samsung SM-G7810
Geekbench ML Score
1379
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | August 27 2024 10:04 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | samsung SM-G7810 |
| Model ID | samsung SM-G7810 |
| 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 | 7.44 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
930
99.6 IPS |
|
|
Image Classification (F16)
|
100% |
1460
156.4 IPS |
|
|
Image Classification (I8)
|
80% |
1354
145.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
2358
14.6 IPS |
|
|
Image Segmentation (F16)
|
100% |
3982
24.6 IPS |
|
|
Image Segmentation (I8)
|
89% |
3772
23.3 IPS |
|
|
Pose Estimation (F32)
|
100% |
1195
4.83 IPS |
|
|
Pose Estimation (F16)
|
100% |
2054
8.31 IPS |
|
|
Pose Estimation (I8)
|
80% |
2062
8.34 IPS |
|
|
Object Detection (F32)
|
100% |
923
32.4 IPS |
|
|
Object Detection (F16)
|
99% |
1197
42.0 IPS |
|
|
Object Detection (I8)
|
53% |
1234
43.3 IPS |
|
|
Face Detection (F32)
|
100% |
1720
19.8 IPS |
|
|
Face Detection (F16)
|
97% |
2820
32.4 IPS |
|
|
Face Detection (I8)
|
76% |
2606
29.9 IPS |
|
|
Text Classification (F32)
|
100% |
474
187.3 IPS |
|
|
Text Classification (F16)
|
98% |
551
218.0 IPS |
|
|
Machine Translation (F32)
|
100% |
549
84.6 IPS |
|
|
Machine Translation (F16)
|
100% |
555
85.5 IPS |
