samsung SM-G7810
Geekbench ML Score
1359
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64
Result Information
| Upload Date | August 25 2024 09:51 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% |
924
99.1 IPS |
|
|
Image Classification (F16)
|
100% |
1458
156.2 IPS |
|
|
Image Classification (I8)
|
80% |
1275
136.7 IPS |
|
|
Image Segmentation (F32)
|
100% |
2344
14.5 IPS |
|
|
Image Segmentation (F16)
|
100% |
3970
24.5 IPS |
|
|
Image Segmentation (I8)
|
89% |
3714
22.9 IPS |
|
|
Pose Estimation (F32)
|
100% |
1199
4.85 IPS |
|
|
Pose Estimation (F16)
|
100% |
2059
8.33 IPS |
|
|
Pose Estimation (I8)
|
80% |
2035
8.24 IPS |
|
|
Object Detection (F32)
|
100% |
897
31.5 IPS |
|
|
Object Detection (F16)
|
99% |
1199
42.1 IPS |
|
|
Object Detection (I8)
|
53% |
1191
41.8 IPS |
|
|
Face Detection (F32)
|
100% |
1708
19.6 IPS |
|
|
Face Detection (F16)
|
97% |
2795
32.1 IPS |
|
|
Face Detection (I8)
|
76% |
2590
29.8 IPS |
|
|
Text Classification (F32)
|
100% |
476
188.3 IPS |
|
|
Text Classification (F16)
|
98% |
500
197.9 IPS |
|
|
Machine Translation (F32)
|
100% |
544
83.9 IPS |
|
|
Machine Translation (F16)
|
100% |
561
86.5 IPS |
