samsung SM-S908U1
Geekbench ML Score
438
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 03 2023 03:53 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | samsung SM-S908U1 |
| Model ID | samsung SM-S908U1 |
| Motherboard | taro |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.78 GHz |
| Cluster 1 | 4 Cores @ 1.79 GHz |
| Cluster 2 | 3 Cores @ 2.50 GHz |
| Cluster 3 | 1 Core @ 3.00 GHz |
| Memory Information | |
|---|---|
| Size | 10.95 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
348
37.3 IPS |
|
|
Image Classification (F16)
|
100% |
356
38.1 IPS |
|
|
Image Classification (I8)
|
81% |
189
20.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
708
4.37 IPS |
|
|
Image Segmentation (F16)
|
100% |
680
4.20 IPS |
|
|
Image Segmentation (I8)
|
89% |
948
5.86 IPS |
|
|
Pose Estimation (F32)
|
100% |
238
0.96 IPS |
|
|
Pose Estimation (F16)
|
100% |
223
0.90 IPS |
|
|
Pose Estimation (I8)
|
80% |
216
0.87 IPS |
|
|
Object Detection (F32)
|
100% |
451
15.8 IPS |
|
|
Object Detection (F16)
|
100% |
465
16.3 IPS |
|
|
Object Detection (I8)
|
52% |
302
10.6 IPS |
|
|
Face Detection (F32)
|
100% |
678
7.79 IPS |
|
|
Face Detection (F16)
|
100% |
649
7.46 IPS |
|
|
Face Detection (I8)
|
75% |
551
6.33 IPS |
|
|
Text Classification (F32)
|
100% |
337
133.2 IPS |
|
|
Text Classification (F16)
|
100% |
342
135.1 IPS |
|
|
Machine Translation (F32)
|
100% |
862
132.8 IPS |
|
|
Machine Translation (F16)
|
100% |
826
127.2 IPS |
