samsung SM-F926B
Geekbench ML Score
1106
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | vikarti |
| Upload Date | September 14 2024 06:24 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | samsung SM-F926B |
| Model ID | samsung SM-F926B |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| 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 | 11.09 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
806
86.4 IPS |
|
|
Image Classification (F16)
|
100% |
1220
130.7 IPS |
|
|
Image Classification (I8)
|
80% |
1162
124.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
2085
12.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
3548
21.9 IPS |
|
|
Image Segmentation (I8)
|
89% |
3381
20.9 IPS |
|
|
Pose Estimation (F32)
|
100% |
870
3.52 IPS |
|
|
Pose Estimation (F16)
|
100% |
1630
6.60 IPS |
|
|
Pose Estimation (I8)
|
80% |
1617
6.54 IPS |
|
|
Object Detection (F32)
|
100% |
459
16.1 IPS |
|
|
Object Detection (F16)
|
99% |
522
18.3 IPS |
|
|
Object Detection (I8)
|
53% |
570
20.0 IPS |
|
|
Face Detection (F32)
|
100% |
1528
17.6 IPS |
|
|
Face Detection (F16)
|
97% |
2740
31.5 IPS |
|
|
Face Detection (I8)
|
75% |
2464
28.3 IPS |
|
|
Text Classification (F32)
|
100% |
486
192.3 IPS |
|
|
Text Classification (F16)
|
98% |
590
233.3 IPS |
|
|
Machine Translation (F32)
|
100% |
503
77.5 IPS |
|
|
Machine Translation (F16)
|
100% |
514
79.3 IPS |
