samsung SM-F926B
Geekbench ML Score
350
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| User | vikarti |
| Upload Date | September 14 2024 06:22 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 | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
384
41.2 IPS |
|
|
Image Classification (F16)
|
100% |
400
42.8 IPS |
|
|
Image Classification (I8)
|
81% |
198
21.2 IPS |
|
|
Image Segmentation (F32)
|
100% |
496
3.07 IPS |
|
|
Image Segmentation (F16)
|
100% |
477
2.95 IPS |
|
|
Image Segmentation (I8)
|
89% |
663
4.09 IPS |
|
|
Pose Estimation (F32)
|
100% |
238
0.96 IPS |
|
|
Pose Estimation (F16)
|
100% |
243
0.98 IPS |
|
|
Pose Estimation (I8)
|
80% |
178
0.72 IPS |
|
|
Object Detection (F32)
|
100% |
285
10.0 IPS |
|
|
Object Detection (F16)
|
100% |
286
10.0 IPS |
|
|
Object Detection (I8)
|
52% |
262
9.21 IPS |
|
|
Face Detection (F32)
|
100% |
520
5.97 IPS |
|
|
Face Detection (F16)
|
100% |
499
5.73 IPS |
|
|
Face Detection (I8)
|
75% |
453
5.21 IPS |
|
|
Text Classification (F32)
|
100% |
265
104.8 IPS |
|
|
Text Classification (F16)
|
100% |
278
110.0 IPS |
|
|
Machine Translation (F32)
|
100% |
500
77.1 IPS |
|
|
Machine Translation (F16)
|
100% |
494
76.2 IPS |
