samsung SM-G780G
Geekbench ML Score
424
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 22 2021 08:47 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | samsung SM-G780G |
| Model ID | samsung SM-G780G |
| Motherboard | kona |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 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 | 5.43 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
439
47.1 IPS |
|
|
Image Classification (F16)
|
100% |
413
44.2 IPS |
|
|
Image Classification (I8)
|
81% |
197
21.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
563
3.48 IPS |
|
|
Image Segmentation (F16)
|
100% |
559
3.46 IPS |
|
|
Image Segmentation (I8)
|
89% |
835
5.16 IPS |
|
|
Pose Estimation (F32)
|
100% |
255
1.03 IPS |
|
|
Pose Estimation (F16)
|
100% |
259
1.05 IPS |
|
|
Pose Estimation (I8)
|
80% |
235
0.95 IPS |
|
|
Object Detection (F32)
|
100% |
423
14.8 IPS |
|
|
Object Detection (F16)
|
100% |
462
16.2 IPS |
|
|
Object Detection (I8)
|
52% |
324
11.4 IPS |
|
|
Face Detection (F32)
|
100% |
660
7.58 IPS |
|
|
Face Detection (F16)
|
100% |
657
7.55 IPS |
|
|
Face Detection (I8)
|
75% |
559
6.43 IPS |
|
|
Text Classification (F32)
|
100% |
360
142.2 IPS |
|
|
Text Classification (F16)
|
100% |
340
134.6 IPS |
|
|
Machine Translation (F32)
|
100% |
560
86.4 IPS |
|
|
Machine Translation (F16)
|
100% |
543
83.6 IPS |
