samsung SM-S908B
Geekbench ML Score
848
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | April 17 2022 08:12 PM |
| Views | 2 |
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 | 10.27 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
295
31.6 IPS |
|
|
Image Classification (F16)
|
100% |
723
77.5 IPS |
|
|
Image Classification (I8)
|
80% |
622
66.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
1222
7.55 IPS |
|
|
Image Segmentation (F16)
|
100% |
2995
18.5 IPS |
|
|
Image Segmentation (I8)
|
89% |
2820
17.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
465
1.88 IPS |
|
|
Pose Estimation (F16)
|
100% |
1144
4.63 IPS |
|
|
Pose Estimation (I8)
|
80% |
1104
4.47 IPS |
|
|
Object Detection (F32)
|
100% |
274
9.60 IPS |
|
|
Object Detection (F16)
|
100% |
473
16.6 IPS |
|
|
Object Detection (I8)
|
54% |
504
17.7 IPS |
|
|
Face Detection (F32)
|
100% |
1149
13.2 IPS |
|
|
Face Detection (F16)
|
97% |
2174
25.0 IPS |
|
|
Face Detection (I8)
|
76% |
2194
25.2 IPS |
|
|
Text Classification (F32)
|
100% |
284
112.4 IPS |
|
|
Text Classification (F16)
|
98% |
569
225.0 IPS |
|
|
Machine Translation (F32)
|
100% |
971
149.7 IPS |
|
|
Machine Translation (F16)
|
100% |
976
150.4 IPS |
