
|
Face Detection (F32)
|
100% |
1104
12.7 IPS |
|
|
Face Detection (F16)
|
97% |
2287
26.3 IPS |
|
|
Face Detection (I8)
|
76% |
1865
21.4 IPS |
|
|
Text Classification (F32)
|
100% |
303
120.0 IPS |
|
|
Text Classification (F16)
|
98% |
532
210.5 IPS |
|
|
Machine Translation (F32)
|
100% |
740
114.0 IPS |
|
|
Machine Translation (F16)
|
100% |
742
114.3 IPS |
